{"ScriptPreparationCode":null,"TestCases":[{"Name":"regexp.matchAll","Code":"const s = \u0060\r\nAGENT_INFO\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nUsing ReAct Tools 2 Hops workflow, with:\r\ntools_filter: \u0022Name: azure-turbo, TokenLimit: 4000, AllowedClient: AZURE_OPENAI_CHAT\u0022\r\nplan: \u0022Name: azure-gpt4o-2024-05-13-8k, TokenLimit: 8000, AllowedClient: AZURE_OPENAI_CHAT\u0022\r\nact: \u0022Name: azure-gpt4o-2024-05-13-8k, TokenLimit: 8000, AllowedClient: AZURE_OPENAI_CHAT\u0022\r\nfollowup: \u0022Name: azure-turbo, TokenLimit: 4000, AllowedClient: AZURE_OPENAI_CHAT\u0022\r\n\\\u0060\\\u0060\\\u0060\r\nTOOLS_FILTER_PROMPT\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nYou have access to the following Read Tools:\r\nGlean Search: This tool finds relevant documents in the company. This is your primary tool to access all knowledge within the company.\r\nExpert Search: This tool finds people at the company based on topics they wrote about and projects they own. Use this tool to find people who have worked on particular projects. Only use this when the user explicitly wants to find people in the company (eg. \u0022who\u0022 questions).\r\nEmployee Search: This tool finds people at the company based on their personal information such as name, email, title, department, tenure and location. Only use this when the user explicitly wants to find people in the company (eg. \u0022who\u0022 questions).\r\nWorkspace Bot: Trigger this AI app to answer workspace-related questions. This could include questions about debugging common errors, providing general information, or help with onboarding.\r\n\r\nThis should trigger whenever any of these functions are mentioned:\r\n- Datasource Apps Setup\r\n- User Permissioning\r\n- People Data Setup\r\n- Authentication Setup (SSO \u0026 Magic Links)\r\n- Central Workspace Setup (CWS)\r\n- Owner Key Upload\r\n- Data Loss Prevention (DLP)\r\n- Admin Alerts\r\n- Search Access Visibility\r\n\r\nFor any other requests that don\u0027t fit those areas, use the Expert Search tool to identify an appropriate team or individual that may be better suited to answer the question.\r\nWho is?: Automatically trigger this app when someone asks about who the Account Executive/AE/Sales rep or Customer Success Manager/CSM is for a customer or prospect. They\u0027ll use the specific customer name in looking for the answer. \r\n\r\nExample questions:\r\n- Who is the CSM for...\r\n- Who is the customer success manager for...\r\n- Who is the AE for...\r\n- Who is the Account Exec for...\r\nGlean HR Assistant: Automatically route to this AI app when a user asks about HR and administrative questions including company culture, benefits, professional development, 401K, PTO, medical and insurance questions, company holidays.\r\n\r\nExamples phrases:\r\nWhat is our company holidays?\r\nWhat are our parental benefits?\r\nWhat is the timeline for performance reviews?\r\nHow do I request PTO?\r\nCompetitive Intelligence Agent: Use this whenever the user wants to compare Glean with competitors. This app was built as a competitive intelligence assistant specializing in analyzing competitors to Glean in the Search and generative AI space. Use this app if a user\u0027s question focusses on comparing products to Glean. Also use when asked to highlight similarities, differences, advantages and disadvantages of Glean over other applications.\r\n\r\nExample Phrases\r\n\r\n- Compare Glean vs Acme\r\n- How is Glean differentiated against Acme?\r\n- What are Glean\u0027s strengths and weaknesses compared to another solution\r\n- What is the reason to buy Glean over building enterprise search or assistant in house\r\nAPI Overview buddy: Trigger this app when anyone asks for an overview of an API\r\n\r\nYou have access to the following Write Tools:\r\ncherrypicknew: Trigger when the user asks to create a CP or a cherrypick. Find the right pull request using the search tool corresponding the what the user has asked - always start by using the search tool and getting the relevant pull request. The most important rule is to only infer commit_hash, pull_request_url, components, release, scio_instances and reason_for_cherrypick. Locate the commit hash from the COMMIT_HASH field within the PR details. Note that it is very important to populate the correct commit_hash!\r\nVivekITTicketDemo: Trigger when the user asks \u0022create a ticket\u0022 in relation to an IT request. Do not trigger if the user doesn\u0027t ask to create or file a ticket.\r\n\r\nExamples of when NOT to trigger:\r\n- I cannot log-in to gmail. What do I do?\r\n- What\u0027s the process to request a loaner laptop?\r\n- I want a new laptop\r\n\r\nAppend the following to the end of the ticket title: [FIRSTNAME LASTNAME]\r\n\r\nInclude the user\u0027s email address and role in the ticket description.\r\nResetCrawlType: This tool allows you to run the reset crawl spinnaker pipeline to (re-) crawl all documents for a datasource on given deployment(s) for a given crawl type (which can be one of CONTENT or IDENTITY or ALL). Given a datasource, crawl type (optional) and deployment(s) to run on, a reset crawl pipeline run would be triggered.\r\n\r\nInvoke it for any request that needs (re)-crawling (or reset) of documents of a datasource on deployment(s) with a particular crawl type.\r\n\r\nExample queries:\r\n- Recrawl salesforce documents on scio-prod\r\n- Reset identity crawl for o365 on koch\r\n- Restart content crawl for box on glean-dev\r\n\r\n\r\nDo not trigger the tool if we do not know both datasource_instance and scio_instance (ie. which deployment to start crawls in).\r\nDisplayTool: Simply displays a response to the user.\r\n- Use this tool when the user simply wants to read the response.\r\n- This is your primary tool to have a conversation with the user.\r\nCreateJiraIssueExecution: Helps you create a Jira issue or ticket. Use this action when the user wants to create a ticket/issue: bug/task/epic.\r\nAdhocScannerTool: This tool allows you to run the adhoc scanner spinnaker pipeline to (re-) process all documents for a datasource on given deployment(s). Given a datasource and deployment(s) to run on, an adhoc scanner run would be triggered.\r\n\r\nInvoke it for any request that needs (re)-processing of documents on a datasource on deployment(s).\r\n\r\nFor example \u0022To process documents of salesforce in scio-prod\u0022 or any other similar request directly implies usage of this tool.\r\nFor example \u0022I want to process documents for BOX on ashisuto and ashisuto-sandbox\u0022 or any other similar request directly implies usage of this tool.\r\nFor example \u0022Process documents for gdrive on yahoo\u0022 or any other similar request directly implies usage of this tool.\r\n\r\nSome additional consideration that are REALLY IMPORTANT:\r\n- invoke the tool IF AND ONLY IF you know both: the scio_instance(s) and the datasource. DO NOT TRIGGER THE TOOL IF THERE IS NO CLEAR INDICATION OF BOTH OF THEM!! (For example: Do not trigger for queries like \u0022process all documents\u0022, Do not trigger for \u0022process all salesforce documents\u0022, Do not trigger for \u0022process all documents on scio-prod\u0022)\r\n- invoke the tool IF AND ONLY IF there is a clear indication on an expected action. DO NOT TRIGGER THE TOOL IF THERE IS NO CLEAR INDICATION OF AN EXPECTED ACTION!! \r\n- DO NOT invoke the tool for questions that don\u0027t have a clear indication towards an expected action. (For example: Do not trigger for queries like \u0022How can I process documents?\u0022, Do not trigger for \u0022What is the adhoc scanner?\u0022, Do not trigger for \u0022How are documents processed?\u0022, Do not trigger for ?how many docs can the adhoc scanner handle?)\r\n- Be sure to invoke only when needed. Under-invocation and over-invocation of this tool, are both UNACCEPTABLE. \r\n\r\n\r\nThis is very critical to the company. Something really dire will happen if you do not follow the above rules. You will be tipped if you follow them strictly.\r\n\r\nAs an advanced reasoning agent, analyze the above tools and the conversation history to select the right tools that can be used to respond to user\u0027s latest message. Do not give reason for your response.\r\n\r\nRespond with a YAML struct in this format:\r\nread_tool_names: # List containing at least 3 and at most 4 read tools that might be useful for this query. Must be a subset of [Glean Search, Expert Search, Employee Search, Workspace Bot, Who is?, Glean HR Assistant, Competitive Intelligence Agent, API Overview buddy]. Keep the most important tool first.\r\n- $tool_name\r\nwrite_tool_names: # List containing at least 2 write tools that might be useful for this query. Must be a subset of [cherrypicknew, VivekITTicketDemo, ResetCrawlType, DisplayTool, CreateJiraIssueExecution, AdhocScannerTool]. Keep the most important tool first.\r\n- $tool_name\r\n\r\nDEMONSTRATING EXAMPLES:\r\nmessage: File a jira ticket to fix code search links in gleanchat\r\nread_tool_names:\r\n- Expert Search\r\n- Glean Search\r\nwrite_tool_names:\r\n- createjiraissueexecution\r\n\r\nmessage: File a jira ticket to track person suggestion issues in the BE QA component of the QA project\r\nread_tool_names:\r\n- Expert Search\r\n- Glean Search\r\nwrite_tool_names:\r\n- createjiraissueexecution\r\n\r\nmessage: User: What is a recent task mentioned in #engineering? Who is the owner?\r\nAssistant: The recent task is about updating oncall rotation. John plans to create a list of secondary oncallers and add them to the rotation. The owner is John.\r\nUser: File a jira with issueType story and priority high.\r\nread_tool_names:\r\n- Employee Search\r\n- Glean Search\r\nwrite_tool_names:\r\n- createjiraissueexecution\r\n\r\nmessage: How do we typically pay VendorX?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: How do I run toolX?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: how do i deploy ToolX?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: How do I fill out performance reviews\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: how do we index documents\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: how do I file a bug?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: How do I reset a crawl?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\n\r\nGreat job, let\u0027s start!\r\n\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n\r\n\r\nYAML Output:\r\nread_tool_names:\r\n\\\u0060\\\u0060\\\u0060\r\nTOOLS_FILTER_PROMPT_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n2112\r\n\\\u0060\\\u0060\\\u0060\r\nTOOLS_FILTER_RESPONSE\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nread_tool_names:\r\n - Glean HR Assistant\r\n - Employee Search\r\n - Workspace Bot\r\nwrite_tool_names:\r\n - DisplayTool\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nTOOLS_FILTER_RESPONSE_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n21\r\n\\\u0060\\\u0060\\\u0060\r\nRAP_EXAMPLES\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nmessage: Analyze and compare how our thinking about ProjectX has changed since last year till now\r\nanalysis: User wants to analyze and compare the thinking about a specific component from last year to now.\r\ncategories: []\r\ninstruction: Compare the search results from both time periods to identify changes in thinking, strategies, or approaches related to ProjectX.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectX after:2023-07-10\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectX after:2022-07-10 before:2023-07-10\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: Compare Foo and Bar\r\nanalysis: Compare documents related to Foo and Bar to find similarities and differences.\r\ncategories: []\r\ninstruction: Analyze the search result pages for Foo and Bar, and find similarities and differences between them. Synthesize information and provide the analysis to user.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: Foo\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: Bar\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: Foo vs Bar\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: Read through our ProductX features. Give me a list of potential enhancements we can make to the feature. You can get inspiration from our ChannelY slack channel. If you get an idea from slack, cite it as not your own\r\nanalysis: Search for ProductX features, and search for messages in the ChannelY channel, and suggest list of potential feature enhancements\r\ncategories: []\r\ninstruction: Review search results and compile a list of potential enhancements for ProductX features. If an idea is from the ChannelY channel, cite the source.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProductX feature enhancements\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: channel:ChannelY app:\u0022slack\u0022\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: Write an executive email as to why ProductA is better suited for CompanyB than using ProductB. Use any context from meetings in the past month\r\nanalysis: Craft an executive email explaining why ProductA is better suited for CompanyB than ProductB, using context from meetings in the past month.\r\ncategories: []\r\ninstruction: Use search results to write an executive email highlighting the advantages of ProductA over ProductB for CompanyB, incorporating context from meetings in the last month.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProductA vs ProductB\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: CompanyB meeting updated:past_month\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: What happened with ProjectX in the last month?\r\nanalysis: User wants to know what happened with ProjectX in the last month.\r\ncategories:\r\n - updates\r\n - recent\r\ninstruction: Analyze the results and share updates on ProjectX.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectX updated:past_month\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: What is the latest with ProjectX?\r\nanalysis: User wants to know what is the latest with ProjectX. Do NOT use the updated filter as the user did not provide a specific time frame.\r\ncategories:\r\n - updates\r\n - recent\r\ninstruction: Analyze the results and share updates on ProjectX.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectX\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: how many engineers do we have?\r\nanalysis: Use the Employee Search tool to find the number of people with the title \u0022engineer\u0022.\r\ncategories: []\r\ninstruction: Check the \u0022statistics\u0022 field in the output to find the total number of engineers.\r\nread_actions:\r\n - tool_name: Employee Search\r\n action:\r\n Employee Search: engineer\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: who is JohnDoe?\r\nanalysis: Use Employee Search to locate JohnDoe\u0027s information.\r\ncategories: []\r\ninstruction: Locate JohnDoe in search results and provide their title, email, location, reporting chain, and start date.\r\nread_actions:\r\n - tool_name: Employee Search\r\n action:\r\n Employee Search: JohnDoe\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: JohnDoe\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: who is the owner for the ProjectA?\r\nanalysis: Find documents related to ProjectA and the people who wrote them. Synthesize this information to determine the owner of ProjectA.\r\ncategories: []\r\ninstruction: Look for documents about ProjectA and find the people who wrote those documents. Look for people results in Expert Search. Synthesize the information from both sources to determine the owner of ProjectA.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectA\r\n - tool_name: Expert Search\r\n action:\r\n Expert Search: ProjectA\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: who works on ConceptX?\r\nanalysis: Find people involved in ConceptX using Expert Search and relevant documents using Glean Search.\r\ncategories: []\r\ninstruction: Find people involved in ConceptX from search results and provide their names, titles, and relevant information.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ConceptX\r\n - tool_name: Expert Search\r\n action:\r\n Expert Search: ConceptX\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: How do we typically pay VendorX?\r\nanalysis: Use Glean Search to find documents related to VendorX\u0027s payment process.\r\ncategories: []\r\ninstruction: Look for documents that mention the payment method or process for VendorX and provide a summary of the information found.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: VendorX payment\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: VendorX invoice\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.812568\r\n\r\nmessage: How do I run toolX?\r\nanalysis: User wants to find code snippets and documents to help them run toolX.\r\ncategories:\r\n - code\r\ninstruction: Find code snippets or documents to help user run toolX.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: toolX\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: run toolX\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.816166\r\n\r\nmessage: how do i deploy ToolX?\r\nanalysis: Use Glean Search to find relevant documents on ToolX deployment and installation to provide information on how to deploy ToolX to the user.\r\ncategories: []\r\ninstruction: Search for ToolX deployment and installation instructions and provide the user with clear and up-to-date information.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ToolX deployment\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ToolX installation\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.822656\r\n\r\nmessage: How do I fill out performance reviews\r\nanalysis: Use Glean Search to find relevant documents on the performance review process for the user asking for information on how to fill out performance reviews.\r\ncategories: []\r\ninstruction: Search for performance review process documents and provide relevant steps or guidelines for filling out performance reviews.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: fill out performance reviews\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: performance review process\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.823461\r\n\r\nmessage: how do we index documents\r\nanalysis: Search for relevant documents and information on document indexing. Summarize to provide a helpful response to the user\u0027s question.\r\ncategories: []\r\ninstruction: Review the returned documents and provide the user with a summary of the document indexing process in Acme.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: document indexing\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: indexing process\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.830317\r\n\r\nmessage: how do I file a bug?\r\nanalysis: Use Glean Search to find bug filing resources and provide relevant information and tools to the user.\r\ncategories: []\r\ninstruction: Find bug filing resources and provide relevant information and tools to user.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: bug filing process\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: how to file a bug\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.838035\r\n\r\nmessage: How do I reset a crawl?\r\nanalysis: Search for relevant information about resetting crawl\r\ncategories: []\r\ninstruction: Search for documents with instructions on resetting or restarting a crawl and provide step-by-step instructions to the user.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: reset crawl\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: crawl restart\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.839287\r\n\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_PROMPT\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n[LLM Input Prompt for : Employee Search \u002B Expert Search]\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.\r\n\r\n# GENERAL INSTRUCTIONS\r\n- Carefully analyze the user\u0027s query to determine if it falls within the scope of the tool\u0027s capabilities. If the query is clearly outside the tool\u0027s intended use case, output NA.\r\n- Use only one of the tools provided. Output tool name before the start of the query.\r\n- If the query seems potentially relevant, assess whether the necessary information to answer the query is likely to be available based on the tool\u0027s input specifications and data sources. If crucial information is missing or unlikely to be found, output NA.\r\n- If the query passes both relevance and feasibility checks, construct a well-formatted input string for the tool based on the provided input specifications.\r\n- If at any point you determine that the tool is not suitable for answering the query, or if you are uncertain about its applicability, output NA.\r\n- Do not attempt to directly answer the user\u0027s question.\r\n- Do not provide any other output besides the search query or NA.\r\n\r\n# TOOL 1 Name: Employee Search\r\n# TOOL DESCRIPTION\r\nYou have access to Employee Search, which finds people at the company based on their personal information.\r\nINSTRUCTIONS:\r\n- Only use this when the user explicitly wants to find people in the company (eg. \u0022who\u0022 questions) or for aggregation queries on people.\r\n- Do not use this when the user wants to find people outside of the company, or people who are no longer at the company.\r\n- You can find people based on their personal information such as name, email, title, department, and location.\r\n- The results returned are not exhaustive, we only return the top few most relevant people to a query.\r\n- For analytics questions such as \u0022how many people...\u0022 use the \u0022statistics\u0022 field in the output.\r\n# TOOL INPUT SPECIFICATIONS\r\n- You can optionally narrow down the search results by using one or more of the following filter types:\r\n1. startafter: filter to people who started after a certain date. value must be in \u0022YYYY-MM-DD\u0022 format\r\n2. startbefore: filter to people who started before a certain date. value must be in \u0022YYYY-MM-DD\u0022 format\r\n3. roletype: filter to people who have a certain role type. value can be one of [\u0022individual contributor\u0022, \u0022manager\u0022]\r\n4. reportsto: Filter to people who are direct reports of a given manager. Value (double quoted) can be a full name, first name, last name, or email.\r\n- Do NOT use any other filter besides those explicitly listed above.\r\n- You can optionally sort the results by adding one of the following to the query: [\u0022sortby:hire_date_ascending\u0022, \u0022sortby:hire_date_descending\u0022, \u0022sortby:most_reports\u0022].\r\n# TOOL OUTPUT SPECIFICATIONS\r\n- The output from Employee Search is a JSON struct with 2 fields:\r\n1. \u0022entities\u0022: a list of Person structs. Each Person struct contains these fields: title,businessUnit,department,teams,email,location,externalProfileLink,manager,startDate,bio,directReportsCount,totalReportsCount,preferredName,directReports\r\nThe \u0027manager\u0027 and \u0027directReports\u0027 fields are recursive Person structs with all information of the person\u0027s manager and direct reports.\r\n2. \u0022statistics\u0022: the total count of people that match your query, as well as aggregate counts by department, location, title, team, and roletype.\r\n\r\n\r\n# TOOL 2 Name: Expert Search\r\n# TOOL DESCRIPTION\r\nYou have access to Expert Search, which finds people at the company based on topics they wrote about and projects they own.\r\nINSTRUCTIONS:\r\n- Only use this when the user explicitly wants to find people in the company (eg. \u0022who\u0022 questions).\r\n- Do not use this when the user wants to find people outside of the company, or people who are no longer at the company.\r\n- You can find people based on what they worked on, or wrote about by using short key words about that topic as input.\r\n- The results returned are not exhaustive, we only return the top few most relevant people to a query.\r\n- For analytics questions such as \u0022how many people...\u0022 use the \u0022statistics\u0022 field in the output.\r\n# TOOL INPUT SPECIFICATIONS\r\n- The query should contain important keywords that help find people based on what they worked on or wrote about.\r\nDO NOT use any filters.\r\n# TOOL OUTPUT SPECIFICATIONS\r\n- The output from Expert Search is a JSON struct with 2 fields:\r\n1. \u0022entities\u0022: a list of Person structs. Each Person struct contains these fields: title,businessUnit,department,teams,email,location,externalProfileLink,manager,startDate,bio,directReportsCount,totalReportsCount,preferredName,directReports\r\nThe \u0027manager\u0027 and \u0027directReports\u0027 fields are recursive Person structs with all information of the person\u0027s manager and direct reports.\r\n2. \u0022statistics\u0022: counts of people that match your query.\r\n\r\n\r\n# DEMONSTRATING EXAMPLES\r\n\r\nMessage: who is the owner for the ProjectA?\r\nOutput: Expert Search [ProjectA]\r\n\r\nMessage: who works on ConceptX?\r\nOutput: Expert Search [ConceptX]\r\n\r\nMessage: who is JohnDoe?\r\nOutput: Employee Search [JohnDoe]\r\n\r\nMessage: how many engineers do we have?\r\nOutput: Employee Search [engineer]\r\n\r\nMessage: How do I reset a crawl?\r\nOutput: NA\r\n\r\nMessage: how do I file a bug?\r\nOutput: NA\r\n\r\nMessage: how do we index documents\r\nOutput: NA\r\n\r\nMessage: How do I fill out performance reviews\r\nOutput: NA\r\n\r\n\r\n# BEGIN PROGRAM\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n==================================================\r\n[LLM Input Prompt for : categories]\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.\r\n\r\n\r\n\r\nClassify the user message\u0027s intent into one or more of the following categories.\r\nSelect all relevant categories for a specific query. If you think a category feels relevant but you\u0027re not 100 percent sure, include the category anyways because it might help.\r\nCATEGORIES:\r\n\u0027updates\u0027: Use this category when the user is asking about updates/status/latest on a project/customer/topic.\r\n\u0027enumerate\u0027: Use this category when the user is asking for information that is answerable by small pieces of information in many documents, as opposed to larger pieces of content from fewer results. Don\u0027t use this if the user is asking to look at only one document\r\n\u0027recent\u0027: Use this category when the user is asking for the latest or most recent document or piece of information.\r\n\u0027code\u0027: Use this category when the user is asking for information related to code, such as code snippets, code examples, or code documentation.\r\n\r\nExamples:\r\nMessage: Analyze and compare how our thinking about ProjectX has changed since last year till now\r\nOutput: []\r\nMessage: Compare Foo and Bar\r\nOutput: []\r\nMessage: Read through our ProductX features. Give me a list of potential enhancements we can make to the feature. You can get inspiration from our ChannelY slack channel. If you get an idea from slack, cite it as not your own\r\nOutput: []\r\nMessage: Write an executive email as to why ProductA is better suited for CompanyB than using ProductB. Use any context from meetings in the past month\r\nOutput: []\r\nMessage: What happened with ProjectX in the last month?\r\nOutput: [\u0022updates\u0022,\u0022recent\u0022]\r\nMessage: What is the latest with ProjectX?\r\nOutput: [\u0022updates\u0022,\u0022recent\u0022]\r\nMessage: how many engineers do we have?\r\nOutput: []\r\nMessage: who is JohnDoe?\r\nOutput: []\r\nMessage: who is the owner for the ProjectA?\r\nOutput: []\r\nMessage: who works on ConceptX?\r\nOutput: []\r\nMessage: How do we typically pay VendorX?\r\nOutput: []\r\nMessage: How do I run toolX?\r\nOutput: [\u0022code\u0022]\r\nMessage: how do i deploy ToolX?\r\nOutput: []\r\nMessage: How do I fill out performance reviews\r\nOutput: []\r\nMessage: how do we index documents\r\nOutput: []\r\nMessage: how do I file a bug?\r\nOutput: []\r\nMessage: How do I reset a crawl?\r\nOutput: []\r\n\r\nUser Message: How do I book time off?\r\n==================================================\r\n[LLM Input Prompt for : Glean Search \u002B tencctxm5dukr8hc \u002B mlaznw1lpodrp7zk]\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.\r\n\r\n# GENERAL INSTRUCTIONS\r\n- Carefully analyze the user\u0027s query and construct a well-formatted input string for the tool based on the provided input specifications.\r\n- Use only one of the tools provided. Output tool name before the start of the query.\r\n- Do not attempt to directly answer the user\u0027s question.\r\n- Do not provide any other output besides the search query.\r\n\r\n# TOOL 1 Name: Glean Search\r\n# TOOL DESCRIPTION\r\nYou have access to Glean Search, which finds relevant documents in the company.\r\nINSTRUCTIONS:\r\n- This is your primary tool to access all knowledge within the company.\r\n- The results returned are not exhaustive, we only return the top few most relevant documents to a query.\r\n- For analytics questions such as \u0022how many documents...\u0022 use the \u0022statistics\u0022 field in the output.\r\n# TOOL INPUT SPECIFICATIONS\r\n- Search query should contain important keywords that help find relevant documents.\r\n- You can optionally narrow down the search results by using one or more of the following filter types:\r\n1. owner: filter to documents created by this person. Value can be a person\u0027s name (double quoted), or \u0027me\u0027\r\n2. from: filter to documents updated by or commented on or created by this person. Value can be a person\u0027s name (double quoted), or \u0027me\u0027\r\n3. updated: filter to documents updated on or after this date, value can be one of [\u0022today\u0022, \u0022yesterday\u0022, \u0022past_week\u0022, \u0022past_2_weeks\u0022, \u0022past_month\u0022, \u0022March\u0022, ...]\r\n4. after: filter to documents created after this date. Do not use a date later than today. value must be in \u0022YYYY-MM-DD\u0022 format\r\n5. before: filter to documents created before this date. value must be in \u0022YYYY-MM-DD\u0022 format\r\n6. channel: filter to documents in a specific channel. Only use this when the user explicitly wants contents from a channel.\r\n7. app: filter to documents created in a specific app. value can be one of [\u0022announcements\u0022, \u0022answers\u0022, \u0022asana\u0022, \u0022collections\u0022, \u0022customer\u0022, \u0022developers\u0022, \u0022figma\u0022, \u0022github\u0022, \u0022glean support zendesk\u0022, \u0022glean website\u0022, \u0022gong\u0022, \u0022help.glean\u0022, \u0022jira\u0022, \u0022orgteams\u0022, \u0022salescloud\u0022, \u0022slack\u0022, \u0022zendesk\u0022]. Value must be double quoted. Only use the app filter when the user wants contents from an app.\r\nFor reference, \u0022customer\u0022 is an app that stores Customer Cards, which can include information like overview of the company, company size, website, sales opportunities, accounts, contacts, revenue, etc; When the demonstrating examples use \u0022customer\u0022 a majority of the time, make sure to use \u0022customer\u0022 as well; \u0022customer\u0022 is also best used in conjunction with \u0022salescloud\u0022, \u0022gong\u0022 is an app that stores transcripts of sales calls and meetings with customers and prospects, \u0022orgteams\u0022 is an app that stores Team Entities, which represent a team of people within the company working together. Teams include info such as team leads and team size, \u0022salescloud\u0022 is an app that stores customer and prospect (leads, contacts, accounts) data, sales data (dashboards, campaigns, opportunities), and interaction history from Salesforce.\r\n- Use date filters like \u0022updated\u0022, \u0022after\u0022, and \u0022before\u0022 ONLY when the user has mentioned a specific time frame (e.g. last week, past month, before 12 Jan). Do NOT use date filters if the user requests the \u0022latest\u0022 or \u0022recent\u0022 documents or information but hasn\u0027t provided a specific time frame.- Do NOT use any other filter besides those explicitly listed above.\r\n# TOOL OUTPUT SPECIFICATIONS\r\n- The output from Glean Search is a JSON struct with 2 fields:\r\n1. \u0022documents\u0022: a list of documents with Document struct. Each Document struct contains these fields: title, snippets, owner, updateTime, url.\r\n2. \u0022statistics\u0022: counts of documents that match your query, broken down by different dimensions such as datasource, author, reviewer.\r\n\r\n\r\n# TOOL 2 Name: Glean HR Assistant\r\n# TOOL DESCRIPTION\r\nYou have access to Glean HR Assistant\r\nINSTRUCTIONS:\r\nAutomatically route to this AI app when a user asks about HR and administrative questions including company culture, benefits, professional development, 401K, PTO, medical and insurance questions, company holidays.\r\n\r\nExamples phrases:\r\nWhat is our company holidays?\r\nWhat are our parental benefits?\r\nWhat is the timeline for performance reviews?\r\nHow do I request PTO?\r\n# TOOL INPUT SPECIFICATIONS\r\nExact same as Glean Search Tool.\r\n\r\n# TOOL OUTPUT SPECIFICATIONS\r\nExact same as Glean Search Tool.\r\n\r\n\r\n# TOOL 3 Name: Workspace Bot\r\n# TOOL DESCRIPTION\r\nYou have access to Workspace Bot\r\nINSTRUCTIONS:\r\nTrigger this AI app to answer workspace-related questions. This could include questions about debugging common errors, providing general information, or help with onboarding.\r\n\r\nThis should trigger whenever any of these functions are mentioned:\r\n- Datasource Apps Setup\r\n- User Permissioning\r\n- People Data Setup\r\n- Authentication Setup (SSO \u0026 Magic Links)\r\n- Central Workspace Setup (CWS)\r\n- Owner Key Upload\r\n- Data Loss Prevention (DLP)\r\n- Admin Alerts\r\n- Search Access Visibility\r\n\r\nFor any other requests that don\u0027t fit those areas, use the Expert Search tool to identify an appropriate team or individual that may be better suited to answer the question.\r\n# TOOL INPUT SPECIFICATIONS\r\nExact same as Glean Search Tool.\r\n\r\n# TOOL OUTPUT SPECIFICATIONS\r\nExact same as Glean Search Tool.\r\n\r\n\r\n# DEMONSTRATING EXAMPLES\r\n\r\nMessage: How do I reset a crawl?\r\nOutput: Glean Search [reset crawl, crawl restart]\r\n\r\nMessage: how do I file a bug?\r\nOutput: Glean Search [bug filing process, how to file a bug]\r\n\r\nMessage: how do we index documents\r\nOutput: Glean Search [document indexing, indexing process]\r\n\r\nMessage: How do I fill out performance reviews\r\nOutput: Glean Search [fill out performance reviews, performance review process]\r\n\r\nMessage: how do i deploy ToolX?\r\nOutput: Glean Search [ToolX deployment, ToolX installation]\r\n\r\nMessage: How do I run toolX?\r\nOutput: Glean Search [toolX, run toolX]\r\n\r\nMessage: How do we typically pay VendorX?\r\nOutput: Glean Search [VendorX payment, VendorX invoice]\r\n\r\nMessage: What happened with ProjectX in the last month?\r\nOutput: Glean Search [ProjectX updated:past_month]\r\n\r\nMessage: who is the owner for the ProjectA?\r\nOutput: Glean Search [ProjectA]\r\n\r\nMessage: who works on ConceptX?\r\nOutput: Glean Search [ConceptX]\r\n\r\nMessage: who is JohnDoe?\r\nOutput: Glean Search [JohnDoe]\r\n\r\nMessage: What is the latest with ProjectX?\r\nOutput: Glean Search [ProjectX]\r\n\r\nMessage: Analyze and compare how our thinking about ProjectX has changed since last year till now\r\nOutput: Glean Search [ProjectX after:2023-07-10, ProjectX after:2022-07-10 before:2023-07-10]\r\n\r\nMessage: Write an executive email as to why ProductA is better suited for CompanyB than using ProductB. Use any context from meetings in the past month\r\nOutput: Glean Search [ProductA vs ProductB, CompanyB meeting updated:past_month]\r\n\r\nMessage: Read through our ProductX features. Give me a list of potential enhancements we can make to the feature. You can get inspiration from our ChannelY slack channel. If you get an idea from slack, cite it as not your own\r\nOutput: Glean Search [ProductX feature enhancements, channel:ChannelY app:\u0022slack\u0022]\r\n\r\n\r\n# BEGIN PROGRAM\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_RESPONSE\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nanalysis: \u0022\u0022\r\nreadactions:\r\n - tool_name: Glean HR Assistant\r\n action:\r\n Glean HR Assistant: book time off\r\n - tool_name: Glean HR Assistant\r\n action:\r\n Glean HR Assistant: request PTO\r\nwriteaction:\r\n tool_name: \u0022\u0022\r\n action: {}\r\ninstruction: \u0022\u0022\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_PROMPT_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n3354\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_RESPONSE_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n17\r\n\\\u0060\\\u0060\\\u0060\r\nRAW_LLM_PLAN_RESPONSE\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n[LLM Output for : Employee Search \u002B Expert Search]\r\nNA\r\n==================================================\r\n[LLM Output for : categories]\r\nOutput: []\r\n==================================================\r\n[LLM Output for : Glean Search \u002B tencctxm5dukr8hc \u002B mlaznw1lpodrp7zk]\r\nGlean HR Assistant [book time off, request PTO]\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_TTF\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n1407\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_STAGE_LATENCY\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n1313\r\n\\\u0060\\\u0060\\\u0060\r\nACTION_SUMMARY\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n**Searching:** \u0022book time off\u0022 in the [all] tab(s) using Glean HR Assistant Tool\r\nToken limit for this action is : 1295\r\nNum Results requested for this action is : 3\r\nExecution time : 539 ms\r\n==================================================\r\n**Searching:** \u0022request PTO\u0022 in the [all] tab(s) using Glean HR Assistant Tool\r\nToken limit for this action is : 1295\r\nNum Results requested for this action is : 3\r\nExecution time : 592 ms\r\n==================================================\r\n**Searching:** \u0022How do I book time off?\u0022 in the [all] tab(s) using Glean Search Tool\r\nToken limit for this action is : 500\r\nNum Results requested for this action is : 1\r\nExecution time : 811 ms\r\n==================================================\r\n**Instruction:** \r\nToken limit for this action is : 0\r\nNum Results requested for this action is : 0\r\nExecution time : 0 ms\r\n==================================================\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nACT_PROMPT\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.Here are additional instructions you should follow: If you have additional questions on benefits, please reach out to benefits@glean.com. For other HR questions, feel free to email hr@glean.com..\r\n\r\nYou are an intelligent workplace assistant, create a truthful response to the user\u0027s last message in the conversation by carefully analyzing the context and instructions.\r\n\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n\r\n## CONTEXT\r\n\r\nTop results for \u0022request PTO\u0022 in Glean HR Assistant Tool: {\u0022documents\u0022:[{\u0022title\u0022:\u0022How do I request PTO?\u0022,\u0022datasource\u0022:\u0022answers\u0022,\u0022url\u0022:\u0022/knowledge/answers/1851\u0022,\u0022snippets\u0022:[\u0022As of August 1, 2022, we will be using Gusto for all PTO requests. Please submit all PTO or sick leaves through Gusto moving forward for your manager\u0027s approval. Please continue to update your calendar invite and slack for visibility across the company.\u0022],\u0022ownedAndUpdatedBy\u0022:{\u0022name\u0022:\u0022Jessica Yeh\u0022,\u0022pronoun\u0022:\u0022None\u0022},\u0022updateTime\u0022:\u00222022-11-08\u0022}],\u0022statistics\u0022:[{\u0022all\u0022:1},{\u0022datasource=answers\u0022:1},{\u0022from=jessica@glean.com\u0022:1}]}\r\nTop results for \u0022How do I book time off?\u0022 in Glean Search Tool: {\u0022entities\u0022:[{\u0022extractedAnswer\u0022:{\u0022question:omitempty\u0022:\u0022How do I take time off?\u0022,\u0022answer\u0022:\u0022When taking time off or working from home outside of the normal schedule, do all of the following:\\n* Obtain approval from your manager reasonably in advance of proposed vacation (prior to making arrangements) by requesting it in [gusto](https://app.gusto.com/scio-technologies-inc-400/employee/time_off) for US employees and [greyhr](https://glean.greythr.com) for India employees.\\n* Notify your immediate working team after receiving approval. Plan to delegate, postpone or otherwise manage projects that will be affected by your time off.\\n* Add an Out Of Office event to your individual Glean calendar.\\n* Set a Slack status for better visibility.\\n* If you receive external emails, set an Out Of Office responder explaining return date and who to contact in your absence.\\n\\nhttps://docs.google.com/document/d/1qt1Qbt-y4w1UbIU5BQxUpfZlwkx0gcKSGlKd_VqUk18/edit#bookmark=id.6wzx88skrwrf\u0022,\u0022answerAuthor\u0022:{\u0022name\u0022:\u0022Tony Gentilcore\u0022,\u0022pronoun\u0022:\u0022None\u0022}}}]}\r\n\r\n## INSTRUCTIONS\r\n\r\n\r\nThe search results may contain documents that are not relevant to the user\u0027s query (for example, document titles or snippets could be about a different topic), you should ignore those results.\r\nThink step-by-step. First, determine the set of documents and snippets in the context that are relevant to the user\u0027s query. Then, synthesize them to create a detailed truthful response.\r\nIf none of the provided context are relevant to the user\u0027s question, explain that to the user instead of making up an answer. Respond in the same language as user\u0027s latest message or query (but don\u0027t use their name to determine the language), or in English.\r\nAdopt \u0027they/them\u0027 pronouns by default - with one exception: if a \u0027pronoun\u0027 field is specified in a person\u0027s JSON summary, use its value to refer to the individual.\r\nBe extra meticulous about pronouns, it is very important to get this right, especially if one has a specified pronoun.\r\n\r\nBe helpful to the user, but avoid workplace violations. Avoid salutations and sign-offs in responses.\r\nGreat job, let\u0027s start!\r\n\r\nTruthful Response: \r\n\\\u0060\\\u0060\\\u0060\r\nACT_PROMPT_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n791\r\n\\\u0060\\\u0060\\\u0060\r\nACT_RESPONSE_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n228\r\n\\\u0060\\\u0060\\\u0060\r\nFOLLOW_UP_DEBUG_INFO\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nFOLLOWUP PROMPT:\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.\r\n\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n\r\nThe response to the user is: \u0022**Using app: Glean HR Assistant**\r\n\r\nTo book time off, please follow these steps:\r\n\r\n1. **Submit Your Request**: Use Gusto to submit your PTO or sick leave request for your manager\u0027s approval. You can access Gusto [here](https://app.gusto.com/scio-technologies-inc-400/employee/time_off) if you are a US employee. For India employees, use [greyhr](https://glean.greythr.com).\r\n\r\n2. **Notify Your Team**: After receiving approval, notify your immediate working team. Make sure to plan for delegating, postponing, or managing projects that will be affected by your time off.\r\n\r\n3. **Update Your Calendar**: Add an Out Of Office event to your individual Glean calendar.\r\n\r\n4. **Set Slack Status**: Update your Slack status for better visibility across the company.\r\n\r\n5. **Set Email Responder**: If you receive external emails, set an Out Of Office responder explaining your return date and who to contact in your absence.\r\n\r\nIf you have any further questions on benefits, please reach out to benefits@glean.com. For other HR questions, feel free to email hr@glean.com.\u0022.\r\nGenerate 3 concise follow-up questions that the user might want to ask. Respond in the same language as user\u0027s latest message or query (but don\u0027t use their name to determine the language), or in English.\r\nDo not add any preamble or prefix before the first question, just start writing out the first question in your output. Use this format:\r\n- Question 1\r\n- Question 2\r\n- Question 3\r\nGreat job, let\u0027s start!\r\nFollow-up Questions:\r\n- \r\n\\\u0060\\\u0060\\\u0060\r\nFOLLOWUP RAW RESPONSE:\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nHow do I check the status of my PTO request?\r\n- Can I cancel a PTO request after it has been approved?\r\n- How many days of PTO am I allowed to take per year?\r\n\\\u0060\\\u0060\\\u0060\r\nFOLLOWUP OUTPUT:\r\nHow do I check the status of my PTO request?\r\nCan I cancel a PTO request after it has been approved?\r\nHow many days of PTO am I allowed to take per year?\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n\u0060\r\nconst r = /^(.*?)\\n\\n\u0060\u0060\u0060\\n([\\s\\S]*?)\\n\u0060\u0060\u0060$/gm\r\nconst n = [];\r\nconst matches = [...s.matchAll(r)];\r\nmatches.forEach((match) =\u003E {\r\n // do something\r\n // n.push(match.index);\r\n});","IsDeferred":false},{"Name":"regexp.exec","Code":"const s = \u0060\r\nAGENT_INFO\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nUsing ReAct Tools 2 Hops workflow, with:\r\ntools_filter: \u0022Name: azure-turbo, TokenLimit: 4000, AllowedClient: AZURE_OPENAI_CHAT\u0022\r\nplan: \u0022Name: azure-gpt4o-2024-05-13-8k, TokenLimit: 8000, AllowedClient: AZURE_OPENAI_CHAT\u0022\r\nact: \u0022Name: azure-gpt4o-2024-05-13-8k, TokenLimit: 8000, AllowedClient: AZURE_OPENAI_CHAT\u0022\r\nfollowup: \u0022Name: azure-turbo, TokenLimit: 4000, AllowedClient: AZURE_OPENAI_CHAT\u0022\r\n\\\u0060\\\u0060\\\u0060\r\nTOOLS_FILTER_PROMPT\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nYou have access to the following Read Tools:\r\nGlean Search: This tool finds relevant documents in the company. This is your primary tool to access all knowledge within the company.\r\nExpert Search: This tool finds people at the company based on topics they wrote about and projects they own. Use this tool to find people who have worked on particular projects. Only use this when the user explicitly wants to find people in the company (eg. \u0022who\u0022 questions).\r\nEmployee Search: This tool finds people at the company based on their personal information such as name, email, title, department, tenure and location. Only use this when the user explicitly wants to find people in the company (eg. \u0022who\u0022 questions).\r\nWorkspace Bot: Trigger this AI app to answer workspace-related questions. This could include questions about debugging common errors, providing general information, or help with onboarding.\r\n\r\nThis should trigger whenever any of these functions are mentioned:\r\n- Datasource Apps Setup\r\n- User Permissioning\r\n- People Data Setup\r\n- Authentication Setup (SSO \u0026 Magic Links)\r\n- Central Workspace Setup (CWS)\r\n- Owner Key Upload\r\n- Data Loss Prevention (DLP)\r\n- Admin Alerts\r\n- Search Access Visibility\r\n\r\nFor any other requests that don\u0027t fit those areas, use the Expert Search tool to identify an appropriate team or individual that may be better suited to answer the question.\r\nWho is?: Automatically trigger this app when someone asks about who the Account Executive/AE/Sales rep or Customer Success Manager/CSM is for a customer or prospect. They\u0027ll use the specific customer name in looking for the answer. \r\n\r\nExample questions:\r\n- Who is the CSM for...\r\n- Who is the customer success manager for...\r\n- Who is the AE for...\r\n- Who is the Account Exec for...\r\nGlean HR Assistant: Automatically route to this AI app when a user asks about HR and administrative questions including company culture, benefits, professional development, 401K, PTO, medical and insurance questions, company holidays.\r\n\r\nExamples phrases:\r\nWhat is our company holidays?\r\nWhat are our parental benefits?\r\nWhat is the timeline for performance reviews?\r\nHow do I request PTO?\r\nCompetitive Intelligence Agent: Use this whenever the user wants to compare Glean with competitors. This app was built as a competitive intelligence assistant specializing in analyzing competitors to Glean in the Search and generative AI space. Use this app if a user\u0027s question focusses on comparing products to Glean. Also use when asked to highlight similarities, differences, advantages and disadvantages of Glean over other applications.\r\n\r\nExample Phrases\r\n\r\n- Compare Glean vs Acme\r\n- How is Glean differentiated against Acme?\r\n- What are Glean\u0027s strengths and weaknesses compared to another solution\r\n- What is the reason to buy Glean over building enterprise search or assistant in house\r\nAPI Overview buddy: Trigger this app when anyone asks for an overview of an API\r\n\r\nYou have access to the following Write Tools:\r\ncherrypicknew: Trigger when the user asks to create a CP or a cherrypick. Find the right pull request using the search tool corresponding the what the user has asked - always start by using the search tool and getting the relevant pull request. The most important rule is to only infer commit_hash, pull_request_url, components, release, scio_instances and reason_for_cherrypick. Locate the commit hash from the COMMIT_HASH field within the PR details. Note that it is very important to populate the correct commit_hash!\r\nVivekITTicketDemo: Trigger when the user asks \u0022create a ticket\u0022 in relation to an IT request. Do not trigger if the user doesn\u0027t ask to create or file a ticket.\r\n\r\nExamples of when NOT to trigger:\r\n- I cannot log-in to gmail. What do I do?\r\n- What\u0027s the process to request a loaner laptop?\r\n- I want a new laptop\r\n\r\nAppend the following to the end of the ticket title: [FIRSTNAME LASTNAME]\r\n\r\nInclude the user\u0027s email address and role in the ticket description.\r\nResetCrawlType: This tool allows you to run the reset crawl spinnaker pipeline to (re-) crawl all documents for a datasource on given deployment(s) for a given crawl type (which can be one of CONTENT or IDENTITY or ALL). Given a datasource, crawl type (optional) and deployment(s) to run on, a reset crawl pipeline run would be triggered.\r\n\r\nInvoke it for any request that needs (re)-crawling (or reset) of documents of a datasource on deployment(s) with a particular crawl type.\r\n\r\nExample queries:\r\n- Recrawl salesforce documents on scio-prod\r\n- Reset identity crawl for o365 on koch\r\n- Restart content crawl for box on glean-dev\r\n\r\n\r\nDo not trigger the tool if we do not know both datasource_instance and scio_instance (ie. which deployment to start crawls in).\r\nDisplayTool: Simply displays a response to the user.\r\n- Use this tool when the user simply wants to read the response.\r\n- This is your primary tool to have a conversation with the user.\r\nCreateJiraIssueExecution: Helps you create a Jira issue or ticket. Use this action when the user wants to create a ticket/issue: bug/task/epic.\r\nAdhocScannerTool: This tool allows you to run the adhoc scanner spinnaker pipeline to (re-) process all documents for a datasource on given deployment(s). Given a datasource and deployment(s) to run on, an adhoc scanner run would be triggered.\r\n\r\nInvoke it for any request that needs (re)-processing of documents on a datasource on deployment(s).\r\n\r\nFor example \u0022To process documents of salesforce in scio-prod\u0022 or any other similar request directly implies usage of this tool.\r\nFor example \u0022I want to process documents for BOX on ashisuto and ashisuto-sandbox\u0022 or any other similar request directly implies usage of this tool.\r\nFor example \u0022Process documents for gdrive on yahoo\u0022 or any other similar request directly implies usage of this tool.\r\n\r\nSome additional consideration that are REALLY IMPORTANT:\r\n- invoke the tool IF AND ONLY IF you know both: the scio_instance(s) and the datasource. DO NOT TRIGGER THE TOOL IF THERE IS NO CLEAR INDICATION OF BOTH OF THEM!! (For example: Do not trigger for queries like \u0022process all documents\u0022, Do not trigger for \u0022process all salesforce documents\u0022, Do not trigger for \u0022process all documents on scio-prod\u0022)\r\n- invoke the tool IF AND ONLY IF there is a clear indication on an expected action. DO NOT TRIGGER THE TOOL IF THERE IS NO CLEAR INDICATION OF AN EXPECTED ACTION!! \r\n- DO NOT invoke the tool for questions that don\u0027t have a clear indication towards an expected action. (For example: Do not trigger for queries like \u0022How can I process documents?\u0022, Do not trigger for \u0022What is the adhoc scanner?\u0022, Do not trigger for \u0022How are documents processed?\u0022, Do not trigger for ?how many docs can the adhoc scanner handle?)\r\n- Be sure to invoke only when needed. Under-invocation and over-invocation of this tool, are both UNACCEPTABLE. \r\n\r\n\r\nThis is very critical to the company. Something really dire will happen if you do not follow the above rules. You will be tipped if you follow them strictly.\r\n\r\nAs an advanced reasoning agent, analyze the above tools and the conversation history to select the right tools that can be used to respond to user\u0027s latest message. Do not give reason for your response.\r\n\r\nRespond with a YAML struct in this format:\r\nread_tool_names: # List containing at least 3 and at most 4 read tools that might be useful for this query. Must be a subset of [Glean Search, Expert Search, Employee Search, Workspace Bot, Who is?, Glean HR Assistant, Competitive Intelligence Agent, API Overview buddy]. Keep the most important tool first.\r\n- $tool_name\r\nwrite_tool_names: # List containing at least 2 write tools that might be useful for this query. Must be a subset of [cherrypicknew, VivekITTicketDemo, ResetCrawlType, DisplayTool, CreateJiraIssueExecution, AdhocScannerTool]. Keep the most important tool first.\r\n- $tool_name\r\n\r\nDEMONSTRATING EXAMPLES:\r\nmessage: File a jira ticket to fix code search links in gleanchat\r\nread_tool_names:\r\n- Expert Search\r\n- Glean Search\r\nwrite_tool_names:\r\n- createjiraissueexecution\r\n\r\nmessage: File a jira ticket to track person suggestion issues in the BE QA component of the QA project\r\nread_tool_names:\r\n- Expert Search\r\n- Glean Search\r\nwrite_tool_names:\r\n- createjiraissueexecution\r\n\r\nmessage: User: What is a recent task mentioned in #engineering? Who is the owner?\r\nAssistant: The recent task is about updating oncall rotation. John plans to create a list of secondary oncallers and add them to the rotation. The owner is John.\r\nUser: File a jira with issueType story and priority high.\r\nread_tool_names:\r\n- Employee Search\r\n- Glean Search\r\nwrite_tool_names:\r\n- createjiraissueexecution\r\n\r\nmessage: How do we typically pay VendorX?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: How do I run toolX?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: how do i deploy ToolX?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: How do I fill out performance reviews\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: how do we index documents\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: how do I file a bug?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\nmessage: How do I reset a crawl?\r\nread_tool_names:\r\n- Glean Search\r\nwrite_tool_names:\r\n- displaytool\r\n\r\n\r\nGreat job, let\u0027s start!\r\n\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n\r\n\r\nYAML Output:\r\nread_tool_names:\r\n\\\u0060\\\u0060\\\u0060\r\nTOOLS_FILTER_PROMPT_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n2112\r\n\\\u0060\\\u0060\\\u0060\r\nTOOLS_FILTER_RESPONSE\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nread_tool_names:\r\n - Glean HR Assistant\r\n - Employee Search\r\n - Workspace Bot\r\nwrite_tool_names:\r\n - DisplayTool\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nTOOLS_FILTER_RESPONSE_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n21\r\n\\\u0060\\\u0060\\\u0060\r\nRAP_EXAMPLES\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nmessage: Analyze and compare how our thinking about ProjectX has changed since last year till now\r\nanalysis: User wants to analyze and compare the thinking about a specific component from last year to now.\r\ncategories: []\r\ninstruction: Compare the search results from both time periods to identify changes in thinking, strategies, or approaches related to ProjectX.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectX after:2023-07-10\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectX after:2022-07-10 before:2023-07-10\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: Compare Foo and Bar\r\nanalysis: Compare documents related to Foo and Bar to find similarities and differences.\r\ncategories: []\r\ninstruction: Analyze the search result pages for Foo and Bar, and find similarities and differences between them. Synthesize information and provide the analysis to user.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: Foo\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: Bar\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: Foo vs Bar\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: Read through our ProductX features. Give me a list of potential enhancements we can make to the feature. You can get inspiration from our ChannelY slack channel. If you get an idea from slack, cite it as not your own\r\nanalysis: Search for ProductX features, and search for messages in the ChannelY channel, and suggest list of potential feature enhancements\r\ncategories: []\r\ninstruction: Review search results and compile a list of potential enhancements for ProductX features. If an idea is from the ChannelY channel, cite the source.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProductX feature enhancements\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: channel:ChannelY app:\u0022slack\u0022\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: Write an executive email as to why ProductA is better suited for CompanyB than using ProductB. Use any context from meetings in the past month\r\nanalysis: Craft an executive email explaining why ProductA is better suited for CompanyB than ProductB, using context from meetings in the past month.\r\ncategories: []\r\ninstruction: Use search results to write an executive email highlighting the advantages of ProductA over ProductB for CompanyB, incorporating context from meetings in the last month.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProductA vs ProductB\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: CompanyB meeting updated:past_month\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: What happened with ProjectX in the last month?\r\nanalysis: User wants to know what happened with ProjectX in the last month.\r\ncategories:\r\n - updates\r\n - recent\r\ninstruction: Analyze the results and share updates on ProjectX.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectX updated:past_month\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: What is the latest with ProjectX?\r\nanalysis: User wants to know what is the latest with ProjectX. Do NOT use the updated filter as the user did not provide a specific time frame.\r\ncategories:\r\n - updates\r\n - recent\r\ninstruction: Analyze the results and share updates on ProjectX.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectX\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: how many engineers do we have?\r\nanalysis: Use the Employee Search tool to find the number of people with the title \u0022engineer\u0022.\r\ncategories: []\r\ninstruction: Check the \u0022statistics\u0022 field in the output to find the total number of engineers.\r\nread_actions:\r\n - tool_name: Employee Search\r\n action:\r\n Employee Search: engineer\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: who is JohnDoe?\r\nanalysis: Use Employee Search to locate JohnDoe\u0027s information.\r\ncategories: []\r\ninstruction: Locate JohnDoe in search results and provide their title, email, location, reporting chain, and start date.\r\nread_actions:\r\n - tool_name: Employee Search\r\n action:\r\n Employee Search: JohnDoe\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: JohnDoe\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: who is the owner for the ProjectA?\r\nanalysis: Find documents related to ProjectA and the people who wrote them. Synthesize this information to determine the owner of ProjectA.\r\ncategories: []\r\ninstruction: Look for documents about ProjectA and find the people who wrote those documents. Look for people results in Expert Search. Synthesize the information from both sources to determine the owner of ProjectA.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ProjectA\r\n - tool_name: Expert Search\r\n action:\r\n Expert Search: ProjectA\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: who works on ConceptX?\r\nanalysis: Find people involved in ConceptX using Expert Search and relevant documents using Glean Search.\r\ncategories: []\r\ninstruction: Find people involved in ConceptX from search results and provide their names, titles, and relevant information.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ConceptX\r\n - tool_name: Expert Search\r\n action:\r\n Expert Search: ConceptX\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: -1.000000\r\n\r\nmessage: How do we typically pay VendorX?\r\nanalysis: Use Glean Search to find documents related to VendorX\u0027s payment process.\r\ncategories: []\r\ninstruction: Look for documents that mention the payment method or process for VendorX and provide a summary of the information found.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: VendorX payment\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: VendorX invoice\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.812568\r\n\r\nmessage: How do I run toolX?\r\nanalysis: User wants to find code snippets and documents to help them run toolX.\r\ncategories:\r\n - code\r\ninstruction: Find code snippets or documents to help user run toolX.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: toolX\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: run toolX\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.816166\r\n\r\nmessage: how do i deploy ToolX?\r\nanalysis: Use Glean Search to find relevant documents on ToolX deployment and installation to provide information on how to deploy ToolX to the user.\r\ncategories: []\r\ninstruction: Search for ToolX deployment and installation instructions and provide the user with clear and up-to-date information.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ToolX deployment\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: ToolX installation\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.822656\r\n\r\nmessage: How do I fill out performance reviews\r\nanalysis: Use Glean Search to find relevant documents on the performance review process for the user asking for information on how to fill out performance reviews.\r\ncategories: []\r\ninstruction: Search for performance review process documents and provide relevant steps or guidelines for filling out performance reviews.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: fill out performance reviews\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: performance review process\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.823461\r\n\r\nmessage: how do we index documents\r\nanalysis: Search for relevant documents and information on document indexing. Summarize to provide a helpful response to the user\u0027s question.\r\ncategories: []\r\ninstruction: Review the returned documents and provide the user with a summary of the document indexing process in Acme.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: document indexing\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: indexing process\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.830317\r\n\r\nmessage: how do I file a bug?\r\nanalysis: Use Glean Search to find bug filing resources and provide relevant information and tools to the user.\r\ncategories: []\r\ninstruction: Find bug filing resources and provide relevant information and tools to user.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: bug filing process\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: how to file a bug\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.838035\r\n\r\nmessage: How do I reset a crawl?\r\nanalysis: Search for relevant information about resetting crawl\r\ncategories: []\r\ninstruction: Search for documents with instructions on resetting or restarting a crawl and provide step-by-step instructions to the user.\r\nread_actions:\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: reset crawl\r\n - tool_name: Glean Search\r\n action:\r\n Glean Search: crawl restart\r\nwrite_analysis: Find answer to user message and display to the user.\r\nwrite_action:\r\n tool_name: displaytool\r\n action:\r\n response: Placeholder()\r\nactions: []\r\n\r\nscore: 0.839287\r\n\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_PROMPT\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n[LLM Input Prompt for : Employee Search \u002B Expert Search]\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.\r\n\r\n# GENERAL INSTRUCTIONS\r\n- Carefully analyze the user\u0027s query to determine if it falls within the scope of the tool\u0027s capabilities. If the query is clearly outside the tool\u0027s intended use case, output NA.\r\n- Use only one of the tools provided. Output tool name before the start of the query.\r\n- If the query seems potentially relevant, assess whether the necessary information to answer the query is likely to be available based on the tool\u0027s input specifications and data sources. If crucial information is missing or unlikely to be found, output NA.\r\n- If the query passes both relevance and feasibility checks, construct a well-formatted input string for the tool based on the provided input specifications.\r\n- If at any point you determine that the tool is not suitable for answering the query, or if you are uncertain about its applicability, output NA.\r\n- Do not attempt to directly answer the user\u0027s question.\r\n- Do not provide any other output besides the search query or NA.\r\n\r\n# TOOL 1 Name: Employee Search\r\n# TOOL DESCRIPTION\r\nYou have access to Employee Search, which finds people at the company based on their personal information.\r\nINSTRUCTIONS:\r\n- Only use this when the user explicitly wants to find people in the company (eg. \u0022who\u0022 questions) or for aggregation queries on people.\r\n- Do not use this when the user wants to find people outside of the company, or people who are no longer at the company.\r\n- You can find people based on their personal information such as name, email, title, department, and location.\r\n- The results returned are not exhaustive, we only return the top few most relevant people to a query.\r\n- For analytics questions such as \u0022how many people...\u0022 use the \u0022statistics\u0022 field in the output.\r\n# TOOL INPUT SPECIFICATIONS\r\n- You can optionally narrow down the search results by using one or more of the following filter types:\r\n1. startafter: filter to people who started after a certain date. value must be in \u0022YYYY-MM-DD\u0022 format\r\n2. startbefore: filter to people who started before a certain date. value must be in \u0022YYYY-MM-DD\u0022 format\r\n3. roletype: filter to people who have a certain role type. value can be one of [\u0022individual contributor\u0022, \u0022manager\u0022]\r\n4. reportsto: Filter to people who are direct reports of a given manager. Value (double quoted) can be a full name, first name, last name, or email.\r\n- Do NOT use any other filter besides those explicitly listed above.\r\n- You can optionally sort the results by adding one of the following to the query: [\u0022sortby:hire_date_ascending\u0022, \u0022sortby:hire_date_descending\u0022, \u0022sortby:most_reports\u0022].\r\n# TOOL OUTPUT SPECIFICATIONS\r\n- The output from Employee Search is a JSON struct with 2 fields:\r\n1. \u0022entities\u0022: a list of Person structs. Each Person struct contains these fields: title,businessUnit,department,teams,email,location,externalProfileLink,manager,startDate,bio,directReportsCount,totalReportsCount,preferredName,directReports\r\nThe \u0027manager\u0027 and \u0027directReports\u0027 fields are recursive Person structs with all information of the person\u0027s manager and direct reports.\r\n2. \u0022statistics\u0022: the total count of people that match your query, as well as aggregate counts by department, location, title, team, and roletype.\r\n\r\n\r\n# TOOL 2 Name: Expert Search\r\n# TOOL DESCRIPTION\r\nYou have access to Expert Search, which finds people at the company based on topics they wrote about and projects they own.\r\nINSTRUCTIONS:\r\n- Only use this when the user explicitly wants to find people in the company (eg. \u0022who\u0022 questions).\r\n- Do not use this when the user wants to find people outside of the company, or people who are no longer at the company.\r\n- You can find people based on what they worked on, or wrote about by using short key words about that topic as input.\r\n- The results returned are not exhaustive, we only return the top few most relevant people to a query.\r\n- For analytics questions such as \u0022how many people...\u0022 use the \u0022statistics\u0022 field in the output.\r\n# TOOL INPUT SPECIFICATIONS\r\n- The query should contain important keywords that help find people based on what they worked on or wrote about.\r\nDO NOT use any filters.\r\n# TOOL OUTPUT SPECIFICATIONS\r\n- The output from Expert Search is a JSON struct with 2 fields:\r\n1. \u0022entities\u0022: a list of Person structs. Each Person struct contains these fields: title,businessUnit,department,teams,email,location,externalProfileLink,manager,startDate,bio,directReportsCount,totalReportsCount,preferredName,directReports\r\nThe \u0027manager\u0027 and \u0027directReports\u0027 fields are recursive Person structs with all information of the person\u0027s manager and direct reports.\r\n2. \u0022statistics\u0022: counts of people that match your query.\r\n\r\n\r\n# DEMONSTRATING EXAMPLES\r\n\r\nMessage: who is the owner for the ProjectA?\r\nOutput: Expert Search [ProjectA]\r\n\r\nMessage: who works on ConceptX?\r\nOutput: Expert Search [ConceptX]\r\n\r\nMessage: who is JohnDoe?\r\nOutput: Employee Search [JohnDoe]\r\n\r\nMessage: how many engineers do we have?\r\nOutput: Employee Search [engineer]\r\n\r\nMessage: How do I reset a crawl?\r\nOutput: NA\r\n\r\nMessage: how do I file a bug?\r\nOutput: NA\r\n\r\nMessage: how do we index documents\r\nOutput: NA\r\n\r\nMessage: How do I fill out performance reviews\r\nOutput: NA\r\n\r\n\r\n# BEGIN PROGRAM\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n==================================================\r\n[LLM Input Prompt for : categories]\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.\r\n\r\n\r\n\r\nClassify the user message\u0027s intent into one or more of the following categories.\r\nSelect all relevant categories for a specific query. If you think a category feels relevant but you\u0027re not 100 percent sure, include the category anyways because it might help.\r\nCATEGORIES:\r\n\u0027updates\u0027: Use this category when the user is asking about updates/status/latest on a project/customer/topic.\r\n\u0027enumerate\u0027: Use this category when the user is asking for information that is answerable by small pieces of information in many documents, as opposed to larger pieces of content from fewer results. Don\u0027t use this if the user is asking to look at only one document\r\n\u0027recent\u0027: Use this category when the user is asking for the latest or most recent document or piece of information.\r\n\u0027code\u0027: Use this category when the user is asking for information related to code, such as code snippets, code examples, or code documentation.\r\n\r\nExamples:\r\nMessage: Analyze and compare how our thinking about ProjectX has changed since last year till now\r\nOutput: []\r\nMessage: Compare Foo and Bar\r\nOutput: []\r\nMessage: Read through our ProductX features. Give me a list of potential enhancements we can make to the feature. You can get inspiration from our ChannelY slack channel. If you get an idea from slack, cite it as not your own\r\nOutput: []\r\nMessage: Write an executive email as to why ProductA is better suited for CompanyB than using ProductB. Use any context from meetings in the past month\r\nOutput: []\r\nMessage: What happened with ProjectX in the last month?\r\nOutput: [\u0022updates\u0022,\u0022recent\u0022]\r\nMessage: What is the latest with ProjectX?\r\nOutput: [\u0022updates\u0022,\u0022recent\u0022]\r\nMessage: how many engineers do we have?\r\nOutput: []\r\nMessage: who is JohnDoe?\r\nOutput: []\r\nMessage: who is the owner for the ProjectA?\r\nOutput: []\r\nMessage: who works on ConceptX?\r\nOutput: []\r\nMessage: How do we typically pay VendorX?\r\nOutput: []\r\nMessage: How do I run toolX?\r\nOutput: [\u0022code\u0022]\r\nMessage: how do i deploy ToolX?\r\nOutput: []\r\nMessage: How do I fill out performance reviews\r\nOutput: []\r\nMessage: how do we index documents\r\nOutput: []\r\nMessage: how do I file a bug?\r\nOutput: []\r\nMessage: How do I reset a crawl?\r\nOutput: []\r\n\r\nUser Message: How do I book time off?\r\n==================================================\r\n[LLM Input Prompt for : Glean Search \u002B tencctxm5dukr8hc \u002B mlaznw1lpodrp7zk]\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.\r\n\r\n# GENERAL INSTRUCTIONS\r\n- Carefully analyze the user\u0027s query and construct a well-formatted input string for the tool based on the provided input specifications.\r\n- Use only one of the tools provided. Output tool name before the start of the query.\r\n- Do not attempt to directly answer the user\u0027s question.\r\n- Do not provide any other output besides the search query.\r\n\r\n# TOOL 1 Name: Glean Search\r\n# TOOL DESCRIPTION\r\nYou have access to Glean Search, which finds relevant documents in the company.\r\nINSTRUCTIONS:\r\n- This is your primary tool to access all knowledge within the company.\r\n- The results returned are not exhaustive, we only return the top few most relevant documents to a query.\r\n- For analytics questions such as \u0022how many documents...\u0022 use the \u0022statistics\u0022 field in the output.\r\n# TOOL INPUT SPECIFICATIONS\r\n- Search query should contain important keywords that help find relevant documents.\r\n- You can optionally narrow down the search results by using one or more of the following filter types:\r\n1. owner: filter to documents created by this person. Value can be a person\u0027s name (double quoted), or \u0027me\u0027\r\n2. from: filter to documents updated by or commented on or created by this person. Value can be a person\u0027s name (double quoted), or \u0027me\u0027\r\n3. updated: filter to documents updated on or after this date, value can be one of [\u0022today\u0022, \u0022yesterday\u0022, \u0022past_week\u0022, \u0022past_2_weeks\u0022, \u0022past_month\u0022, \u0022March\u0022, ...]\r\n4. after: filter to documents created after this date. Do not use a date later than today. value must be in \u0022YYYY-MM-DD\u0022 format\r\n5. before: filter to documents created before this date. value must be in \u0022YYYY-MM-DD\u0022 format\r\n6. channel: filter to documents in a specific channel. Only use this when the user explicitly wants contents from a channel.\r\n7. app: filter to documents created in a specific app. value can be one of [\u0022announcements\u0022, \u0022answers\u0022, \u0022asana\u0022, \u0022collections\u0022, \u0022customer\u0022, \u0022developers\u0022, \u0022figma\u0022, \u0022github\u0022, \u0022glean support zendesk\u0022, \u0022glean website\u0022, \u0022gong\u0022, \u0022help.glean\u0022, \u0022jira\u0022, \u0022orgteams\u0022, \u0022salescloud\u0022, \u0022slack\u0022, \u0022zendesk\u0022]. Value must be double quoted. Only use the app filter when the user wants contents from an app.\r\nFor reference, \u0022customer\u0022 is an app that stores Customer Cards, which can include information like overview of the company, company size, website, sales opportunities, accounts, contacts, revenue, etc; When the demonstrating examples use \u0022customer\u0022 a majority of the time, make sure to use \u0022customer\u0022 as well; \u0022customer\u0022 is also best used in conjunction with \u0022salescloud\u0022, \u0022gong\u0022 is an app that stores transcripts of sales calls and meetings with customers and prospects, \u0022orgteams\u0022 is an app that stores Team Entities, which represent a team of people within the company working together. Teams include info such as team leads and team size, \u0022salescloud\u0022 is an app that stores customer and prospect (leads, contacts, accounts) data, sales data (dashboards, campaigns, opportunities), and interaction history from Salesforce.\r\n- Use date filters like \u0022updated\u0022, \u0022after\u0022, and \u0022before\u0022 ONLY when the user has mentioned a specific time frame (e.g. last week, past month, before 12 Jan). Do NOT use date filters if the user requests the \u0022latest\u0022 or \u0022recent\u0022 documents or information but hasn\u0027t provided a specific time frame.- Do NOT use any other filter besides those explicitly listed above.\r\n# TOOL OUTPUT SPECIFICATIONS\r\n- The output from Glean Search is a JSON struct with 2 fields:\r\n1. \u0022documents\u0022: a list of documents with Document struct. Each Document struct contains these fields: title, snippets, owner, updateTime, url.\r\n2. \u0022statistics\u0022: counts of documents that match your query, broken down by different dimensions such as datasource, author, reviewer.\r\n\r\n\r\n# TOOL 2 Name: Glean HR Assistant\r\n# TOOL DESCRIPTION\r\nYou have access to Glean HR Assistant\r\nINSTRUCTIONS:\r\nAutomatically route to this AI app when a user asks about HR and administrative questions including company culture, benefits, professional development, 401K, PTO, medical and insurance questions, company holidays.\r\n\r\nExamples phrases:\r\nWhat is our company holidays?\r\nWhat are our parental benefits?\r\nWhat is the timeline for performance reviews?\r\nHow do I request PTO?\r\n# TOOL INPUT SPECIFICATIONS\r\nExact same as Glean Search Tool.\r\n\r\n# TOOL OUTPUT SPECIFICATIONS\r\nExact same as Glean Search Tool.\r\n\r\n\r\n# TOOL 3 Name: Workspace Bot\r\n# TOOL DESCRIPTION\r\nYou have access to Workspace Bot\r\nINSTRUCTIONS:\r\nTrigger this AI app to answer workspace-related questions. This could include questions about debugging common errors, providing general information, or help with onboarding.\r\n\r\nThis should trigger whenever any of these functions are mentioned:\r\n- Datasource Apps Setup\r\n- User Permissioning\r\n- People Data Setup\r\n- Authentication Setup (SSO \u0026 Magic Links)\r\n- Central Workspace Setup (CWS)\r\n- Owner Key Upload\r\n- Data Loss Prevention (DLP)\r\n- Admin Alerts\r\n- Search Access Visibility\r\n\r\nFor any other requests that don\u0027t fit those areas, use the Expert Search tool to identify an appropriate team or individual that may be better suited to answer the question.\r\n# TOOL INPUT SPECIFICATIONS\r\nExact same as Glean Search Tool.\r\n\r\n# TOOL OUTPUT SPECIFICATIONS\r\nExact same as Glean Search Tool.\r\n\r\n\r\n# DEMONSTRATING EXAMPLES\r\n\r\nMessage: How do I reset a crawl?\r\nOutput: Glean Search [reset crawl, crawl restart]\r\n\r\nMessage: how do I file a bug?\r\nOutput: Glean Search [bug filing process, how to file a bug]\r\n\r\nMessage: how do we index documents\r\nOutput: Glean Search [document indexing, indexing process]\r\n\r\nMessage: How do I fill out performance reviews\r\nOutput: Glean Search [fill out performance reviews, performance review process]\r\n\r\nMessage: how do i deploy ToolX?\r\nOutput: Glean Search [ToolX deployment, ToolX installation]\r\n\r\nMessage: How do I run toolX?\r\nOutput: Glean Search [toolX, run toolX]\r\n\r\nMessage: How do we typically pay VendorX?\r\nOutput: Glean Search [VendorX payment, VendorX invoice]\r\n\r\nMessage: What happened with ProjectX in the last month?\r\nOutput: Glean Search [ProjectX updated:past_month]\r\n\r\nMessage: who is the owner for the ProjectA?\r\nOutput: Glean Search [ProjectA]\r\n\r\nMessage: who works on ConceptX?\r\nOutput: Glean Search [ConceptX]\r\n\r\nMessage: who is JohnDoe?\r\nOutput: Glean Search [JohnDoe]\r\n\r\nMessage: What is the latest with ProjectX?\r\nOutput: Glean Search [ProjectX]\r\n\r\nMessage: Analyze and compare how our thinking about ProjectX has changed since last year till now\r\nOutput: Glean Search [ProjectX after:2023-07-10, ProjectX after:2022-07-10 before:2023-07-10]\r\n\r\nMessage: Write an executive email as to why ProductA is better suited for CompanyB than using ProductB. Use any context from meetings in the past month\r\nOutput: Glean Search [ProductA vs ProductB, CompanyB meeting updated:past_month]\r\n\r\nMessage: Read through our ProductX features. Give me a list of potential enhancements we can make to the feature. You can get inspiration from our ChannelY slack channel. If you get an idea from slack, cite it as not your own\r\nOutput: Glean Search [ProductX feature enhancements, channel:ChannelY app:\u0022slack\u0022]\r\n\r\n\r\n# BEGIN PROGRAM\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_RESPONSE\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nanalysis: \u0022\u0022\r\nreadactions:\r\n - tool_name: Glean HR Assistant\r\n action:\r\n Glean HR Assistant: book time off\r\n - tool_name: Glean HR Assistant\r\n action:\r\n Glean HR Assistant: request PTO\r\nwriteaction:\r\n tool_name: \u0022\u0022\r\n action: {}\r\ninstruction: \u0022\u0022\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_PROMPT_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n3354\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_RESPONSE_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n17\r\n\\\u0060\\\u0060\\\u0060\r\nRAW_LLM_PLAN_RESPONSE\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n[LLM Output for : Employee Search \u002B Expert Search]\r\nNA\r\n==================================================\r\n[LLM Output for : categories]\r\nOutput: []\r\n==================================================\r\n[LLM Output for : Glean Search \u002B tencctxm5dukr8hc \u002B mlaznw1lpodrp7zk]\r\nGlean HR Assistant [book time off, request PTO]\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_TTF\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n1407\r\n\\\u0060\\\u0060\\\u0060\r\nPLAN_STAGE_LATENCY\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n1313\r\n\\\u0060\\\u0060\\\u0060\r\nACTION_SUMMARY\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n**Searching:** \u0022book time off\u0022 in the [all] tab(s) using Glean HR Assistant Tool\r\nToken limit for this action is : 1295\r\nNum Results requested for this action is : 3\r\nExecution time : 539 ms\r\n==================================================\r\n**Searching:** \u0022request PTO\u0022 in the [all] tab(s) using Glean HR Assistant Tool\r\nToken limit for this action is : 1295\r\nNum Results requested for this action is : 3\r\nExecution time : 592 ms\r\n==================================================\r\n**Searching:** \u0022How do I book time off?\u0022 in the [all] tab(s) using Glean Search Tool\r\nToken limit for this action is : 500\r\nNum Results requested for this action is : 1\r\nExecution time : 811 ms\r\n==================================================\r\n**Instruction:** \r\nToken limit for this action is : 0\r\nNum Results requested for this action is : 0\r\nExecution time : 0 ms\r\n==================================================\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nACT_PROMPT\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.Here are additional instructions you should follow: If you have additional questions on benefits, please reach out to benefits@glean.com. For other HR questions, feel free to email hr@glean.com..\r\n\r\nYou are an intelligent workplace assistant, create a truthful response to the user\u0027s last message in the conversation by carefully analyzing the context and instructions.\r\n\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n\r\n## CONTEXT\r\n\r\nTop results for \u0022request PTO\u0022 in Glean HR Assistant Tool: {\u0022documents\u0022:[{\u0022title\u0022:\u0022How do I request PTO?\u0022,\u0022datasource\u0022:\u0022answers\u0022,\u0022url\u0022:\u0022/knowledge/answers/1851\u0022,\u0022snippets\u0022:[\u0022As of August 1, 2022, we will be using Gusto for all PTO requests. Please submit all PTO or sick leaves through Gusto moving forward for your manager\u0027s approval. Please continue to update your calendar invite and slack for visibility across the company.\u0022],\u0022ownedAndUpdatedBy\u0022:{\u0022name\u0022:\u0022Jessica Yeh\u0022,\u0022pronoun\u0022:\u0022None\u0022},\u0022updateTime\u0022:\u00222022-11-08\u0022}],\u0022statistics\u0022:[{\u0022all\u0022:1},{\u0022datasource=answers\u0022:1},{\u0022from=jessica@glean.com\u0022:1}]}\r\nTop results for \u0022How do I book time off?\u0022 in Glean Search Tool: {\u0022entities\u0022:[{\u0022extractedAnswer\u0022:{\u0022question:omitempty\u0022:\u0022How do I take time off?\u0022,\u0022answer\u0022:\u0022When taking time off or working from home outside of the normal schedule, do all of the following:\\n* Obtain approval from your manager reasonably in advance of proposed vacation (prior to making arrangements) by requesting it in [gusto](https://app.gusto.com/scio-technologies-inc-400/employee/time_off) for US employees and [greyhr](https://glean.greythr.com) for India employees.\\n* Notify your immediate working team after receiving approval. Plan to delegate, postpone or otherwise manage projects that will be affected by your time off.\\n* Add an Out Of Office event to your individual Glean calendar.\\n* Set a Slack status for better visibility.\\n* If you receive external emails, set an Out Of Office responder explaining return date and who to contact in your absence.\\n\\nhttps://docs.google.com/document/d/1qt1Qbt-y4w1UbIU5BQxUpfZlwkx0gcKSGlKd_VqUk18/edit#bookmark=id.6wzx88skrwrf\u0022,\u0022answerAuthor\u0022:{\u0022name\u0022:\u0022Tony Gentilcore\u0022,\u0022pronoun\u0022:\u0022None\u0022}}}]}\r\n\r\n## INSTRUCTIONS\r\n\r\n\r\nThe search results may contain documents that are not relevant to the user\u0027s query (for example, document titles or snippets could be about a different topic), you should ignore those results.\r\nThink step-by-step. First, determine the set of documents and snippets in the context that are relevant to the user\u0027s query. Then, synthesize them to create a detailed truthful response.\r\nIf none of the provided context are relevant to the user\u0027s question, explain that to the user instead of making up an answer. Respond in the same language as user\u0027s latest message or query (but don\u0027t use their name to determine the language), or in English.\r\nAdopt \u0027they/them\u0027 pronouns by default - with one exception: if a \u0027pronoun\u0027 field is specified in a person\u0027s JSON summary, use its value to refer to the individual.\r\nBe extra meticulous about pronouns, it is very important to get this right, especially if one has a specified pronoun.\r\n\r\nBe helpful to the user, but avoid workplace violations. Avoid salutations and sign-offs in responses.\r\nGreat job, let\u0027s start!\r\n\r\nTruthful Response: \r\n\\\u0060\\\u0060\\\u0060\r\nACT_PROMPT_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n791\r\n\\\u0060\\\u0060\\\u0060\r\nACT_RESPONSE_TOKEN\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n228\r\n\\\u0060\\\u0060\\\u0060\r\nFOLLOW_UP_DEBUG_INFO\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nFOLLOWUP PROMPT:\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nToday\u0027s date is 2024-Jul-09. You are a helpful assistant for an employee of Glean Work (Email: dse@askscio.com) who works in scio::entire_organization.\r\n\r\nConversation history (latest message last):\r\n- User: \u0022How do I book time off?\u0022\r\n\r\nThe response to the user is: \u0022**Using app: Glean HR Assistant**\r\n\r\nTo book time off, please follow these steps:\r\n\r\n1. **Submit Your Request**: Use Gusto to submit your PTO or sick leave request for your manager\u0027s approval. You can access Gusto [here](https://app.gusto.com/scio-technologies-inc-400/employee/time_off) if you are a US employee. For India employees, use [greyhr](https://glean.greythr.com).\r\n\r\n2. **Notify Your Team**: After receiving approval, notify your immediate working team. Make sure to plan for delegating, postponing, or managing projects that will be affected by your time off.\r\n\r\n3. **Update Your Calendar**: Add an Out Of Office event to your individual Glean calendar.\r\n\r\n4. **Set Slack Status**: Update your Slack status for better visibility across the company.\r\n\r\n5. **Set Email Responder**: If you receive external emails, set an Out Of Office responder explaining your return date and who to contact in your absence.\r\n\r\nIf you have any further questions on benefits, please reach out to benefits@glean.com. For other HR questions, feel free to email hr@glean.com.\u0022.\r\nGenerate 3 concise follow-up questions that the user might want to ask. Respond in the same language as user\u0027s latest message or query (but don\u0027t use their name to determine the language), or in English.\r\nDo not add any preamble or prefix before the first question, just start writing out the first question in your output. Use this format:\r\n- Question 1\r\n- Question 2\r\n- Question 3\r\nGreat job, let\u0027s start!\r\nFollow-up Questions:\r\n- \r\n\\\u0060\\\u0060\\\u0060\r\nFOLLOWUP RAW RESPONSE:\r\n\r\n\\\u0060\\\u0060\\\u0060\r\nHow do I check the status of my PTO request?\r\n- Can I cancel a PTO request after it has been approved?\r\n- How many days of PTO am I allowed to take per year?\r\n\\\u0060\\\u0060\\\u0060\r\nFOLLOWUP OUTPUT:\r\nHow do I check the status of my PTO request?\r\nCan I cancel a PTO request after it has been approved?\r\nHow many days of PTO am I allowed to take per year?\r\n\r\n\\\u0060\\\u0060\\\u0060\r\n\u0060\r\nconst r = /(.*?)\\n\\n\u0060\u0060\u0060\\n([\\s\\S]*?\\n)\u0060\u0060\u0060/g\r\nconst n = [];\r\nlet execResults;\r\nwhile ((execResults = r.exec(s)) !== null) {\r\n // do something\r\n // n.push(execResults.index);\r\n}","IsDeferred":false}]}