> For the complete documentation index, see [llms.txt](https://docs.rewst.help/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rewst.help/rewst-documentation/documentation/rewst-agent/how-to-ask-better-questions-of-the-rewst-agent.md). # How to ask better questions of the Rewst Agent ### General questions If you're new to using AI assistants, here's one important takeaway: how you craft your question will determine the quality of your result. 1. Be specific. Instead of "How do I automate tickets?" ask "What ConnectWise PSA actions are available for creating tickets?" 2. Provide context. If asking about a specific workflow or execution, provide the ID or name so the Rewst Agent can hone in on your particular scenario. 3. Ask follow-up questions. Think of it as a conversation where the Rewst Agent can drill down into details once you help him identify the right resource. 4. Ask questions before building, not just after. The Rewst Agent can help you find the right tools before as part of your design and planning process. ### Ask questions to build workflows When asking the Rewst Agent to build for you, it's crucial that you give it good information about your goals and constraints. It'll also ask follow up questions while thinking and building. Respond to those questions fully and thoughtfully for best results. When formulating your request, be ready with the following information: Purpose and goal * What is the workflow supposed to accomplish? * What problem are you solving or what process are you automating? * What is the expected outcome when the workflow completes successfully? Trigger information * How should the workflow start? * On a schedule - e.g., daily, weekly, every hour? * Manually via a form? * In response to an event - e.g., a new ticket created, a webhook, an email received? * Called by another workflow as a subworkflow? Input data * What information does the workflow need to begin? * User inputs - e.g., customer name, ticket ID, email address? * Data from an external system? * Static values or organization variables? Integrations and systems involved * Which tools does the workflow need to interact with? * Examples: ConnectWise PSA, Microsoft 365, NinjaOne, Datto, HaloPSA, etc. * Do you have these integrations already installed and configured in Rewst? Logic and conditions * Are there any decisions or branching logic? * "If X, do this; otherwise, do that" * Loops - e.g., "For each user in this list, do..." * Error handling - e.g., "If this fails, notify someone" Actions and steps * What specific actions need to happen? * Create a ticket, send an email, update a record, run a script, etc. * In what order should these actions occur? Output and results * What should happen when the workflow finishes? * Send a notification or report? * Update a system or database? * Pass data to another workflow? Error handling and edge cases * What should happen if something goes wrong? * Retry the action? * Send an alert? * Log the error and continue? #### Example of a good workflow build request > *"I want a workflow that runs every morning at 8 AM. It should pull all open tickets from ConnectWise PSA that are older than 7 days, then send a summary email to our service manager with the ticket details. If there are no old tickets, it should skip the email."* --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.rewst.help/rewst-documentation/documentation/rewst-agent/how-to-ask-better-questions-of-the-rewst-agent.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.