> For the complete documentation index, see [llms.txt](https://docs.usepylon.com/pylon-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.usepylon.com/pylon-docs/agents/automations.md). # Automations Automate repeatable support work with workflows that investigate issues, classify and route work, update fields, create tickets, and more. {% hint style="info" %} Automations that run AI instructions require access to Agentic features or Skills. Availability depends on your workspace's plan — contact your account team if you don't see them. Creating or editing the AI instructions also requires edit access under **Support agents** in your role's permissions. {% endhint %} Automations connect a trigger to work you want Pylon to perform automatically. For example, an Automation can run when a new issue arrives, investigate the issue using relevant context and connected tools, and surface its findings for your team. ### How Automations work 1. **Choose a kickoff event.** Define when the Automation should run, such as when a new issue is created or on a recurring schedule. 2. **Define the work.** Add AI instructions or a Skill that tells Pylon what to do. 3. **Connect tools and context.** Give the Automation the context and connected tools it needs to complete the work. 4. **Review and enable.** Confirm the automation and turn it on. Once enabled, the Automation runs whenever its trigger conditions are met. ### Example: Investigate new issues Create an Automation that runs whenever a new issue arrives. Pylon can investigate the issue, gather relevant context and evidence, and prepare its findings for your team. ### Example: Triage, classification & tagging Create an Automation that runs when a new issue arrives or its status changes. It can classify the issue and apply the appropriate tags or custom fields. ### Context Automations can use relevant context from Pylon and your connected systems to complete their work, including: * The triggering issue, account, or other object * Knowledge base articles and connected documentation * Past issues * Account fields and notebooks * Connected codebases and logs * MCP connectors and other enabled tools * Skills The context and tools available to an Automation determine what it can understand and what actions it can take. --- # 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.usepylon.com/pylon-docs/agents/automations.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.