> For the complete documentation index, see [llms.txt](https://docs.jetadmin.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.jetadmin.io/ai-agents.md). # AI Agents - [Create your first agent](https://docs.jetadmin.io/ai-agents/overview.md) - [Getting Started](https://docs.jetadmin.io/ai-agents/overview/agents.md): Learn how to use Jetadmin Agents to automate tasks using natural language and LLMs, no coding or complex logic required. - [Add an Agent](https://docs.jetadmin.io/ai-agents/overview/add-an-agent.md): Choose how to add a Jetadmin agent to your app - [Instructions, tools, skills, files, and models](https://docs.jetadmin.io/ai-agents/instructions-tools-skills-files-and-models.md) - [Agent Instructions](https://docs.jetadmin.io/ai-agents/instructions-tools-skills-files-and-models/agent-instructions.md): Instructions in JetAdmin define how an agent should think, act, and communicate when handling tasks. - [Agent Tools](https://docs.jetadmin.io/ai-agents/instructions-tools-skills-files-and-models/agent-tools.md): Agents in JetAdmin use tools to interact with data, perform actions, and extend their capabilities. - [Agent Skills](https://docs.jetadmin.io/ai-agents/instructions-tools-skills-files-and-models/agent-skills.md): Skills allow you to extend agent behavior with reusable instructions and capabilities. - [Agent Files](https://docs.jetadmin.io/ai-agents/instructions-tools-skills-files-and-models/agent-files.md): The Files feature allows you to view and manage files created by agents during conversations. - [AI Models](https://docs.jetadmin.io/ai-agents/instructions-tools-skills-files-and-models/ai-models.md): Agents in JetAdmin can use different AI models depending on the task, performance needs, and cost considerations. - [Test an agent safely](https://docs.jetadmin.io/ai-agents/test-an-agent-safely.md) - [Run agents in apps, workflows, and automatic tasks](https://docs.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks.md) - [Using agents](https://docs.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks/agents-1.md): Learn how to use Jetadmin Agents to automate tasks using natural language and LLMs, no coding or complex logic required. - [The Agent Interface](https://docs.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks/the-agent-interface.md): Explore the key sections of the Jetadmin Agent configuration interface, where you define your agent’s purpose, inputs, behavior, and access to tools. - [Running Agents](https://docs.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks/running-agents.md): Learn how to trigger and run Agents in Jetadmin manually via the UI, through workflows, or by chaining agents together for seamless automation. - [Workflows with Agents](https://docs.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks/workflows-with-agents.md): Agents in JetAdmin can be used inside workflows to add decision-making and flexibility to structured automations. - [Agent Automatic Tasks](https://docs.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks/agent-automatic-tasks.md): Automatic Tasks allow agents to run automatically based on schedules, events, or predefined triggers. - [How Agents Work](https://docs.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks/how-agents-work.md): Understand how Jetadmin Agents operate behind the scenes, breaking down the step-by-step reasoning cycle that drives their decision-making and actions. - [Agent templates](https://docs.jetadmin.io/ai-agents/agent-templates.md): JetAdmin provides prebuilt agent templates to help you get started quickly. - [Library](https://docs.jetadmin.io/ai-agents/agent-templates/library.md): The Library in JetAdmin allows you to upload and manage files that agents can use as a knowledge source. - [Slack, Telegram, Email, and MCP](https://docs.jetadmin.io/ai-agents/slack-telegram-email-and-mcp.md) - [Using Agents in Slack](https://docs.jetadmin.io/ai-agents/slack-telegram-email-and-mcp/using-agents-in-slack.md): JetAdmin agents can be added to Slack channels and direct messages, allowing users to interact with agents directly inside Slack. - [Using Agents in Telegram](https://docs.jetadmin.io/ai-agents/slack-telegram-email-and-mcp/using-agents-in-telegram.md): JetAdmin agents can be connected to Telegram chats and groups using the JetAdmin Telegram bot. - [Using Agents with Email](https://docs.jetadmin.io/ai-agents/slack-telegram-email-and-mcp/using-agents-with-email.md): JetAdmin agents can be used through email by enabling a dedicated email inbox for the agent. - [Using Agents with MCP Clients](https://docs.jetadmin.io/ai-agents/slack-telegram-email-and-mcp/using-agents-with-mcp-clients.md): JetAdmin agents can be added to AI tools and MCP-compatible clients using the Add to AI feature. - [Using Agents in External Tools](https://docs.jetadmin.io/ai-agents/slack-telegram-email-and-mcp/using-agents-in-external-tools.md): Agents in JetAdmin can be connected to external platforms and used as bots. This allows you to interact with your agents directly from tools like Slack, Telegram, and more without opening your app. - [External Integrations for AI Agents (On-Premises)](https://docs.jetadmin.io/ai-agents/slack-telegram-email-and-mcp/external-integrations-for-ai-agents-on-premises.md): Configure Slack and Telegram integrations for AI agents in on-premises deployments using environment variables. --- # 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.jetadmin.io/ai-agents.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.