> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/build-and-improve.md).

# Build and improve

- [Build an Agent](https://docs.lleverage.ai/build-and-improve/overview.md): Set up an Agent for real operational work: define its role, let it build its Skills and Connections, give it context, test it and prepare it for operators.
- [Instructions and behaviour](https://docs.lleverage.ai/build-and-improve/overview/instructions-and-behaviour.md): Configure the organisation, Project and task-level instruction layers that shape how the Agent approaches work.
- [Skills and operating methods](https://docs.lleverage.ai/build-and-improve/overview/skills-and-operating-methods.md): Build and improve recurring Agent tasks as reusable Skills, primarily by working with the Agent itself.
- [Connect systems](https://docs.lleverage.ai/build-and-improve/overview/connect-systems.md): Give an Agent authorised access to business systems and understand the boundary between Connection authority and Skill instructions.
- [Custom integrations](https://docs.lleverage.ai/build-and-improve/overview/custom-integrations.md): Set up a custom integration with the Agent when the system you need is not available as a native Lleverage provider.
- [Give the Agent context](https://docs.lleverage.ai/build-and-improve/overview/give-the-agent-context.md): Give the Agent durable working context using Files, Tables, Knowledge and Memory without blurring their different authority models.
- [Test and improve the Agent](https://docs.lleverage.ai/build-and-improve/overview/test-and-improve-the-agent.md): Validate an Agent on representative operational work, inspect its evidence, and improve the setup at the layer that caused the problem.
- [Prepare the Agent for operators](https://docs.lleverage.ai/build-and-improve/overview/prepare-the-agent-for-operators.md): Hand an Agent over to operators with the right project access, channels, boundaries and support path.
- [Automate](https://docs.lleverage.ai/build-and-improve/automate.md): Turn a known part of an operational process into a defined, repeatable execution path.
- [Build a workflow](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow.md)
- [Triggers](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/triggers.md): Triggers are the starting points of any workflow in Lleverage. They determine how your workflow is initiated and what form it will take when published. Triggers define the entry point for your automat
- [Chat](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/chat.md)
- [Form](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/form.md)
- [Output](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/output.md)
- [Flow Control](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/flow-control.md)
- [Variables and Data Flow](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/variables-and-data-flow.md)
- [Canvas reference](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/canvas-reference.md)
- [Keyboard Shortcuts](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/canvas-reference/keyboard-shortcuts.md)
- [Canvas Controls](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/canvas-reference/canvas-controls.md)
- [Action Cards](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/canvas-reference/action-cards.md)
- [Action Connections](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/canvas-reference/action-connections.md)
- [Working with data](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/working-with-data.md)
- [Extracting Information](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/working-with-data/extracting-information.md)
- [Using Information](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/working-with-data/using-information.md)
- [Workflow Copilot](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/workflow-copilot.md)
- [Co-Pilot Best Practices](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/workflow-copilot/co-pilot-best-practices.md)
- [Templates](https://docs.lleverage.ai/build-and-improve/automate/build-a-workflow/templates.md)
- [Human handoffs](https://docs.lleverage.ai/build-and-improve/automate/human-handoffs.md): Add deliberate human decisions or input to a running Workflow without confusing them with Agent conversation.
- [Request Decision](https://docs.lleverage.ai/build-and-improve/automate/human-handoffs/request-approval.md): Pause a Workflow and ask an assigned person to make a defined decision before execution continues.
- [Request Input](https://docs.lleverage.ai/build-and-improve/automate/human-handoffs/request-input-page.md): Pause a Workflow and collect structured information from an assigned person before execution continues.
- [Publish apps & APIs](https://docs.lleverage.ai/build-and-improve/automate/publish-apps-and-apis.md)
- [Sharing](https://docs.lleverage.ai/build-and-improve/automate/publish-apps-and-apis/sharing.md)
- [Chat App](https://docs.lleverage.ai/build-and-improve/automate/publish-apps-and-apis/chat-app.md)
- [Form App](https://docs.lleverage.ai/build-and-improve/automate/publish-apps-and-apis/form-app.md)
- [API Endpoint](https://docs.lleverage.ai/build-and-improve/automate/publish-apps-and-apis/api-endpoint.md)
- [REST API](https://docs.lleverage.ai/build-and-improve/automate/publish-apps-and-apis/rest-api.md): Use Project API tokens to call Lleverage's versioned REST API from services, scripts and other programmatic clients.
- [Test and publish](https://docs.lleverage.ai/build-and-improve/automate/test-and-publish.md): Validate a Workflow against real execution behaviour, then publish the version that production can use.
- [Run Panel](https://docs.lleverage.ai/build-and-improve/automate/test-and-publish/run-panel.md)
- [Error handling and validation](https://docs.lleverage.ai/build-and-improve/automate/test-and-publish/error-handling-and-validation.md): Configure explicit retry or continue behaviour and understand what validation cannot protect you from at runtime.
- [Tests](https://docs.lleverage.ai/build-and-improve/automate/test-and-publish/tests.md): Test a Draft Workflow as a real execution, with explicit awareness of external side effects and test-mode differences.
- [Publishing workflows](https://docs.lleverage.ai/build-and-improve/automate/test-and-publish/publishing-workflows.md): Publish a Draft Workflow into the version that live traffic, triggers and operator-facing apps can use.
- [Scheduling workflows](https://docs.lleverage.ai/build-and-improve/automate/test-and-publish/scheduling-workflows.md): Configure the current recurring schedule options for a published Workflow and understand when they take effect.
- [Advanced workflow building](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building.md)
- [Subworkflows](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/subworkflows.md)
- [Agent](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/agent.md)
- [AI](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/ai.md)
- [Prompt](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/ai/prompt.md)
- [AI Web Search](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/ai/ai-web-search.md)
- [Generate Image](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/ai/generate-image.md)
- [Evaluate](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/ai/evaluate.md)
- [Categorise](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/ai/categorise.md)
- [Browser Agent](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/ai/browser-agent.md)
- [Custom Code](https://docs.lleverage.ai/build-and-improve/automate/advanced-workflow-building/custom-code.md)
- [Intelligence](https://docs.lleverage.ai/build-and-improve/intelligence.md): Maintain the Skills, structured data, files, reference material and Memory that give an Agent reusable project context.
- [Memory](https://docs.lleverage.ai/build-and-improve/intelligence/memory.md)
- [Skills](https://docs.lleverage.ai/build-and-improve/intelligence/skills.md): Create and maintain reusable Agent capabilities that encode how a recurring operational task should be done.
- [Tables](https://docs.lleverage.ai/build-and-improve/intelligence/tables.md)
- [Files](https://docs.lleverage.ai/build-and-improve/intelligence/files.md)
- [Knowledge](https://docs.lleverage.ai/build-and-improve/intelligence/knowledge.md)
- [Monitoring](https://docs.lleverage.ai/build-and-improve/monitoring.md): Inspect what Lleverage actually executed, where work stopped and whether the business result followed from the run.
- [Alerts](https://docs.lleverage.ai/build-and-improve/monitoring/alerts-system.md): Use alerts to surface operational conditions that need attention without continuously watching Monitoring.
- [Tutorials](https://docs.lleverage.ai/build-and-improve/tutorials.md)


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.lleverage.ai/build-and-improve.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.