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

# Agent Builder

- [Overview](https://docs.uptiq.ai/agent-builder/agent-builder.md)
- [Get Started](https://docs.uptiq.ai/agent-builder/get-started.md): The two surfaces of the builder, and how to find your way around.
- [The Canvas](https://docs.uptiq.ai/agent-builder/the-canvas.md)
- [Build](https://docs.uptiq.ai/agent-builder/build.md): Define what the agent is and what it can reach.
- [Basic Details](https://docs.uptiq.ai/agent-builder/build/basic-details.md)
- [Instructions](https://docs.uptiq.ai/agent-builder/build/instructions.md)
- [Agent Behavior](https://docs.uptiq.ai/agent-builder/build/agent-behavior.md)
- [Runtime & Versioning](https://docs.uptiq.ai/agent-builder/build/runtime-and-versioning.md)
- [Execution Plan/Checklist](https://docs.uptiq.ai/agent-builder/build/execution-plan-checklist.md)
- [Adding a Skill to the Agent](https://docs.uptiq.ai/agent-builder/build/adding-a-skill-to-the-agent.md)
- [Skills & Capabilities](https://docs.uptiq.ai/agent-builder/build/skills-and-capabilities.md)
- [MCP Tools](https://docs.uptiq.ai/agent-builder/build/mcp-tools.md)
- [Apps & Services](https://docs.uptiq.ai/agent-builder/build/apps-and-services.md)
- [Attaching Knowledge to an Agent](https://docs.uptiq.ai/agent-builder/build/attaching-knowledge-to-an-agent.md)
- [RAG Knowledge Pipeline](https://docs.uptiq.ai/agent-builder/build/rag-knowledge-pipeline.md): QORE’s RAG (Retrieval-Augmented Generation) framework enables apps and agents to retrieve relevant information from connected knowledge sources before generating responses.
- [Triggers](https://docs.uptiq.ai/agent-builder/build/triggers.md)
- [Secrets & Variables](https://docs.uptiq.ai/agent-builder/build/secrets-and-variables.md)
- [Test](https://docs.uptiq.ai/agent-builder/test.md): Validate the agent before anyone depends on it.
- [Evals](https://docs.uptiq.ai/agent-builder/test/evals.md): Test agent responses against scored datasets with automated LLM grading.
- [Deploy](https://docs.uptiq.ai/agent-builder/deploy.md): Ship the agent into your product, safely.
- [Export Agent](https://docs.uptiq.ai/agent-builder/deploy/export-agent.md): Bundle an agent's full configuration into a portable, reusable package.
- [Agent Integration](https://docs.uptiq.ai/agent-builder/deploy/agent-integration.md): Embed, call, or drive your agent from your own applications.
- [Authentication](https://docs.uptiq.ai/agent-builder/deploy/authentication.md)
- [Whitelisted Domains](https://docs.uptiq.ai/agent-builder/deploy/whitelisted-domains.md)
- [Guardrails](https://docs.uptiq.ai/agent-builder/deploy/guardrails.md): Protect agent runs with PII masking, tool approval, and model policies.
- [PII masking](https://docs.uptiq.ai/agent-builder/deploy/guardrails/pii-masking.md)
- [Tool execution](https://docs.uptiq.ai/agent-builder/deploy/guardrails/tool-execution.md)
- [Monitor](https://docs.uptiq.ai/agent-builder/monitor.md): Watch the agent in production and improve it from what you learn.
- [Online-Eval](https://docs.uptiq.ai/agent-builder/monitor/online-eval.md): Score every live conversation automatically, in the background, without affecting end users.
- [Reinforcement Learnings](https://docs.uptiq.ai/agent-builder/monitor/reinforcement-learnings.md): Turn reviewed production feedback into approved learning cases.


---

# 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.uptiq.ai/agent-builder.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.