> For the complete documentation index, see [llms.txt](/llms.txt). Every page on this site is also available as markdown at `<path>.md`.

# Guides

Use these guides when you have a specific runtime task to complete. They assume
you already have a `RuntimeSpec` or have worked through the [Quickstart](/docs/quickstart).

## Require approvals before execution

Use [Approvals](/docs/guides/approvals) when plans or tools should pause for a host
application decision before the runtime continues.

## Configure a data environment

Use [Data Environment](/docs/guides/data-environment) to connect Rust-owned storage,
catalog, target database, and knowledge dependencies through runtime config.

## Profile data and export a catalog

Use [Profiling and Catalog Export](/docs/guides/catalog-profiling) to profile a read-only
target database with the CLI, persist the resulting catalog, and export a
portable artifact your runtime consumes through the data environment.

## Attach knowledge and documents

Use [Knowledge and Documents](/docs/guides/knowledge) to index source material and expose
retrieval-backed context to agents through the built-in knowledge tools.

## Expose tools over MCP

Use [Expose Tools Over MCP](/docs/guides/mcp) to serve runtime tools to MCP-aware clients
over stdio or Streamable HTTP.

## Run the local Studio UI

Use [Studio](/docs/guides/studio) to chat with your agents in a local browser interface,
browse attached data sources, create tests, run evals, and inspect runs and
traces.

## Debug system prompts

Use [Debugging System Prompts](/docs/guides/system-prompts) to find the stage where an
agent's system prompt went missing or stale, from `layered_prompt(...)` down
to the provider call. For prompt authoring, see
[Prompts](/docs/concepts/prompts).

## Test an agent without provider credentials

Use [Testing](/docs/guides/testing) to run deterministic and scripted interpreters,
exercise approval flows, and assert emitted events without calling a live
model provider.

## Write evals

Use [Evals](/docs/guides/evals) to score recorded samples, run runtime-backed evals, and
replay scripted coordinator flows through real tools and plan execution.

## Judge final responses with a model

Use [Judge Evals](/docs/guides/judge-evals) to score final response quality with a
rubric-driven LLM judge, weight judges against deterministic scorers, and read
verdicts and traces from eval artifacts.

## Stream runtime events

Use [Streaming Events](/docs/guides/streaming) to adapt runtime event dictionaries into an
HTTP or application-specific event stream.