> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pandaprobe.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Turn your agent into a self-healing agent in under 5 minutes

The **PandaProbe Harness** wraps any PandaProbe-instrumented agent in a self-healing envelope: it evaluates every completed turn, posts a diagnostic notice when quality degrades, and gives your agent the tools to analyze its own failures and write — and *prove* — its own operating rules.

<Note>
  Before you begin, make sure you have:

  * A PandaProbe account. Sign up at [app.pandaprobe.com](https://app.pandaprobe.com).
  * A PandaProbe API key + project name.
  * The `pandaprobe` CLI installed and authenticated — the harness reaches the platform exclusively through it.
  * An agent traced with the [PandaProbe SDK](/tracing/get-started/quickstart), so its sessions produce scoreable traces.
</Note>

<Steps>
  <Step title="Install the package">
    <Tabs>
      <Tab title="pip">
        ```bash theme={null}
        pip install pandaprobe-harness
        ```
      </Tab>

      <Tab title="uv">
        ```bash theme={null}
        uv add pandaprobe-harness
        ```
      </Tab>
    </Tabs>

    The core has **zero runtime dependencies**. Framework adapters are optional extras, e.g. `pip install "pandaprobe-harness[langgraph]"`.
  </Step>

  <Step title="Install and authenticate the CLI">
    ```bash theme={null}
    curl -fsSL https://cli.pandaprobe.com/install.sh | sh
    export PANDAPROBE_API_KEY="your-api-key"
    export PANDAPROBE_PROJECT_NAME="your-project-name"
    ```

    <Note>
      Every platform call the harness makes — running evaluations, polling scores, inspecting traces — shells out to `pandaprobe`. It never talks to the REST API directly.
    </Note>
  </Step>

  <Step title="Pick a workspace root">
    The harness maintains its diagnostic workspace (mailbox, journal, rules, eval cases) on disk. The default is `/harness`; point it anywhere writable:

    ```bash theme={null}
    export HARNESS_ROOT="./harness"
    ```
  </Step>

  <Step title="Wire the harness into your agent loop">
    Any custom loop integrates in a handful of lines — no adapter required:

    ```python theme={null}
    from pandaprobe_harness import Harness
    from pandaprobe_harness.agent_tools.native import as_anthropic_tools

    harness = Harness.create()          # provisions the workspace, wires everything,
                                        # runs the startup health check

    # 1. The harness preamble: learned rules + the standing self-diagnostic
    #    protocol + a "N pending notices" banner when something is wrong.
    system_prompt = harness.system_context() + MY_PROMPT

    # 2. The self-diagnostic toolset (14 operations) alongside your own tools.
    specs, dispatch = as_anthropic_tools(harness.toolset)
    tools = my_tools + specs

    # 3. Delimit turns — the harness evaluates each completed turn.
    async def one_turn(session_id: str, user_input: str) -> str:
        async with harness.turn(session_id):
            return await my_agent_step(system_prompt, tools, user_input)
    ```

    Using LangGraph, CrewAI, or another supported framework? A `Harness.for_<framework>()` factory wires turn detection for you — see [Framework adapters](/harness/integrations/frameworks).
  </Step>

  <Step title="Watch a healing cycle">
    Nothing else is required — the loop is fully automatic:

    1. A turn finishes and its session scores **breach** (e.g. `agent_reliability` drops below `0.5`).
    2. The harness posts a **diagnostic notice** to the workspace mailbox and the system context grows a `⚠ HARNESS: 1 pending diagnostic notice(s)` banner.
    3. Guided by the standing protocol, your agent pulls the notice, inspects the flagged traces, and records a mitigation rule — which enters as an unproven **candidate**.
    4. The harness **validates** the candidate automatically (by replaying the captured failure, or by watching the next live sessions) and promotes it to an active rule — or retires it.
    5. The validated rule re-enters the system prompt on every future run.

    Inspect what happened at any time:

    ```python theme={null}
    harness.mailbox.pending()                    # open notices
    harness.rules.active()                       # validated rules
    harness.journal.recent()                     # the cross-run event log
    ```
  </Step>
</Steps>

## Try it offline first

The repository ships runnable, fully-offline demos — no credentials, no network:

```bash theme={null}
git clone https://github.com/chirpz-ai/pandaprobe-harness && cd pandaprobe-harness
uv sync --group dev
uv run python examples/offline_self_heal.py       # the pull loop, end to end
uv run python examples/closed_loop_self_heal.py   # candidate → validate → promote → regression
```

## What's next?

<CardGroup cols={3}>
  <Card title="Concepts" icon="shapes" href="/harness/get-started/concepts">
    What self-healing means here, and the ideas behind the closed loop
  </Card>

  <Card title="How it works" icon="cog" href="/harness/get-started/how-it-works">
    The full pipeline, the workspace on disk, and one healing cycle in detail
  </Card>

  <Card title="Framework adapters" icon="link" href="/harness/integrations/frameworks">
    LangGraph, LangChain, DeepAgents, CrewAI, Claude Agent SDK, OpenAI Agents
  </Card>
</CardGroup>