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

# Quickstart

> Launch the example world, run your agent against its tasks, and follow the scores to the evidence.

This walkthrough tests whether your agent can start engineering triage of a
duplicate invoice and notify finance. You will launch a world, run its two
tasks, and inspect the invoice task's two scorer results.

Before you run, you need a Chronicle account and a **registered, runnable
agent** with the task's tools and model credentials. Registration alone does
not package or execute the agent. Follow [Connect your agent](/platform/agents)
if execution is not configured yet.

You can explore the records and task without an agent in the
[interactive product example](/product-explorer).

<Steps>
  <Step title="Launch the example world">
    Open **Worldsmith** and choose **Coordinate an order-to-cash rollout**.
    Chronicle loads connected Slack, Linear, Salesforce, and SAP records,
    plus two ready-made tasks.

    <Frame caption="The draft's ENG-2 record links order 7001, case 00001001, and the finance handoff channel. Launching uses these records as the starting data." className="product-capture">
      <img src="https://mintcdn.com/chroniclelabs-0d363efc/BRuFTKj-kt84RfoY/images/product/worldsmith-record-focused.png?fit=max&auto=format&n=BRuFTKj-kt84RfoY&q=85&s=6142ce0e7b991d874c778d1eb1cb1961" alt="Draft Linear issue ENG-2 with its duplicate-invoice description and cross-service references" width="808" height="745" data-path="images/product/worldsmith-record-focused.png" />
    </Frame>

    [Open the issue record at full size](/images/product/worldsmith-record-focused.png).

    Choose **Launch world**. In the world's **Twins** tab, wait for every
    service to show **Running**. Launching also saves the tasks as a suite.

    **Checkpoint:** open the world's records and find Linear issue **ENG-2**.
    Its incident description references order **7001**, case **00001001**,
    and **#erp-alerts**—the same IDs used in the task.
  </Step>

  <Step title="Read the task and its checks">
    In the world, open **Tasks → Open task suite**. Select
    **Triage the duplicate invoice incident**. The agent must:

    1. Read ENG-2 and case 00001001 to confirm the incident.
    2. Move ENG-2 to **In Progress**.
    3. Post a new message in **#erp-alerts** containing this exact sentence:

    > ENG-2 is in progress for order 7001; case 00001001 remains open.

    The two attached scorers check the issue change and the handoff message.
    Both have a pass threshold of **1**. The handoff check matches the exact
    sentence, so a paraphrase can fail.

    The instruction also says not to close the case or claim a fix. Add a
    [separate scorer](/platform/tasks-and-scorers) if you want either
    constraint checked independently.
  </Step>

  <Step title="Run an evaluation">
    Open **Backtests → New backtest** and fill in the rows:

    | Row             | Choose                                                            |
    | --------------- | ----------------------------------------------------------------- |
    | **Run**         | Name: `Invoice triage smoke test`. Mode: **Suite**.               |
    | **Agents**      | Your configured agent version, for example `billing-agent@1.0.0`. |
    | **Test data**   | The suite created by the world. Its name ends in **· Tasks**.     |
    | **Grading**     | Leave as is. The task's attached scorers run automatically.       |
    | **Environment** | Leave as is. Each task already has its starting world.            |
    | **Execution**   | Use **1** concurrent trial for the first run.                     |

    Choose **Run backtest**. Two tasks and one agent produce two trials.
    Each gets a fresh world; changes made while exploring the dashboard do
    not become the trial's starting state.
  </Step>

  <Step title="Read the scores and evidence">
    When the run finishes, open **Results → Cases** and find the invoice task.
    Switch to **Raw trials** and select its attempt. Read **Scores** for each
    check's value and threshold, then follow the trial's **Timeline**.

    | You see                                        | Next check                                                                                                                              |
    | ---------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
    | Both checks score **1**                        | Confirm the Linear update and required Slack handoff in the recorded requests and changes.                                              |
    | Issue check **1**, handoff check **0**         | Compare the Slack channel, record IDs, and message text with the required sentence. A zero does not by itself mean no message was sent. |
    | **Failure**, missing scores, or a scorer error | Read the error first. Confirm execution and scoring completed before judging the agent's behavior.                                      |

    **Checkpoint:** you can identify the agent version, its task, each scorer
    result, and the request or record change behind that result. A completed
    run alone is not a passing test.
  </Step>
</Steps>

## Compare a second version

After the first run, register and configure an improved version, such as
**billing-agent\@1.1.0**. Create a **Compare** evaluation, select both versions,
and choose **Set baseline** on **1.0.0**. Keep the same task suite and starting
world. Two tasks and two versions produce four trials.

[Run an evaluation](/platform/evaluations) explains the comparison and result
views in detail.

## Next steps

<CardGroup cols={2}>
  <Card title="Strengthen the checks" icon="list-check" href="/platform/tasks-and-scorers">
    Add a case-open guard or a judge for the agent's explanation.
  </Card>

  <Card title="Build your own world" icon="wand-magic-sparkles" href="/worldsmith/quickstart">
    Describe the system and scenario you want to test.
  </Card>

  <Card title="Run from the API" icon="code" href="/api-reference/evaluations">
    Launch and inspect evaluations with your SDK.
  </Card>
</CardGroup>