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

# Quickstart

> Create and run your first CiCi evaluation.

This guide is for product users who already have access to a CiCi workspace.

## Before you begin

Have the following ready:

* One human-facing AI workflow to evaluate
* A specific behavior you want the experience to support
* Two product variants or configurations to compare
* Representative situations in which people use the workflow
* A decision you expect the evidence to inform

<Steps>
  <Step title="Create or open a notebook">
    Use a notebook to hold the evaluation question, scenarios, variants, signals, runs, and results for one product workflow.
  </Step>

  <Step title="Describe the intended behavior">
    Write the behavior in terms a reviewer could observe or score. Prefer “The user identifies the correct next step” over “The experience is helpful.”
  </Step>

  <Step title="Define signals">
    Choose the measurable signs that distinguish the intended behavior from its alternatives. Keep each signal focused on one judgment.
  </Step>

  <Step title="Add scenarios and variants">
    Use situations that represent real decisions, including cases where the correct response is uncertain, constrained, or requires escalation.
  </Step>

  <Step title="Review readiness and launch">
    Resolve the readiness checks, confirm the frozen study setup, and launch the sprint. CiCi runs APM tasks in the background and reports progress.
  </Step>

  <Step title="Read the Results summary">
    Start with lifecycle status and evidence limits. Then inspect Behavioral Evidence, outcomes supported by frozen briefs, and any available Signal Gap.
  </Step>

  <Step title="Choose the next evidence step">
    If modeled evidence is sufficient for your immediate decision, create a test-ready refinement brief. If the decision depends on how people actually respond, plan human validation.
  </Step>
</Steps>

<Tip>
  Start with one workflow and a small, decision-relevant signal set. A broad evaluation with vague signals is harder to interpret than a narrow evaluation tied to a real product decision.
</Tip>

## Next steps

<CardGroup cols={2}>
  <Card title="Plan an evaluation" href="/evaluations/plan-an-evaluation" icon="clipboard-list">
    Turn a product question into scenarios, signals, and comparison variants.
  </Card>

  <Card title="Read your results" href="/results/read-your-results" icon="chart-line">
    Interpret the lifecycle panel, evidence views, and withheld claims.
  </Card>
</CardGroup>