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

# How to use EvalGate

> Step-by-step guides in plain English for every EvalGate surface. Start here if you are new.

# How to use EvalGate

Welcome to the EvalGate help center. These guides explain, in plain English and
with screenshots, how to use every part of EvalGate. No prior experience with
evaluation platforms is required. Each article is a short, numbered walkthrough
you can follow top to bottom.

<Note>
  Screenshots in this section show the EvalGate web app. The exact buttons and
  labels may shift between releases, but the steps stay the same. If a screen
  looks different, follow the words, not the picture.
</Note>

## New here? Start with EvalGate 101

Everything you need to understand the product in 15 minutes.

<CardGroup cols={3}>
  <Card title="What EvalGate is for" icon="graduation-cap" href="./evalgate-101/introduction">
    One paragraph and one diagram: trace to eval to gate.
  </Card>

  <Card title="Finding your way around" icon="compass" href="./evalgate-101/navigating-evalgate">
    The sidebar, the main panel, and where every feature lives.
  </Card>

  <Card title="Your first local gate" icon="bolt" href="./evalgate-101/first-local-gate">
    Block a regression in CI before lunch. No account required.
  </Card>

  <Card title="Connect a model provider" icon="key" href="./evalgate-101/connect-provider-key">
    Bring your own key so model-backed features can run.
  </Card>
</CardGroup>

## Evaluations & datasets

Build the test cases that define what "good" means for your AI.

<CardGroup cols={3}>
  <Card title="Create an evaluation" icon="clipboard-check" href="./evaluations/create-evaluation">
    From blank page to a runnable eval in two minutes.
  </Card>

  <Card title="Add test cases" icon="list-ul" href="./evaluations/add-test-cases">
    Type, paste, import, or promote a real failure into a case.
  </Card>

  <Card title="Run an evaluation" icon="play" href="./evaluations/run-evaluation">
    One click, then read the pass/fail report.
  </Card>

  <Card title="Review the results" icon="magnifying-glass-chart" href="./evaluations/review-results">
    What the scores, costs, and failures actually mean.
  </Card>

  <Card title="Install an evaluation pack" icon="box-open" href="./evaluation-packs/install-pack">
    Start with detailed healthcare, legal, support, coding, or financial coverage.
  </Card>
</CardGroup>

## Repository intelligence

Find source-backed AI systems and missing coverage at one exact commit.

<CardGroup cols={2}>
  <Card title="Scan a repository" icon="code-branch" href="./repository-intelligence/scan-repository">
    Detect providers, agents, prompts, tools, evals, and release risks without executing repository code.
  </Card>
</CardGroup>

## Traces & logs

See exactly what your AI did in production, then turn it into coverage.

<CardGroup cols={3}>
  <Card title="Explore the logs" icon="table-list" href="./traces/explore-logs">
    Filter thousands of traces down to the one that matters.
  </Card>

  <Card title="Inspect a trace" icon="diagram-next" href="./traces/inspect-trace">
    Tree, timeline, tools, cost, scores, and evidence.
  </Card>

  <Card title="Save views and cohorts" icon="bookmark" href="./traces/save-views">
    Keep a query so you never rebuild it twice.
  </Card>

  <Card title="Export traces" icon="file-export" href="./traces/export-traces">
    Download a bounded, redacted CSV or JSONL file.
  </Card>
</CardGroup>

## Prompts & scorers

Version the prompts and scoring logic that decide quality.

<CardGroup cols={3}>
  <Card title="Create a prompt" icon="code" href="./prompts/create-prompt">
    Author, version, and test a prompt before it ships.
  </Card>

  <Card title="Publish and roll back" icon="rotate" href="./prompts/publish-prompt">
    Promote an approved version, then undo safely.
  </Card>

  <Card title="Create a scorer" icon="scale-balanced" href="./scorers/create-scorer">
    Deterministic, code, composite, or LLM judge.
  </Card>

  <Card title="Calibrate a scorer" icon="sliders" href="./scorers/calibrate-scorer">
    Anchor sets, mapping, and the release gate.
  </Card>
</CardGroup>

## Playground & experiments

Safely try a change before it reaches users.

<CardGroup cols={2}>
  <Card title="Run a Playground" icon="flask" href="./playground/run-playground">
    Compare prompt variants side by side on real cases.
  </Card>

  <Card title="Pick a winner" icon="trophy" href="./playground/pick-winner">
    Turn the best variant into the new baseline.
  </Card>
</CardGroup>

## Continuous eval & monitors

Watch live traffic and get alerted when quality slips.

<CardGroup cols={3}>
  <Card title="Create a monitor" icon="satellite-dish" href="./continuous-eval/create-monitor">
    Define what to sample and how to score it.
  </Card>

  <Card title="Simulate, then activate" icon="toggle-on" href="./continuous-eval/activate-monitor">
    Prove the monitor on history before it touches live traffic.
  </Card>

  <Card title="Read an alert" icon="bell" href="./continuous-eval/read-alert">
    What a fired alert tells you and where to go next.
  </Card>
</CardGroup>

## Copilot & review

Let the AI assistant draft changes, then keep a human in charge.

<CardGroup cols={2}>
  <Card title="Ask the Copilot" icon="robot" href="./copilot/ask-copilot">
    Start a thread from any supported surface.
  </Card>

  <Card title="Accept or reject a proposal" icon="check-to-slot" href="./copilot/accept-proposal">
    Review the diff, then apply or throw it away.
  </Card>
</CardGroup>

## Deployments & reports

Ship the winning configuration and seal the evidence.

<CardGroup cols={3}>
  <Card title="Deploy an artifact" icon="rocket" href="./deployments/deploy-artifact">
    Promote a versioned, immutable artifact to production.
  </Card>

  <Card title="Run the eval loop" icon="loop" href="./deployments/run-eval-loop">
    Carry one failure from trace to signed report.
  </Card>

  <Card title="Share a signed report" icon="file-signature" href="./deployments/share-report">
    Give reviewers a verifiable, revocable summary.
  </Card>
</CardGroup>

## Settings & account

Manage your workspace, team, keys, and billing.

<CardGroup cols={3}>
  <Card title="Invite your team" icon="users" href="./settings/invite-team">
    Add members and set their permissions.
  </Card>

  <Card title="Manage API keys" icon="key" href="./settings/manage-keys">
    Create, rotate, and revoke programmatic access.
  </Card>

  <Card title="Check feature status" icon="list-check" href="./settings/feature-status">
    See what is Beta, Experimental, or generally available.
  </Card>
</CardGroup>

## Can't find what you need?

<CardGroup cols={2}>
  <Card title="Feature status" icon="list-check" href="/docs/platform/feature-status">
    The authoritative inventory of what ships today.
  </Card>

  <Card title="Current-behavior manuals" icon="book" href="/docs/platform/feature-manuals">
    Permissions, limits, failure behavior, and troubleshooting.
  </Card>

  <Card title="API reference" icon="brackets-curly" href="/docs/api/overview">
    Integrate directly with the platform.
  </Card>

  <Card title="Open an issue" icon="bug" href="https://github.com/evalgate/ai-evaluation-platform/issues">
    Report a bug or request a guide.
  </Card>
</CardGroup>