> ## 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. ## New here? Start with EvalGate 101 Everything you need to understand the product in 15 minutes. > [card] [What EvalGate is for](https://evalgate.com/docs/help/evalgate-101/introduction.md) > > One paragraph and one diagram: trace to eval to gate. > [card] [Finding your way around](https://evalgate.com/docs/help/evalgate-101/navigating-evalgate.md) > > The sidebar, the main panel, and where every feature lives. > [card] [Your first local gate](https://evalgate.com/docs/help/evalgate-101/first-local-gate.md) > > Activate a repository, then block a regression in CI before lunch. > [card] [Connect a model provider](https://evalgate.com/docs/help/evalgate-101/connect-provider-key.md) > > Bring your own key so model-backed features can run. ## Evaluations & datasets Build the test cases that define what "good" means for your AI. > [card] [Create an evaluation](https://evalgate.com/docs/help/evaluations/create-evaluation.md) > > From blank page to a runnable eval in two minutes. > [card] [Add test cases](https://evalgate.com/docs/help/evaluations/add-test-cases.md) > > Type, paste, import, or promote a real failure into a case. > [card] [Run an evaluation](https://evalgate.com/docs/help/evaluations/run-evaluation.md) > > One click, then read the pass/fail report. > [card] [Review the results](https://evalgate.com/docs/help/evaluations/review-results.md) > > What the scores, costs, and failures actually mean. > [card] [Install an evaluation pack](https://evalgate.com/docs/help/evaluation-packs/install-pack.md) > > Start with detailed healthcare, legal, support, coding, or financial coverage. ## Repository intelligence Find source-backed AI systems and missing coverage at one exact commit. > [card] [Scan a repository](https://evalgate.com/docs/help/repository-intelligence/scan-repository.md) > > Detect providers, agents, prompts, tools, evals, and release risks without executing repository code. ## Traces & logs See exactly what your AI did in production, then turn it into coverage. > [card] [Explore the logs](https://evalgate.com/docs/help/traces/explore-logs.md) > > Filter thousands of traces down to the one that matters. > [card] [Inspect a trace](https://evalgate.com/docs/help/traces/inspect-trace.md) > > Tree, timeline, tools, cost, scores, and evidence. > [card] [Save views and cohorts](https://evalgate.com/docs/help/traces/save-views.md) > > Keep a query so you never rebuild it twice. > [card] [Export traces](https://evalgate.com/docs/help/traces/export-traces.md) > > Download a bounded, redacted CSV or JSONL file. ## Prompts & scorers Version the prompts and scoring logic that decide quality. > [card] [Create a prompt](https://evalgate.com/docs/help/prompts/create-prompt.md) > > Author, version, and test a prompt before it ships. > [card] [Publish and roll back](https://evalgate.com/docs/help/prompts/publish-prompt.md) > > Promote an approved version, then undo safely. > [card] [Create a scorer](https://evalgate.com/docs/help/scorers/create-scorer.md) > > Deterministic, code, composite, or LLM judge. > [card] [Calibrate a scorer](https://evalgate.com/docs/help/scorers/calibrate-scorer.md) > > Anchor sets, mapping, and the release gate. ## Playground & experiments Safely try a change before it reaches users. > [card] [Run a Playground](https://evalgate.com/docs/help/playground/run-playground.md) > > Compare prompt variants side by side on real cases. > [card] [Pick a winner](https://evalgate.com/docs/help/playground/pick-winner.md) > > Turn the best variant into the new baseline. ## Continuous eval & monitors Watch live traffic and get alerted when quality slips. > [card] [Create a monitor](https://evalgate.com/docs/help/continuous-eval/create-monitor.md) > > Define what to sample and how to score it. > [card] [Simulate, then activate](https://evalgate.com/docs/help/continuous-eval/activate-monitor.md) > > Prove the monitor on history before it touches live traffic. > [card] [Read an alert](https://evalgate.com/docs/help/continuous-eval/read-alert.md) > > What a fired alert tells you and where to go next. ## Copilot & review Let the AI assistant draft changes, then keep a human in charge. > [card] [Ask the Copilot](https://evalgate.com/docs/help/copilot/ask-copilot.md) > > Start a thread from any supported surface. > [card] [Accept or reject a proposal](https://evalgate.com/docs/help/copilot/accept-proposal.md) > > Review the diff, then apply or throw it away. ## Deployments & reports Ship the winning configuration and seal the evidence. > [card] [Deploy an artifact](https://evalgate.com/docs/help/deployments/deploy-artifact.md) > > Promote a versioned, immutable artifact to production. > [card] [Run the eval loop](https://evalgate.com/docs/help/deployments/run-eval-loop.md) > > Carry one failure from trace to signed report. > [card] [Share a signed report](https://evalgate.com/docs/help/deployments/share-report.md) > > Give reviewers a verifiable, revocable summary. ## Settings & account Manage your workspace, team, keys, and billing. > [card] [Invite your team](https://evalgate.com/docs/help/settings/invite-team.md) > > Add members and set their permissions. > [card] [Manage API keys](https://evalgate.com/docs/help/settings/manage-keys.md) > > Create, rotate, and revoke programmatic access. > [card] [Check feature status](https://evalgate.com/docs/help/settings/feature-status.md) > > See what is Shipped (live), Experimental, or Planned. ## Can't find what you need? > [card] [Feature status](https://evalgate.com/docs/platform/feature-status.md) > > The authoritative inventory of what ships today. > [card] [Current-behavior manuals](https://evalgate.com/docs/platform/feature-manuals.md) > > Permissions, limits, failure behavior, and troubleshooting. > [card] [API reference](https://evalgate.com/docs/api/overview.md) > > Integrate directly with the platform. > [card] [Contact EvalGate](https://www.evalgate.com/contact) > > Report a bug or request a guide. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.