> ## 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.

# Use AI for more of your work. Keep your standards.

> Connect your repo and EvalGate finds the AI in your code: model calls, prompts, agents, and tools. Test what they do, catch regressions before release, and keep the proof.

**Use AI for more of your work. Keep your standards.**

Connect your repo and EvalGate finds the AI in your code: model calls, prompts, agents, and tools. Test what they do, catch regressions before release, and keep the proof.

CI for AI behavior: trace → eval → gate.

[Run the public refund demo](https://github.com/evalgate/refund-agent-demo) to reproduce PASS → BLOCK → PASS with the published SDK. [Independent clean-install evidence](https://github.com/evalgate/refund-agent-demo/actions/runs/38460889746).

Agents can start with the [structured JSON API view](https://www.evalgate.com/?mode=agent)
or the [agent discovery guide](https://evalgate.com/docs/guides/agent-discovery.md). The public
[Skills repository](https://github.com/evalgate/skills) includes
[AGENTS.md](https://github.com/evalgate/skills/blob/main/AGENTS.md), the
[Agent Plugins manifest](https://github.com/evalgate/skills/blob/main/plugin.json)
and bundled skills/MCP configuration. Try the
[credential-free API test mode](https://evalgate.com/docs/platform/api-test-mode.md) with synthetic text.

The product is one operating loop: **trace to eval to gate**. Real behavior
produces evidence, reviewed failures become test cases, and promoted test cases
become CI gates before a prompt, model, retriever, or agent change ships.

> [card] [Quick start](https://evalgate.com/docs/quickstart.md)
>
> Run a reviewed case, accept a passing baseline, and watch a deliberate regression exit 2.

> [card] [Trace to eval to gate](https://evalgate.com/docs/concepts/trace-eval-gate.md)
>
> Understand the operating loop before you wire in platform features.

> [card] [SDK and CLI](https://evalgate.com/docs/sdk/typescript.md)
>
> Install the TypeScript or Python SDK and use the same assertions locally, in app code, and in CI.

> [card] [Framework recipes](https://evalgate.com/docs/guides/framework-recipes.md)
>
> Copy setup paths for Node, Next.js, Python, FastAPI, LangChain, and RAG apps.

> [card] [API reference](https://evalgate.com/docs/api/overview.md)
>
> Integrate directly with the EvalGate platform for traces, runs, projects, and keys.

> [card] [Feature status](https://evalgate.com/docs/platform/feature-status.md)
>
> See which surfaces are Shipped (live), which client gaps remain, and where to find verification evidence.

> [card] [Platform map](https://evalgate.com/docs/platform/platform-map.md)
>
> Task-oriented map of EvalGate surfaces when the product feels too large.

> [card] [Evaluation layers](https://evalgate.com/docs/concepts/evaluation-layers.md)
>
> How application evaluation, evaluator measurement, qualification, and authorization fit together.

## The adoption path

**1. Prove one local gate**

Install the SDK without an account, replace the placeholder with a real check, and accept a reviewed passing baseline. Run the same gate after a deliberate regression before adding it to CI.

**2. Capture real failures**

Add tracing when local gates are not enough. EvalGate captures production and staging behavior with inputs, outputs, tool calls, latency, token usage, cost, and metadata.

**3. Promote failures into coverage**

Convert repeated or high-risk failures into reusable eval cases. Label, cluster, synthesize, and review cases so your suites track actual user pain.

**4. Gate releases with evidence**

Run the eval suite in CI, compare against the baseline, and give reviewers clear pass/fail evidence before changes merge.

## What to use first

EvalGate surfaces marked **Shipped** in [Feature status](https://evalgate.com/docs/platform/feature-status.md) are live and available. Review that inventory for client gaps before depending on a convenience SDK or CLI method.

| Stage | Use this | Outcome |
| - | - | - |
| First repo | Repository activation + local gate | A baseline and a regression report you can trust |
| Production AI feature | Traces and eval runs | Turn real behavior into coverage |
| Team rollout | Reviews, judges, PR annotations | Make AI quality reviewable |
| Governed rollout | Costs, benchmarks, audit history | Track quality, spend, and release evidence |

> [!NOTE]
>
> Judges and other model-backed workflows are **bring your own provider key (BYOK)**: your provider or gateway credential is used and bills model usage directly. [Understand BYOK and model-provider setup](https://evalgate.com/docs/platform/model-providers-byok.md).

## Explore next

> [card] [CI/CD integration](https://evalgate.com/docs/guides/cicd-integration.md)
>
> Wire EvalGate into GitHub Actions or GitLab CI to gate every PR.

> [card] [Tracing setup](https://evalgate.com/docs/guides/tracing-setup.md)
>
> Capture the real AI behavior that should become eval coverage.

> [card] [LLM judge](https://evalgate.com/docs/concepts/llm-judge.md)
>
> Add judge-backed scoring when assertions alone are not enough.

> [card] [Model providers and BYOK](https://evalgate.com/docs/platform/model-providers-byok.md)
>
> Connect your provider or gateway credential and understand the separate authentication, billing, and data boundaries.

> [card] [Agent governance](https://evalgate.com/docs/platform/agent-governance.md)
>
> Scale from one gate to governed AI release workflows.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.