GitHub Actions · 29 Gate Types · Fail-Closed by Default

Quality Gates That AI Can't Game

AI agents now write your code AND your tests — and they optimize for the metrics they can see. An LLM told to "reach 80% coverage" will generate hollow tests that hit 80.1% while proving nothing. Evidence Gate hides the criteria entirely with Blind Gates, making metric gaming structurally impossible.

.github/workflows/ci.yml
# Add quality gates in 3 lines
- uses: evidence-gate/evidence-gate-action@v1
  with:
    gate_type: "test_coverage"
    phase_id: "testing"
    evidence_files: "coverage.json"

How It Works

Three steps to enforced quality in every pull request

1

Define

Add Evidence Gate to your workflow YAML. Specify gate types, evidence files, and thresholds.

2

Evaluate

Gates automatically verify your evidence files — existence, schema, thresholds, and integrity.

3

Enforce

Fail-closed: pipelines stop on quality violations. Results appear in PR summary and workflow annotations.

Blind Gates: Why AI Agents Need Hidden Criteria

When an LLM writes your code AND your tests, every visible threshold becomes a target to optimize against — not a quality standard to meet

Traditional Gate CI Pipeline GATE 80% coverage (visible) 80.1 AI agent reads threshold LLM generates hollow tests targeting exactly 80.1% vs Blind Gate CI Pipeline GATE PASS or FAIL AI agent cannot see criteria × LLM cannot game what it cannot see

The problem: Traditional CI gates publish their thresholds in workflow YAML. An AI coding agent (Copilot, Cursor, Devin, etc.) instructed to "pass CI" can read these thresholds and generate minimal tests that hit exactly 80.1% coverage — satisfying the metric while proving nothing about quality.

The solution: Blind Gates evaluate evidence server-side against criteria that are never exposed to the pipeline, the repository, or the AI agent. The LLM that generated the code cannot see, reverse-engineer, or optimize against the pass/fail threshold. Quality must be genuine.

How it works: Your pipeline submits evidence files. The Evidence Gate API evaluates them against private criteria configured by your team. The pipeline — and the AI agent driving it — only receives pass or fail. Never the criteria themselves.

Designed for AI Governance

Evidence Gate's design aligns with Japan's AI Business Operator Guidelines

Fail-Closed Safety

All gates default to FAIL. Only explicitly verified evidence earns a PASS. Supports the guideline's emphasis on safety and risk prevention.

Transparency & Trust Levels

Genchi Genbutsu Trust Levels (L1–L4) make evidence reliability explicit. SHA-256 Evidence Chain enables integrity verification of all judgment data.

Security & Accountability

AWS KMS encryption (FIPS 140-2 validated), HMAC-signed cursors, and a maturity-level-based Quality State Model provide auditable governance at every step.

Evidence Gate supports practices aligned with key principles including transparency, safety, and accountability. Learn more about our approach →

This product is not endorsed by or affiliated with any government body. Feature descriptions are for informational purposes only and do not constitute compliance certification.

Agent Governance Ecosystem

Three layers of protection — from CI validation to runtime controls

CI Layer

evidence-gate-action GitHub Actions

Build-time quality gates — validates blueprints, policies, SBOM, and provenance before deploy

Infra Layer

nemoclaw-governance Python CLI & Library

Validates NVIDIA NemoClaw blueprint.yaml and OpenShell sandbox policies before deployment

Runtime Layer

agentgov Proxy + SDK

Runtime cost controls, budget enforcement, and network governance for AI agent operations

evidence-gate-action

29 gate types including NemoClaw blueprint and policy validation. Fail-closed, tamper-proof CI gates.

View on GitHub →

nemoclaw-governance

CLI and Python library for NVIDIA NemoClaw configuration validation. pip install nemoclaw-governance

View on GitHub →

agentgov

Cost-aware governance proxy for AI agents. Budget enforcement, hold/settle billing, streaming controls.

View on GitHub →

Why three layers? NemoClaw provides sandbox isolation but has zero cost controls. agentgov adds runtime budget enforcement. Evidence Gate validates everything at CI time — before code reaches production.

Simple, Transparent Pricing

Start free, upgrade when your team needs advanced features

Feature Free ($0/mo) Pro (Contact) Enterprise (Contact us)
Evaluations/month 100 Unlimited
API calls/month 1,000 Unlimited
All 29 gate types
SARIF output
GitHub Check Runs
SHA-256 integrity hashing
Fail-closed error handling
Three enforcement modes (warn / observe / enforce)
Config file (.evidencegate.yml) — zero required inputs
SBOM gate (CycloneDX/SPDX structural validation)
Provenance gate (SLSA build attestation)
NemoClaw gates (blueprint + policy validation)
Signal-sorted Job Summary (Critical > Warning > Info)
AI agent repair contract (retry_prompt output)
Gate presets
Sticky PR comments
Blind Gate evaluation
Evidence chain verification (L4)
Quality State tracking
Remediation workflows
Missing evidence + suggested actions
Self-hosted deployment
Custom API base URL
Dedicated support
Get Started Free Contact Sales

Up and Running in 5 Minutes

Add quality gates to your GitHub Actions workflow in three simple steps

1 Install from Marketplace

Visit the Evidence Gate Marketplace page and click "Use latest version" to add the action to your repository.

2 Add to your workflow

Add the Evidence Gate step to your GitHub Actions workflow file:

name: Quality Gate
on: [pull_request]

permissions:
  contents: read
  checks: write

jobs:
  evaluate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      # Your build & test steps here...

      - name: Evidence Gate
        uses: evidence-gate/evidence-gate-action@v1
        with:
          # Or use .evidencegate.yml config file for zero required inputs
          gate_type: "test_coverage"
          phase_id: "testing"
          evidence_files: "coverage.json"

3 See results in your PR

Evidence Gate writes a detailed summary to GITHUB_STEP_SUMMARY, visible directly in your pull request's workflow run. Gate pass/fail results, evidence hashes, and threshold evaluations appear automatically — no configuration needed.