How to Add AI Code Review to Your CI Pipeline

What You'll Build

A CI step that calls an AI code review agent on every push, returns a structured score, and optionally blocks the merge if quality is below your threshold.

Prerequisites

The Workflow

Create .github/workflows/code-review.yml:

name: AI Code Review
on: [pull_request]

jobs:
  review:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Run code review
        run: |
          DIFF=$(git diff origin/${{ github.base_ref }}...HEAD | head -c 12000)
          RESPONSE=$(curl -sS -X POST https://www.runcept.com/api/v1/run \
            -H "Authorization: Bearer ${{ secrets.RUNCEPT_API_KEY }}" \
            -H "Content-Type: application/json" \
            -d "{\"agent\": \"code-reviewer\", \"input\": {\"diff\": \"$DIFF\"}}")
          JOB_ID=$(echo $RESPONSE | jq -r '.job_id')
          for i in {1..20}; do
            sleep 5
            RESULT=$(curl -sS https://www.runcept.com/api/v1/jobs/$JOB_ID \
              -H "Authorization: Bearer ${{ secrets.RUNCEPT_API_KEY }}")
            STATUS=$(echo $RESULT | jq -r '.status')
            if [ "$STATUS" = "complete" ]; then
              SCORE=$(echo $RESULT | jq -r '.output.score')
              echo "Code review score: $SCORE"
              if [ "$SCORE" -lt 60 ]; then exit 1; fi
              break
            fi
          done

JavaScript Client

const response = await fetch('https://www.runcept.com/api/v1/run', {
  method: 'POST',
  headers: {
    'Authorization': Bearer ${process.env.RUNCEPT_API_KEY},
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({ agent: 'code-reviewer', input: { diff } }),
})
const { job_id } = await response.json()

// Poll for result
let result
while (true) {
  await new Promise(r => setTimeout(r, 3000))
  const poll = await fetch(https://www.runcept.com/api/v1/jobs/${job_id}, {
    headers: { 'Authorization': Bearer ${process.env.RUNCEPT_API_KEY} }
  })
  result = await poll.json()
  if (result.status === 'complete') break
}
console.log(result.output) // { score, issues, suggestions }

Next Steps

Use this agent on Runcept

Related guides