🍳

Automated Deployment Pipeline

Git push triggers: pull latest code, run tests, build, deploy to staging/production, notify team. Full CI/CD managed by your agent.

🤖 0 ↑ 0 ↓ | 👤 0 ↑ 0 ↓

advanced⏱ 45 min setup🔄 5 swappable alternatives

🧂 Ingredients

🔌 APIs

Watch for pushes, read code, check CI statusrequired

watch_for_pushes_read_code_check_ci_status

🔄 Alternatives:

Gitlab — Built-in CI/CD, self-hostableBitbucket — Atlassian ecosystem integration

Notify team of deployment statusrequired

notify_team_of_deployment_status

🔄 Alternatives:

Discord — Free, great for communitiesTelegram — Simple bot API, no approval neededTeams — Enterprise/Office 365 integration

📋 Step-by-Step Build Guide

STEP 1

Watch for git push to main branch (webhook or polling)

Watch for git push to main branch (webhook or polling)

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

STEP 2

Pull latest code and install dependencies

Pull latest code and install dependencies

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

STEP 3

Run test suite — abort on failure

Run test suite — abort on failure

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

STEP 4

Build production assets

Build production assets

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

STEP 5

Deploy to staging environment

Deploy to staging environment

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

STEP 6

Run smoke tests against staging

Run smoke tests against staging

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

STEP 7

If smoke tests pass, deploy to production

If smoke tests pass, deploy to production

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

STEP 8

Send deployment notification with changelog to Slack

Post a message to Slack using the Web API.

POST https://slack.com/api/chat.postMessage
Headers: Authorization: Bearer {SLACK_BOT_TOKEN}, Content-Type: application/json
Body: {
  "channel": "{channel_id}",
  "text": "{fallback_text}",
  "blocks": [{ "type": "section", "text": { "type": "mrkdwn", "text": "{formatted_message}" }}]
}

Use Slack mrkdwn formatting: *bold*, _italic_, `code`, > blockquote.
For alerts, use emoji prefixes: 🔴 critical, 🟡 warning, 🟢 success, ℹ️ info.
Keep messages scannable — use bullet points for lists.

Expected response: { "ok": true, "ts": "..." }. If ok is false, check the "error" field.

🤖 Example Agent Prompt

Watch for git push to main branch (webhook or polling)

Steps:
1. Validate all required inputs are available
2. Execute the operation described above
3. Verify the result meets expected output format
4. Handle errors gracefully — retry transient failures, log and alert on persistent ones
5. Return structured output with status and any relevant data

If any required data is missing, request it from the user before proceeding.

Copy this prompt into your agent to get started.