Operations Agent

Overview

The Operations Agent is in alpha and has known issues that are currently being fixed. Some commands may not work as expected. We’re actively looking for feedback - if you encounter an error, please report it here.

The Operations Agent handles the third phase of AI-DLC. It takes constructed features to production, verifies they work correctly, and sets up monitoring.

Invocation

Claude Code
Cursor
GitHub Copilot

/specsmd-operations-agent

/specsmd-operations-agent

Or use the @ prefix:

@specsmd-operations-agent

/specsmd-operations-agent

Commands

Command	Purpose
`build`	Build the project
`deploy`	Deploy to environment
`verify`	Verify deployment
`monitor`	Set up monitoring

build

Builds the project for deployment:

> build

The agent will:

Check Prerequisites

Verify all construction bolts are complete

Run Build

Execute build commands from tech stack

Run Tests

Execute full test suite

Create Artifacts

Package for deployment

Example Session

User: build

Operations Agent: Starting build process...

## Prerequisites Check
✓ All construction bolts complete
✓ No uncommitted changes
✓ On main branch

## Build
Running: npm run build
✓ TypeScript compilation successful
✓ Bundle created (245KB gzipped)

## Tests
Running: npm test
✓ 47 unit tests passed
✓ 12 integration tests passed
✓ 5 e2e tests passed

## Artifacts
✓ Docker image built: myapp:1.2.0
✓ Image pushed to registry

Build complete. Ready for deployment.

deploy

Deploys to a target environment:

> deploy staging

Or for production:

> deploy production

The agent will:

Environment Check

Verify target environment configuration

Pre-deployment

Run database migrations, cache warming

Deploy

Deploy using configured strategy

Health Check

Verify services are healthy

Deployment Strategies

The agent supports common strategies based on your infrastructure:

Strategy	Description
Rolling	Replace instances gradually
Blue-Green	Switch between two environments
Canary	Route percentage of traffic to new version

Production deployments require explicit confirmation. The agent will show you exactly what will happen before proceeding.

verify

Runs verification after deployment:

> verify staging

The agent will:

Smoke Tests

Run quick sanity checks

Health Endpoints

Check all service health endpoints

Integration Check

Verify integrations are working

Performance Baseline

Ensure response times are acceptable

Example Output

User: verify staging

Operations Agent: Running verification for staging...

## Smoke Tests
✓ Homepage loads (234ms)
✓ API responds (45ms)
✓ Authentication works

## Health Endpoints
✓ /health - OK (12ms)
✓ /health/db - OK (23ms)
✓ /health/cache - OK (8ms)

## Integration Check
✓ Database connection
✓ Redis connection
✓ Email service

## Performance
✓ p50 latency: 45ms (target: <100ms)
✓ p95 latency: 123ms (target: <500ms)
✓ p99 latency: 234ms (target: <1000ms)

Verification passed. Staging is healthy.

monitor

Sets up or checks monitoring:

> monitor setup

Or check current status:

> monitor status

The agent helps with:

Logging

Structured logging configuration

Metrics

Key performance indicators

Alerts

Alert rules and thresholds

Dashboards

Visualization of system health

Key Metrics

The agent suggests monitoring:

Category	Metrics
Availability	Uptime, error rate, success rate
Performance	Latency (p50, p95, p99), throughput
Resources	CPU, memory, disk, connections
Business	Active users, transactions, conversions

Human Checkpoints

The Operations Agent has 4 human checkpoints aligned with environment progression:

Gate	Location	Purpose
Gate 1	After build	Approve build artifacts before deployment
Gate 2	Before staging deploy	Confirm ready for staging environment
Gate 3	Before production deploy	Critical approval for production
Gate 4	After monitoring setup	Confirm operations complete

Production deployment (Gate 3) requires explicit confirmation. The agent will show exactly what will happen before proceeding.

Artifacts

Operations artifacts are stored in:

memory-bank/operations/
├── environments.md      # Environment configurations
├── runbooks/           # Operational procedures
│   ├── deployment.md
│   ├── rollback.md
│   └── incident.md
└── monitoring/
    ├── alerts.md
    └── dashboards.md

Runbooks

The agent generates runbooks for common operations:

Deployment Runbook

Step-by-step deployment procedure:

Pre-deployment checklist
Deployment commands
Verification steps
Rollback procedure

Incident Response

What to do when things go wrong:

Detection and triage
Escalation matrix
Communication template
Post-mortem process

Scaling Runbook

How to handle increased load:

Signs of scaling needs
Horizontal vs vertical
Scaling commands
Verification

Best Practices

Always Verify

Never skip verification after deployment. Automated checks catch issues humans miss.

Stage Environments

Deploy to staging before production. Test the deployment process itself.

Monitor Proactively

Set up alerts before you need them. Don’t wait for production issues.

Document Runbooks

Keep runbooks updated. They’re essential during incidents.

Getting Started

Framework

Ideation Flow

FIRE Flow

AI-DLC Flow

Simple Flow

Compare

Resources

Overview

Invocation

Commands

build

Example Session

deploy

Deployment Strategies

verify

Example Output

monitor

Logging

Metrics

Alerts

Dashboards

Key Metrics

Human Checkpoints

Artifacts

Runbooks

Best Practices

​Overview

​Invocation

​Commands

​build

​Example Session

​deploy

​Deployment Strategies

​verify

​Example Output

​monitor

Logging

Metrics

Alerts

Dashboards

​Key Metrics

​Human Checkpoints

​Artifacts

​Runbooks

​Best Practices

Overview

Invocation

Commands

build

Example Session

deploy

Deployment Strategies

verify

Example Output

monitor

Key Metrics

Human Checkpoints

Artifacts

Runbooks

Best Practices