Anthropic's coding agent for the terminal, your IDE and a desktop app, included in paid Claude plans.
Paid
DevOps engineer
ChangingAI writes configurations, pipelines and infrastructure descriptions on request, while the engineer owns reliability, cost and security. A new part of the job: running AI services in production and monitoring them.
Where this job sits on the map
In the same group: 78 of 100 professions.
What changes
An agent writes configuration files and build pipelines from a description.
Agents work right inside the pipeline: code review, fixes, checks.
There are now AI services to keep an eye on: latency, errors, token costs.
AI drafts, the person decides
How the work splits here: AI prepares a draft, the person checks it and makes the call.
What AI does
- Writes Dockerfiles, pipeline configurations and infrastructure descriptions
- Looks at a failed build and suggests a fix
- Writes runbooks for when something breaks
- Boils logs and metrics down to a short report
You check itRead it, check the facts, fix it. Without this check the draft goes nowhere.
What stays with the person
- Decisions about the reliability and cost of infrastructure
- What agents are allowed to do in production
- On-call duty and incident reviews
- Agreeing on changes with the team
What to learn first
6 lessons from the course, in order. Start with the first one.
- How to write a good promptUserHow to give AI a task: the five parts of a good prompt, Plan Mode, and how to refine an answer instead of starting over.Start here
- Permissions and securityBuilderClaude Code permission modes, secrets in .env and how to store keys in production.
- Headless Mode and CI/CD: Claude without a UIEngineerClaude Code with no interface: the -p flag, --bare, JSON output, GitHub Actions and cost control in CI.
- Production observability: what to monitor when your agent is liveEngineerWhat to monitor on a production agent: five metrics, three alert levels, tools, debugging from a complaint and a dashboard.
- Cost engineering: $20 vs. $200 a month, or how to pay 10 times less for the same resultsBuilderNine ways to cut LLM costs: model choice, caching, batch, local models, limits and monitoring.
- Failure recovery patterns: what to do when your agent breaks in productionEngineerSeven common ways AI agents break in production, how to recover, chaos tests and incident reviews.
Which tools to use
OpenAI's coding agent: parallel background tasks, a desktop app and the cloud.
FreemiumGitHub's AI assistant in your IDE and on GitHub, with chat, an agent, code review and a free plan.
FreemiumA VS Code-based code editor with AI agents, a free Hobby plan and Pro at $20 a month.
Freemium
Ready-to-use materials
- Data security when working with AIChecklist
What not to paste into a chat, which settings to check and how to limit AI agents.
Free Task, context, limits and checks, so the agent does the right thing and breaks nothing.
Free- Cost of your AI tool stackCalculator
What all your AI subscriptions cost per month and per year, and which ones are worth a second look.
Free
How to earn with AI
We don't promise income: results depend on your niche, your market and your work.
- Job
Build an agent into the pipeline for review and routine fixes, and take on reliability and costs yourself.
- Service
Setting up deployment, monitoring and AI cost tracking for small teams launching their own product.
- Product
An infrastructure template for a typical AI service: deployment, secrets, monitoring, backups.
Similar professions
Checked: October 2026