METAHEURISTICBook a call
[Build]

Hire an AI agent developer.

Someone to actually build the thing: the agent, the tools it calls, the queue it runs on, the dashboard your ops team watches, and the tests that stop it regressing on a Friday.

4.6k
GitHub stars across public work
57
Public repositories

The demo took a weekend. The production version has been “two weeks away” for a quarter. Between them sits work nobody demoed: authentication into six internal systems, a queue that survives a deploy, an approval screen for the cases the agent should not decide alone, and a test suite that catches the regression before your customer does.

An AI agent developer is the person who does that work.

What gets built

The agent

Planning and tool-calling loop, scoped to a task small enough to verify. Budgets, retries, cutoffs, and an escalation path to a human when confidence or permissions run out.

The tools

Each integration wrapped in a narrow, validated, idempotent contract. Real auth, real rate limits, real pagination, real error handling. This is where agents mostly fail and where most of the engineering time goes.

The runtime

Queues, workers, durable execution for long-running tasks, and a deploy that does not lose in-flight work. Temporal or a job runner when the workflow must survive a restart; something far simpler when it does not.

The supervision surface

Approval queues, trace viewers, run history, cost per task, and a kill switch that any ops lead can reach without paging an engineer.

The tests

Golden tasks in CI, adversarial cases alongside the happy path, and a regression gate that blocks a merge when quality drops.

Where agents pay off first

Teams get the fastest return where the work is high-volume, rule-shaped, and currently done by a human copying between two systems:

  • Support triage and drafting - classify, retrieve policy, draft a reply, route the ones that need judgement.
  • Document processing - extraction from contracts, invoices, claims and filings, with a confidence threshold routing the ambiguous cases to a person.
  • Internal research - pull from your own corpus, cite sources, and refuse to answer when the corpus does not cover it.
  • Operations automation - reconciliation, data hygiene, ticket enrichment, onboarding and offboarding runbooks.
  • Engineering workflows - review triage, migration assistance, test generation, dependency and release hygiene.

And where they do not pay off: anything that needs a guaranteed-correct answer every time with no human in the loop, anything where the cost of a wrong action is unbounded, and anything you could solve with a SQL query and a cron job. You will get that answer on the first call, for free.

Working style

Small scope, shipped behind a flag, measured before it is widened. Your engineers in the pull requests from week one. Written decisions, so the reasoning survives after the engagement ends. No runtime to license, no platform lock-in, and the code, prompts and evals are yours from the first commit.

Questions before you hire.

What is the difference between this and the agentic AI engineer page? +

Emphasis. Agentic AI engineering is about the control loop and whether it is safe and measurable. Agent development is the full build around it - integrations, queues, UI, deployment, on-call. Most engagements need both and they are the same person.

Can you integrate with our internal systems? +

Yes, and that is usually the bulk of the work. Salesforce, Jira, Zendesk, SAP, internal HTTP services, SQL warehouses, S3, SharePoint. MCP servers where they earn their place, plain SDK calls where they do not - I have written about when MCP is worth the abstraction tax.

Do you build the UI too? +

The operational surface, yes - approval queues, trace viewers, eval dashboards, the screens your team actually uses to supervise the agent. Consumer-grade product design is better handled by your designer; I will build to their spec.

How do you handle human-in-the-loop approvals? +

As a first-class state in the workflow, not a modal someone forgot. The agent pauses, writes its proposed action and reasoning to a queue, and a human approves, edits or rejects. Approvals are logged and become eval data - the humans are training the next version whether they know it or not.

Can you take over a half-finished build from another contractor? +

Yes. Expect the first week to be an honest audit: what works, what is load-bearing, what should be deleted. You get the teardown in writing before anyone agrees to a rebuild.

Need an agentic AI engineer this quarter?

Contract, fractional, or embedded with your team. Start with a 20-minute call - you leave it with an honest read on whether your use case is buildable, whatever happens next.