I’ll get your team shipping production software with AI agents. I’ve done it.

At ZeroClick, the company behind the two-million-user Pie ad blocker, I built and shipped a production product where AI agents wrote the entire codebase. It made money, I owned it end to end, and the agents worked inside a harness I engineered.

Book a free scoping callTaking new projects now

zsh — harness

100%of the codebase agent-built on the product I shipped at ZeroClick

10 wkspie.yt from first commit to public launch, agents writing the code

14 yrsof engineering standards to hold the output to (ex-PayPal Senior Staff)

Proof

Case study: pie.yt

In 2025 I built pie.yt, an ad-free YouTube viewer, still live, as ZeroClick’s first product developed entirely through what we called harness engineering: instead of writing the code, I engineered the environment that let AI agents write production code I would sign my name to. That environment is the conventions, context files, guardrails, and review gates. I owned the product from conception to launch.

It shipped, it worked, and it is still live. The code met the bar I spent five years holding as a Senior Staff engineer at PayPal, because the harness required it to. That harness is what I build for your team.

Solo founder with an AI-built prototype and no team yet? That engagement looks different: see POC to production.

What agent-ready looks like

Agents usually fail because the codebase and workflow give them nothing to hold onto, not because the models are weak.

Before: agent-hostile

Conventions live in senior engineers’ heads
Thin or slow tests, so nothing verifies agent output
No CLAUDE.md or context files, so every session starts from zero
Agents get blanket access or no access; security is a standoff
Each engineer prompts differently; results can’t be reproduced
Token spend untracked and unbounded

After: agent-ready

CLAUDE.md conventions and skills encode how your team builds
Fast test gates that agent work must pass before review
Hooks enforce policy so nothing relies on the agent’s memory
MCP wiring gives agents your internal tools, scoped and audited
Subagent patterns for review, testing, and migration work
Cost controls and metrics: spend per merged PR, not per seat

What your team gets

Every item below gets committed to your repos and documented.

Harness configuration for your actual repos: CLAUDE.md conventions, skills, hooks, and guardrails
MCP integration: your internal tools, docs, and services wired in so agents work with your context
Security and permissions policy: what agents may touch, enforced technically (scoped credentials, sandboxing, allow-lists, human gates on irreversible actions), written with your security team
CI integration: test and review gates that agent-written work has to pass before a human reviews it
Cost controls: budgets, tracking, and the metrics that distinguish productive spend from waste
Real merged work: we ship items from your actual backlog together, and the first harness-engineered feature is the training vehicle
Playbooks your team keeps: onboarding docs and patterns so the practice outlives the engagement

Start here

Find out what's in the way.

Codebase evaluation through an agent’s eyes: the tests, docs, structure, and CI gaps that block reliable agent work today
A live pilot: I run a real task from your backlog through an agent harness on your actual code, and you watch
Starter harness config for your repos (CLAUDE.md, conventions, guardrails, review gates)
Security and permissions recommendation your security team can sign off on
A sequenced rollout plan (who starts, on what work, measured how) with a fixed quote for the embedded engagement

Agent-Readiness Audit$3,000One to two weeks · fixed price · credited toward the projectBook a free intro call Email me insteadFounding-client terms: I discount the first two projects in this service in exchange for a named case study and a testimonial. Ask on the call.

What engagements cost

Never hourly. The audit produces a fixed quote for everything that follows.

Agent-Readiness AuditThe audit is the entry point. It is useful even if you run the rollout yourselves, and the fee is credited if we continue.	1–2 weeks	$3,000
Embedded EnablementI set up the harness across your repos and ship real backlog items with your engineers pairing alongside.	2–4 weeks	$15k–$30k
Fractional AI Engineering LeadThe tools change monthly; someone senior has to own the practice. A flat retainer keeps the harness current and levels up each team as it onboards.	ongoing	$4k–$7.5k/mo

When this won't work

I will tell you in the scoping call, and again in the audit, if you’re in one of these situations. I’ll decline the engagement rather than take money for a rollout that won’t stick:

Leadership wants a headline, not a workflow change. If nobody senior will spend time in the new workflow, the tools will sit unused no matter how well they’re set up.
The codebase can’t verify anything.If there are close to no tests and no appetite to build a minimum verification layer, agent output can’t be trusted at scale. Fixing that comes first, and it may be all you need from me.
You’re hoping to replace engineers wholesale. This multiplies good engineers. It doesn’t replace them.
Compliance forbids code leaving your network and you can’t run approved models. Sometimes there’s a path. Often the timing is wrong. I’ll tell you which it is.

Guides

Read before you hire anyone

Written from building agent infrastructure that ran in production. If a guide solves your problem outright, you don’t need me.

Questions clients ask

Which tools do you set up?

I’m deepest in Claude Code and the Claude Agent SDK, the stack I used to ship pie.yt and the agent infrastructure at ZeroClick. The harness itself (conventions, context, hooks, gates, CI) is tool-agnostic, which protects the investment as the tools change.

Will agent-written code pass our review bar?

That’s the defining constraint of the engagement. The harness includes the review gates, testing requirements, and conventions that make agent output meet a senior engineer’s bar. Where the codebase blocks that, fixing it is sequenced into the plan.

Is this training or consulting?

It’s embedded engineering. We ship your actual backlog together and the workflow transfers by doing. The first harness-engineered feature your team ships is the training vehicle.

How do we measure whether it worked?

We pick metrics up front: typically cycle time on the pilot team, PR throughput and revert rate, cost per merged PR, and the share of merged work that’s agent-authored. You should see movement during the engagement.

Our security team is nervous. What do agents get access to?

Whatever you decide, enforced technically: scoped credentials, sandboxed execution, allow-listed commands, and human gates on anything irreversible. I write this policy with your security team.

Find out what's in your team's way.

Book a scoping call. Tell me your team size, your stack, and what you've tried. I'll give you a straight answer, including 'you're not ready yet, and here's what to fix first.'

Book a free intro call Email me insteadI personally reply within one business day. · Taking new projects now.