AI agent development

Bounded agents that do real work, with logs you can trust.

Agent demos are easy. Agents that survive contact with real data, real permissions, and real edge cases are not. I build bounded agents that use tools, respect permissions, log every action, and hand off to a human when they should. Connected to your workflows, measured by evals, and safe to put in front of real work.

InvestmentFrom $30k

Fixed project fee, scoped to the agent. Complexity (tools, autonomy, integrations) sets the band.

The problem

Most agent demos never reach production.

The gap between a demo and a deployed agent is permissions, logging, evals, and failure handling. A demo answers a happy-path prompt. A production agent has to know what it is allowed to do, prove what it did, and fail safely when the input is strange. That gap is the work.

Where it hurts
Agents that work in a demo and fall apart on real dataNo record of what the agent did or whyNo permission boundaries, so the blast radius is unknownNo evals, so quality is a vibe, not a number
What I build

What you get, and how it is built.

The build

Bounded agents with tool use, permissions, logs, evals, and approval.

Scoped to a real job, given only the tools and permissions it needs, and instrumented so you can see and trust every run.

Included
A bounded agent scoped to a specific jobTool use wired to your real systemsPermission boundaries and a known blast radiusFull run logs and tool-call historyEvals and human approval for the high-stakes steps
How it works

A small number of moves, each one verifiable.

Every stage ships its own deliverables, so you can see progress and correct course before the next one starts.

01

Scope the job

We define exactly what the agent does, what it can touch, and where a human stays in the loop.

Job specPermission mapTool list
02

Build the agent

I build the agent, its tools, and its guardrails against your real systems.

Working agentToolsGuardrails
03

Instrument and eval

Logging, tool-call history, and an eval suite go in so quality is measured, not assumed.

Run logsEval suiteApproval flow
04

Ship and own

You own the agent and its instrumentation. An optional retainer keeps the evals honest as it scales.

DocumentationHandoffOptional retainer
Why me

I do not sell an autonomous workforce. I sell bounded agents that work.

No agent army, no AI employees, no autonomous company. Bounded agents with logs, permissions, approvals, and a number for how well they do the job.

I do not advise on AI from the outside. I build these systems in my own products first, live with the failure modes, and rebuild the parts that break under real users. The patterns I bring to your build are the ones I have already paid for in mine.

Pricing

One project fee. No surprises.

Fixed project fee, scoped to the agent. Complexity (tools, autonomy, integrations) sets the band.

Build
From $30kfixed

A bounded production agent with tools, permissions, logs, and evals.

Scoped, bounded agentTools + permission boundariesLogs + eval suite
Book a call
Typical range
$40k-$90k

Multi-tool, autonomous, or deeply integrated agents sit higher in the band.

Tool orchestrationDeeper integrationsHigher autonomy
Book a call
FAQ

Before you reach out

Next step

Start with a short call. Straight answer either way.

We confirm fit, scope the work, and decide whether to start with the Intensive or go straight to the build.

Newsletter

One letter, every Sunday. Working systems, not hot takes.

Build logs, working systems, and field notes from running a portfolio of AI ventures. Sent weekly, never more.

Weekly. No spam. Unsubscribe anytime.