Agentic AI consulting for systems that must work in production
Four engagement shapes, each with a concrete thing you keep at the end. I take on a small number at a time so every one gets senior attention.
AI Architecture Review
A senior second opinion on an AI system that is in production or about to be: retrieval, agent orchestration, evaluation, cost, and failure handling.
You get
- Written risk register, ranked by likelihood and blast radius
- Prioritized recommendations with effort estimates
- An evaluation plan you can run before and after changes
- 60-minute walkthrough call with your engineers
I need from you
- Read access to the architecture docs and code
- A sample of real traffic or evaluation data
- One 45-minute kickoff call
Afterwards
Most teams either implement the recommendations themselves or book a prototype sprint for the hardest item.
Best when you have something live or near launch and want it checked before it scales. Full details of the ai architecture review →
Prototype Sprint
One AI capability taken from idea to a working, instrumented prototype with honest numbers, so you can decide with evidence instead of a demo.
You get
- Working prototype on your data, deployed to an environment you control
- Evaluation harness with baseline metrics for accuracy, latency, and cost
- Production-hardening roadmap: what is missing and what it costs to add
- Weekly written progress notes and a final review call
I need from you
- Representative sample data and access to the systems it touches
- A decision owner who can answer questions within a day
- A 30-minute check-in each week
Afterwards
You own the code and the eval harness. If it proves out, I can stay on to harden it or hand it to your team.
Best when you need to prove feasibility or win stakeholder buy-in fast. Full details of the prototype sprint →
Production AI Implementation
Design, build, integrate, and deploy an AI workflow end to end, including evaluation, monitoring, documentation, and handover to your team.
You get
- A production workflow running in your environment, with verification and human-escalation paths
- Evaluation harness and per-decision monitoring of accuracy, cost, and latency
- Architecture documentation and an operational runbook
- Structured handover sessions so your team owns the system
I need from you
- A decision owner and an engineering contact who can answer questions within a day
- Access to the data and systems the workflow touches, in an environment you control
- Agreement on the success metric before build starts
Afterwards
Your team owns the system. Many teams move to an advisory retainer for design reviews as they extend it.
Best when feasibility is settled and you need the workflow to exist in production, built to survive real data and real review. Full details of the production ai implementation →
Advisory Retainer
Ongoing architecture judgment for a team building AI features: design reviews, model and vendor decisions, evaluation strategy, and hiring support.
You get
- Design review of every significant AI change before it ships
- Async answers within one business day
- A monthly architecture and risk memo
- Interview loop support for AI engineering hires
I need from you
- Access to your design docs and the channel where decisions happen
- One recurring 60-minute call per fortnight
Afterwards
Renew month to month, or step down to occasional reviews once the team is self-sufficient.
Best when you are building an AI team and want senior judgment without a full-time hire. Full details of the advisory retainer →
What determines the price
Every engagement is a fixed quote, agreed in writing before work starts, so there are no surprise invoices. The quote moves on four things:
- How many systems, data sources, and environments are in scope
- Whether the work happens inside regulated or restricted environments (data residency, audit trails, access approvals)
- How fast you need it: a compressed timeline costs more than a steady one
- How much evaluation data and system access already exists versus needs to be built first
If you share a budget range on the contact form I will tell you plainly whether the scope you have in mind fits it.
How to start
Send a short note through the contact form describing the system and where it hurts. I reply within two business days. If there is a fit, we schedule a 30-minute call and I send a written scope and quote within a week. No mailing list, no drip sequence.