Services

AI Architecture Review

Duration
1 week
Pricing
Fixed quote after a 30-minute call
My role
I review and advise. Your team implements, or we scope a sprint for me to do it.

You have an AI system that works in demos and mostly works in production, and you need someone outside the team to tell you where it will break before it does. The review reads the architecture and the code, exercises the system against real traffic or evaluation data, and returns a ranked list of risks with the fix for each.

Discuss this engagement

Signs this is the right engagement

How it runs

  1. Kickoff call (45 minutes): goals, constraints, and what keeps you up at night
  2. Days 1 to 3: read the architecture and code, trace real requests end to end, run the evaluation data
  3. Day 4: write the risk register and recommendations
  4. Day 5: 60-minute walkthrough with your engineers, with the written report delivered the same day

What you get

What I need from you

When this is the wrong engagement

Afterwards

Most teams either implement the recommendations themselves or book a prototype sprint for the hardest item.

Relevant work

A Second Opinion by Design: Dual-Model Validation for Financial Document Extraction

Fintech · In production

98.7% extraction accuracy

A dual-LLM extraction and judge pipeline reaching 98.7% accuracy and cutting manual review time by 78.3% across financial documents.

Natural Language Access to Production Data That Refuses to Guess

Manufacturing, industrial data · Delivered

18 verification steps before any answer, backed by 700+ automated tests

A plain-language query layer over a manufacturing data warehouse that runs 18 verification steps before answering, and says so when it cannot answer reliably.

Related writing

A Second Check, Always

Essay · September 2, 2026 · 10 min read

One model doing the work and an independent mechanism checking it is the single most reliable pattern I know for production AI. Here is how to build it.

Refuse Over Guess

Essay · September 2, 2026 · 12 min read

Why the most important design decision in a production AI system is deciding when the model is not allowed to answer, and how to engineer that refusal.

Pricing

Every engagement is a fixed quote agreed in writing before work starts. The quote moves on four things:

Start with a short note

Describe 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 within a week.