Services
Advisory Retainer
- Duration
- Monthly, 3-month minimum
- My role
- I advise. I do not implement on a retainer, so your team stays the owner.
Your team is shipping AI features and making architecture decisions every week. A retainer puts a senior reviewer in the loop before those decisions harden: each significant change gets a design review, model and vendor choices get an outside opinion, and evaluation strategy stays honest.
Discuss this engagement
Signs this is the right engagement
- The team is strong but nobody has shipped agentic systems at production scale before
- Model and vendor choices are being made on benchmarks rather than your workload
- You are hiring AI engineers and want an experienced interviewer in the loop
- Design decisions keep getting revisited because nobody owns the architecture
How it runs
- Month 1: architecture baseline and a written risk memo
- Ongoing: design review of every significant AI change before it ships, async answers within one business day
- Fortnightly 60-minute call with the team lead
- Monthly architecture and risk memo for leadership
What 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
What I need from you
- Access to your design docs and the channel where decisions happen
- One recurring 60-minute call per fortnight
When this is the wrong engagement
- You need someone to write the code (that is a prototype sprint)
- There is no team yet to advise
Afterwards
Renew month to month, or step down to occasional reviews once the team is self-sufficient.
Relevant work
SaaS customer support, internal operations · In production
94.2% of tickets resolved fully automatically
A multi-agent system that resolves 94.2% of support tickets on its own and hands humans a ranked summary for everything else.
Fintech, SME accounting · In production
100K transactions processed, over 90% automated end to end
An AI-native accounting platform that has matched, categorized, and posted 100K transactions across 10+ businesses with over 90% automated end to end, escalating only what it cannot resolve.
Related writing
May 9, 2026 · 3 min read
Anthropic's agent templates for regulated industries matter less for the customer logos than for the orchestration topology underneath: lazy-loaded skills, governed connectors, and isolated subagents.
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.
Pricing
Every engagement is a fixed quote agreed in writing before work starts. 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
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.