Durable execution
The agent resumes, retries, and finishes. A dropped model call does not lose the work.
Your AI demos great. Production breaks it.
I fix agents that fail silently and burn money. Durable, observable, cost-capped.
I don't build demos.
Most AI projects die in production.
Your agent returns a wrong answer and nothing flags it. The bill climbs and nobody knows why. You have to explain that to your team.
What production-safe means.
Evaluation
A test set catches wrong answers before your customers do.
Cost and latency caps
Hard limits on spend and response time. The agent cannot burn the budget.
I don't build demos.
I work on live agents with real traffic. If you need a demo or a chatbot, I'll refer you to someone else.
What I take
- Production failures on live agents
- Silent wrong answers
- Cost overruns
- Missing or weak evals
- Reliability work on systems already in production
What I turn away
- Demos
- Proofs of concept
- Copilots
- Model-selection theatre
- Chatbots
Need a demo? I'll refer you to someone else.
Engagements open with a failure autopsy.
We start with the logs.
-
Autopsy
We look at what broke in production and what the eval missed.
-
Fix
Durable execution, real evals, and hard caps on spend and latency.
-
Prove
You get a sanitised postmortem you can share with your team.
Postmortems
from real failures.
Each one covers what broke, what the eval missed, and what fixed it.
The first teardown is in progress.
View all writingYour agent is failing. You cannot say why.
Tell me what broke. I'll tell you if I can fix it.
Start a conversation