Work with me
I audit developer-facing products — APIs, docs, SDKs, onboarding flows — by running AI agents through them, then deliver prioritised findings and actionable recommendations.
or write to [email protected]
What you'll get
- Prioritised findings linked to transcript evidence
- Actionable recommendations your team can ship against
- Full session transcripts for your own review
- Reproducible steps for key findings
- Consultation call to walk through results and next steps
🔒 Your report is private — never made public without your agreement.
Matt Steen — product leader, twenty years shipping APIs, integrations, and self-serve experiences.
How I can help
Baseline Audit
A standardised six-task suite covering discovery, onboarding, a core workflow, error handling, cleanup, and reflection. You get an evidence-backed report with prioritised findings, actionable recommendations, and full transcript evidence.
Start here to see where agents and developers get stuck.
Deep-Dive Engagement
Custom task suites designed around your specific workflows and integration paths, covering the surfaces that matter most — API, docs, dashboard, onboarding — with prioritised findings and actionable recommendations.
Go deeper on the workflows that matter most to your team.
How it works
A baseline audit runs in four steps. Deep-dive engagements follow the same shape, scaled up.
1. Scope
A short call to understand your product, the surfaces that matter (API, docs, dashboard, onboarding), and the developer journeys worth testing.
2. Design
I build task suites that mirror the real jobs your users do, not synthetic benchmarks. Baseline audits use a standard six-task suite; deep-dives are custom-scoped with you.
3. Run
AI agents at two capability tiers attempt the tasks, with transcripts captured end-to-end.
4. Report
Prioritised findings tied to transcript evidence, delivered as a written report plus a walkthrough call to talk through what to fix first.
See a sample report →🔒 Your report is private — never made public without your agreement.
Selected prior work
Cut Shopify merchant integration time from weeks to hours — scoped MVP from funnel data
Shipped LLM-based automation across a multi-region content platform
Double-digit lift in new MRR via onboarding redesign