petruarakiss
indexwriting
aboutprojects
handoff

End of page. Start of the working loop.

If this site did its job, the next step is simple: ask for the private CV, read the field notes, or check the public proof. I am looking for AI product work where the model is only one part of the system.

Request CVRead the notes
available for
Staff / Principal AI product roles
best work
harnesses, retrieval, evals, workflow control
base
Madrid / remote-first
paths
writingprojectsabout
contact
emailLinkedInGitHubX
context before autonomyevals before confidenceproof beats claimscode must stay legiblesystems over demosprivate CV on requestcontext before autonomyevals before confidenceproof beats claimscode must stay legiblesystems over demosprivate CV on request
(c) 2026 Petru Arakissbuilt as a public surface; private documents stay off the web
writing

Field notes on production AI.

Long-form notes on harness engineering, context, evals, traces, and the unglamorous parts that make coding agents and AI systems useful after the first demo.

current essays1 piece
  • 26-04-3013 minAI EngineeringHarness engineering is the missing discipline around coding agents13 min read
editorial map

What this writing is for.

Harness engineering

How coding agents become useful when the repo, tools, tests, browser, traces, and review loops are designed as one operating environment.

Production AI systems

Retrieval, workflow control, permissions, cost boundaries, observability, and the product surfaces people need when the model is wrong or unsure.

Engineering judgment

Notes on using AI tools without outsourcing taste: where automation helps, where it drifts, and how to keep software legible.