The best AI products aren't the smartest. They're the ones that change safely, every week.

That is what we build: the evals, workflows, and infrastructure that let a team ship fast without shipping regressions. Four proofs from this quarter.

Rebuilding without stopping the business

2 weeksto cut over, Java → Python

0rollbacks after launch

0releases frozen during the migration

A consumer AI video app had outgrown its original engine and was slowing down with every release.

We rebuilt it and cut over in two weeks with zero rollbacks, so the team kept shipping to users the whole time instead of freezing for a quarter. When an AI product outgrows its first codebase, that is the work we do: replace the foundation without stopping the business.

This year the team grew to 20, and shipped to production every week of the quarter.

More client work

Made prompt changes safe to ship

For a B2B AI product, the content that most shaped answer quality was edited by hand with no safety net: you shipped an edit and hoped. We put evals in the release pipeline as a gate, so a change that would lower answer quality is caught before a customer sees it. 193 automated checks now sit between an edit and production, and nothing ships unreviewed — so the team can improve the product every day without gambling on quality.

Made the product feel 50–60% faster in the moment that sells it

In a consulting-AI product, the live board is what a consultant shows the client, so its speed is the product's felt quality. We made that board render 50–60% faster and stream in as it builds, at cache-read pricing rather than full cost. The moment that matters most, live in front of a client, now feels instant.

Turned a capability that needed screen-sharing into a link

Letting a client watch that board update live once meant screen-sharing or emailing a file, and only worked on a single server. We made it stream over the web as live snapshots, across any number of machines, with no account and no install. Friction became a link anyone can open.

Worth reading

Prompt caching, and how to think about itWhere caching saves real money and latency with large models, and where it quietly does not. → The metrics we judge AI output byHow we measure whether a model's output is good, and keep our evals honest as the product changes. → How we run a big migration without regretThe questions we answer before a rewrite, so it ships in weeks instead of stalling for a year. →

What we make

Products that are born out of our AI-first workflows.

StenoMeeting notes that write themselves, clean and searchable when the call ends.steno.unravel.tech ↗ thingShip your coding agents' output as live, commentable, versioned pages. This letter runs on it.usething.ai ↗ TabloKeeps a human in the loop on your AI coding agents, live from the corner of the screen.tablo.unravel.tech ↗

Planning an AI product, or a rebuild that can't afford downtime?

Thirty minutes, and we'll tell you straight what it takes, what it's worth, and how fast we can do it.

Book a call or reply to this email — it reaches us directly at kapil@unravel.tech