tsukumocontact

AI dev studio & consulting

We run AI inproduction.Most teams arestill running demos.

AI in production. Ship ~10x.tsukumo turns your dev team into agentic operators — devs who run fleets of AI agents in production, not a copilot that finishes their lines. Prod-grade, on the stack and standards you already have. We build this for ourselves; we'll do it with your team.

Talk to us about your teamSee what we've shipped

We don't sell you a model. We change how your team operates. 

0207the gap

The gap between a copilot in the editor and agents that actually run work in production — that's where most teams are stuck.

  • 01

    You bought the seats. Your devs have Claude Code. It autocompletes, it answers, it's a better search.

  • 02

    You can tell that's maybe 10% of what this is — you keep seeing demos of AI doing far more.

  • 03

    None of it survives contact with your real codebase, your real standards, your real review culture.

  • 04

    It isn't a license problem or a model problem. It's an operating problem.

How do you make agents reliable, cheap, and trustworthy on a real codebase — without breaking what works or scaring the people who built it. That gap is what we do.

0307what we do

Two doors into the same capability.

leg A01 / 02

Studio

We build it.

Product and AI systems, shipped to production at studio pace. The software we ship for ourselves (WRAI.TH, trovex, yoru) is the proof: we run our own agent fleets to build them. You get a product and a demonstration of the way of working.

  • Product builds
  • Agent fleets in prod
  • Owned outcomes
leg B02 / 02

Consulting

We transition your team.

We take a team that uses AI as a copilot and turn it into a team that runs agents as operators, in production. On your existing environment, your standards, your stack. We augment your devs; we do not replace them. The craft stays theirs, and the output multiplies.

  • Strategy
  • Implementation
  • Training
0407we run what we sell

We build our own production tooling.

The software we ship for ourselves is the proof: we run our own agent fleets to build it. Self-proof — we do to ourselves what we'd do for you.

orchestration

WRAI.TH

Runs and coordinates fleets of coding agents over a relay.

context

trovex

Feeds agents the right context at the right time.

observability

yoru

Tells us what the agents actually did, in production.

0507work

We don't run on testimonials we don't have.

Here's what's real. Result numbers are gathered with each client before they go on the site — we publish numbers we can stand behind, or we don't publish them.

01 / 03Self-proof
tsukumo studio — agent fleets building our own software.

Our own studio

We run our own agent fleets to build and ship our software.

Context
We're a developer studio building developer tools, including the open suite — WRAI.TH for orchestration, trovex for context, yoru for observability. Small team, high output expectation.
The gap
Building a multi-tool suite at studio pace is more than a copilot-assisted team can carry. We needed agents doing real, repeated work — not just finishing lines.
What we did
We run AI agents as operators across our own development: fleets that build, test, document, and coordinate, on the same standards we'd hold a client's codebase to. We did to ourselves exactly what we sell.
Outcomemetric pending — verified figure in progress
02 / 03Consulting · anonymized, NDA
Quantitative fund engagement — anonymized under NDA, no identifying detail.

A quantitative fund

AI brought into a high-stakes finance environment, carefully.

Context
A quantitative fund operating where correctness and risk control are non-negotiable, and where “move fast and break things” is the wrong instinct.
The gap
The brief was to scale research and engineering throughput without loosening controls. (Engagement detail kept deliberately generic — anonymized under NDA.)
What we did
We built and transitioned agent capability on their environment, with their controls intact. (Specifics withheld under NDA.)
Outcomemetric pending — verified figure in progress
03 / 03Studio · real estate
Compagnie Immobilière du Léman — AI content and marketing system.

Compagnie Immobilière du Léman

AI applied to real-estate content and marketing.

Context
A real-estate business that needed to scale content and marketing output — market notes, area guides, listings, editorial — without scaling headcount to match.
The gap
They needed to grow publishing cadence and content coverage faster than headcount could.
What we did
We built an AI content and marketing system in their voice and to their standards.
Outcomemetric pending — verified figure in progress

Honesty rule: no invented metrics, logos, or quotes — ever. Until each case has a real, verified outcome, it ships as an engagement summary without a fabricated number.

0607who it's for

For

  • CTOs at startups and scale-ups who've felt the gap.
  • Teams who want to ship at a level seats alone won't reach.
  • Leaders who respect their developers enough to want them stronger, not sidelined.
  • People who treat AI in production as an engineering problem.

Not for

  • Anyone who thinks AI is easy.
  • Anyone who believes buying licenses is the same as capability.
  • Buyers who think the point of AI is to ship the same thing cheaper.
  • Teams looking for a demo to screenshot, not software to run.

This isn't about cheaper. It's about prod-grade and roughly 10x the output from the team you already trust.

0707contact

Your devs are readyto be operators.Your tools arewaiting to wake up.

That's the tsukumo idea. Tell us what you ship and where AI keeps stalling — let's talk about your team.

or email hello@tsukumo.ch