loading
Loading.Work
We don't run on testimonialswe don't have.
Real engagements, told straight: the context, the gap, what we did, and an honest outcome. 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.
Two of these are paid client engagements; two are our own ventures, the products we build and run ourselves. We tag which is which. The honest proof that we can run AI in production is that we run it on our own software first.
Consulting · quant financeClient engagement
Clareo Systems
From copilot to operator, inside a high-stakes finance environment.
- Context
- Clareo Systems is a quantitative finance firm, where correctness and risk control are non-negotiable and “move fast and break things” is the wrong instinct.
- The gap
- A strong team using AI as a copilot, with the ceiling that implies. The jump to running agents as operators, safely and inside their controls, is a skill and process change, not a license.
- What we did
- Agentic-development training for the team, set up the agentic process and guardrails for their environment, and upskilled the CTO to lead it. Their people operating agents, on their standards.
Studio · real estateClient engagement
Compagnie Immobilière du Léman
Marketing and product, both running on agents.
- Context
- A real-estate business that needed to scale content and marketing output (market notes, area guides, listings, editorial) and modernize its platform, without scaling headcount to match.
- The gap
- Manual content and marketing couldn't keep pace, and the platform wasn't built for an agent-first way of working.
- What we did
- Automated their acquisition marketing, stood up agentic blog-content creation in their voice, built an agentic-first platform, and ran GEO/SEO so the content gets found, including by AI engines.
Self-proof · own ventureOur own venture
Our own studio
We run what we sell, on our own operations and products.
- Context
- We are our own first client. We don't just advise on running AI in production; we run it on our own operations and products, which is the honest test of everything we sell.
- The gap
- Real business operations (accounting, billing, payroll) and product development that a small team can't carry at the pace we hold ourselves to, without agents doing real work.
- What we did
- Built internal AI for accountants, an automated billing pipeline, and a payroll engine, and stood up autonomous dev teams that build and ship. The operating model we transition clients into is the one running our own business.
Outcome
AI-run accounting, billing, and payroll, plus autonomous dev teams shipping product.
Read the case →Studio · civic techOur own venture
Open Truth
Applying agents to a problem most teams wouldn't attempt.
- Context
- Open Truth tackles verification of political claims, a domain where being right, sourced, and unbiased matters more than being fast or clever.
- The gap
- Claim verification at scale is beyond manual fact-checking, and a naive LLM that just answers is the wrong tool: it has to be sourced, checkable, and resistant to confidently-wrong output.
- What we did
- Built the algorithm plus the agent system that verifies political claims, designed so the output is grounded and auditable rather than an opinion. A novel AI system, not an off-the-shelf chatbot.