Thinkery · Wädenswil, Switzerland
Make AI work better.
Thinkery is an applied AI company focused on context and efficiency. We work with companies that already use AI — improving workflows, making company knowledge usable, and building specialized agents.
I’m Yves, founder of Thinkery. I work directly with clients while building the team around this work.
Yves Gugger · Founder The hard part is context.
The model is rarely the thing that is failing.
Once AI is already being used, the difficult questions move beyond the model itself. What does the system know about the task? What happened before? Which information matters now? What may it do? What can be reused instead of reconstructed?
Companies already hold most of the knowledge their AI needs. The challenge is turning the right part into usable context without pushing everything through every model call.
That is the area Thinkery is going deep on.
Work with Thinkery.
We apply that focus in three areas where context and efficiency materially change the system.
AI Workflows
AI is already part of the team’s work, but the workflow around it often remains improvised. Context gets rebuilt, coding-agent practices stay personal, and extra checking can cancel out the time AI was supposed to save.
Thinkery redesigns the workflow, connects the missing pieces and builds reusable context and agent handoffs where they create value.
Less repetition. Better handoffs. Measurable improvement.
AI Workflows →Knowledge & Context
Company knowledge already exists across documents, systems, code and people. Retrieval can find related information, but real work also depends on authority, history, permissions and current state.
Thinkery designs the context layer around the task — from RAG and retrieval to memory, provenance and context selection.
The right knowledge. At the right moment. Without sending everything.
Knowledge & Context →Specialized Agents
A useful agent needs more than a model and a chat interface. It needs a defined job, the right context, access to tools, clear boundaries and a way to know when a person should take over.
Thinkery designs and builds focused agents around that complete system, while deliberately controlling unnecessary calls, context and cost.
Focused on the job. Measured in real work.
Specialized Agents →From question to system.
We do not start with a predetermined AI deliverable. We start with the work and a question worth answering.
We understand the workflow, form a hypothesis, build enough to test it and measure what changed. Depending on the problem, that can stop at an experiment, become a production system, or be built together with the internal team.
The same people stay close to the problem from the first conversation through implementation. Strategy, design and engineering are not handed from one department to another.
Latest Thinkings.
The questions behind the work, published while we are still working on them.
Every answer carries three prices: francs, seconds and watts. All three move with the same number, and the third appears in no dashboard.
Tokens behave like money. Unbudgeted, they get spent without anyone noticing. Why a longer window is not free, and how more context can make answers worse.
Search finds what is similar. Retrieval has to decide what a task needs. On embeddings, how documents get cut up, and the metric that misleads.
Why we write the question down before we write code. With an example that did not work, and the reason it still sits on the shelf.
What we’re building.
We also build our own technology around the problems we keep encountering.
LeanCTX
LeanCTX is our product for selecting, reusing and measuring AI context. It started from a problem in our own AI development workflow and grew into a system for reducing repeated context without treating quality as optional.
Experience from
- GenTwo
- Zühlke
- Adnovum
LeanCTX · Starred by engineers at
- Microsoft
- Amazon
- IBM
- Red Hat
- Tencent
- Autodesk
- Dynatrace
- Dell
- VTEX
- Zühlke
Engineers at these companies have starred LeanCTX on GitHub. That is a fact about the product, not a client list.
Bring us a question.
If your company is already using AI and you are trying to improve a workflow, make knowledge usable or build a specialized agent, tell us what you are working on.