about

I’m Filip. I build AI that a person stays in charge of.

Keel Agents is the name I work under: one independent AI engineer building agents, document Q&A and LLM features for small businesses, agencies and startups.

I am self-taught and came to AI engineering from backend and web apps. I would rather show than claim: each project below comes with its tests, its measured results and its limits written down. My public code is on GitHub.

projects

What I have built

Two projects, built on my own to the standard I would deliver to a client. They are portfolio projects, not client engagements. Read the evidence rather than take my word for it.

EU AI Act compliance assistant

You ask a question about the EU AI Act. Every sentence of the answer cites the provision it came from, and the code checks that the provision was really retrieved. When the Act does not support an answer, the assistant refuses.

measured 901 chunks split on the Act’s own structure, 36 questions labelled by hand, 245 offline tests.

Read the case study or see the code on GitHub.

AI service delivery coordinator

It turns a client request into a project plan. A person edits and approves the plan; only then does anything reach Asana and HubSpot. After that it watches delivery and proposes what to do about blockers and slipping dates, for a person to approve.

tested About 6,800 tests plus 85 browser tests. CI runs strict mypy and both Docker Compose stacks.

Read the case study or watch the three-minute walkthrough.

habits

How I work

These five habits show in both projects. They are also what I would bring to yours.

The AI drafts, a person approves

Anything with consequences waits for a person. The AI can propose a plan or draft a message. It cannot send it, or write it into your systems, on its own.

Measured, not assumed

If a claim about quality matters, a test or an evaluation sits behind it. I measure against questions I labelled by hand, and I publish the result even when it is unflattering.

Spend is capped in code

Anything that calls a paid model has a hard limit written into the program, not a polite request in a prompt.

Untrusted text is data

What a customer types, a comment on a task or a note in a CRM is never an instruction. It reaches the model quoted, never as part of the instructions.

Limits are stated plainly

Every project I hand over comes with a list of what it does not do. You should hear that from me before you find it out.

engagements

Working together

Remote and in writing. Scope, decisions and progress are written down, so you can forward them to a colleague without explaining a call.
Updates as the work goes. You see what changed and what I decided, not just that time has passed.
Your repository. The code lives in your repo, with tests and a README another engineer can follow, so you can run it without me.
One person. You talk to the person writing the code.

Tell me what is eating your team’s week.

Send a short brief: what the work is, who does it now, and what it costs you. I reply within two working days with a rough scope, a price range and whether AI is the right tool for it at all.

Send a brief

Or write to keel.agents@gmail.com.