# I build the seam between AI agents and people, and then I make it reviewable.

Engineering lead of a five-person team that went from no process to a shipped product, largest single contributor to the codebase while leading it, and the person who made agent-assisted development a reviewable practice there. On my own time: measured detection-and-tracking pipelines and a shared memory for a fleet of agents.

## Tags

- tech lead
- agent systems
- MCP
- TypeScript
- Python
- applied ML
- tracking and estimation

## Proofs

- 148: merged pull requests across a seven-app TypeScript monorepo in ten months, while leading the team
- 83 / 83: MCP tools annotated and validated at boot; a registry that refuses to start if a tool lies about itself
- 8.24 frames: to declare a track with a sequential test, against 16 for a fixed-sample test and 28 for the best counting rule, at matched error rates
- 1e-6: agreement between the browser tracker on this site and its Python reference, checked by a test, not by eye

## How I work

Measure before you tune. The evaluation harness is written before the algorithm, and every phase is closed by a number on it, never by a feeling. Every parameter carries its provenance (measured, from a paper, derived, decided, or assumed) and the condition that would make me revisit it.

Name the failure mode before anyone asks. The strongest thing an engineer can do is state, unasked and with a number, the regime in which their own method stops working. My project notes carry falsifiers next to results.

Agents are part of the team, so their work is reviewed. I introduced agentic development to a company on day one and then built the rails: an onboarding course as a gate, review of AI sessions as part of code review, a scored rubric with named red flags. Velocity without reviewability is debt.

People get goals, not tasks. An engineer owns their module as its product owner. A tech lead keeps modules in sync, patterns consistent and delivery accountable, and is not a decision bottleneck.

## Principles I hold

- Every phase is closed by a number on the eval harness, not by a feeling.
- One implementation, not a prototype and a rewrite: the harness measures the code that ships.
- Comparisons only at matched false alarms.
- Review of AI sessions is part of code review.
- Decisions are written next to the code, with the reason and the date.
- The only guaranteed loss, with zero variance, is the eternal brainstorm: never starting.

## Contact

The most useful first message is not a role title. Tell me where a person like this is needed and what your hardest problem is. I answer within a day.

- [bohdan@fesenko.ai](mailto:bohdan@fesenko.ai)
- [GitHub](https://github.com/bohdan-fesenko)
- [LinkedIn](https://www.linkedin.com/in/bohdan-fesenko/)
