Olivier Debeuf De Rijcker

Chief AI Engineer

I build agent systems.

I work with the people who will use the system. I stay when it goes live.

01 / Practice

I find useful business problems with stakeholders, shape the product, build it, and stay involved through acceptance.

Useful model output depends on context, tool boundaries, state, evidence, and clear interfaces.

The implementation covers retrieval, ranking, agent workflows, evaluation, observability, privacy, and production verification.

02 / Systems

I turn model pipelines into usable production systems.

Cortex connects a Next.js interface and FastAPI backend to recruitment data. The source records stay read-only. Recruiter feedback is stored separately, and each user sees only the records they own.

Role
Product + architecture + code
Boundary
Upstream records read-only
Span
CRM data to recruiter decision
03 / Record

Selected evidence

Production systemPublic / linked

Cortex

Rebuilt the recruiting system at Pauwels Consulting around AI. Recruiters get ranked candidates for every vacancy with the reasons shown, and a shortlist that took an afternoon takes minutes. I shaped it with the recruiters who use it, then sat with them through the switch, which took as long as building it. Every shortlist they accept or change feeds back into the ranking.

Next.js + FastAPI / PostgreSQL / Claude Agent SDK / Two-stage matching

Open the launch post
Product launchPublic / linked

Seld

Launched Seld, a local-first, open-source AI chief of staff that keeps open work, decisions, evidence references, and next actions in plain files so agent sessions can be replaced without losing the outcome. I built the product architecture, deterministic continuity layer, public site, and evidence-led release process.

Product + engineering / Open source / Local-first / Agent continuity

Open seld.ai
Open sourcePublic / linked

codex-multiprovider

Released codex-multiprovider 0.1.0 alpha, which lets Codex use Kimi K3 and experimental Claude routes through an external CLI bridge. It includes fail-closed routing, a gated continuity preview for provider exhaustion, Fable review, and private ChatGPT Pro handoffs without changing the signed app.

Python / Codex CLI / Provider routing / Local continuity

Open repository
Open sourcePublic / linked

Databricks MCP Server

Built and open-sourced an MCP server that lets coding agents inspect and operate Databricks environments across notebooks, SQL, and Unity Catalog.

Python / MCP / Databricks / Agent tooling

Open repository
Upstream reviewPublic / linked

Claude Code 2.1.0 regression

Diagnosed a Claude Code 2.1.0 release crash, traced it to semver parsing of a dated changelog header, and submitted a minimal repair. Anthropic confirmed the fix and closed the report.

Failure analysis / Root cause / Upstream review

Open reviewed PR #16683

04 / Method

  1. 01

    Failure analysis

    I start with the point where the model, data, product, and operator disagree.

  2. 02

    Context design

    I treat state, tools, evidence, and permissions as part of the system.

  3. 03

    Testable claims

    I version prompts and schemas, then tie confidence to evidence.

  4. 04

    Runtime verification

    I check deployed behaviour after the branch passes its tests.

  5. 05

    Human control

    People retain the final decision on architecture, risk, acceptance, and consequential actions.

05 / Contact

Technical conversations, open-source work, and media.

Build
Next.js / TypeScript / static export
Type
Onest / IBM Plex Mono
Background
Engineering / company building / commercial operations