Divine Ogbe

Divine Ogbe
London

Engineer.
Founder.
Going back to hardware.

Software engineer and technical leader with 8+ years across fintech, e-commerce and AI. Trained in electrical and electronics engineering, based in London.

Where I've been

  • Covenant University Master's degree in electrical and electronics engineering, specialising in power systems.
  • Stakle Real-time financial analytics for five institutions, serving 5M+ visits at 99.9% uptime.
  • Papyrus Owned complex modules for enterprise clients.
  • Motorway Senior engineer. Led a team of 10 on the MOT and tax checker, lifting retention 4%. Won the 2023 hackathon.
  • MediTech Ex-CTO at a Nigerian healthtech.
  • Sunday Morning Co-founder & CTO. Agentic recruitment built on Graph RAG, with an MCP server ChatGPT and Claude query directly. usesm.com

Publications

Cited 26 times · Google Scholar

UK Global Talent Visa

Endorsed by Tech Nation in November 2022 for leadership in digital technology.

Building

Lithe

An open-source, Jest-style test runner for AI agents. Write tests in TypeScript, mock the model and its tools, check what the output means rather than its exact wording, and see step by step where an agent's behaviour changed between commits.

$ npx lithe
tests/agent.test.ts
  ✓ asks before sending email (812ms)
  ✓ never ghosts a candidate (1.4s)

control-eval

An AI-control harness. When an agent doing routine DevOps work is also quietly trying to exfiltrate a secret, how often does a cheaper monitor model catch it, and at what false-alarm cost? Fully sandboxed, scored against independent ground truth.

$ npm run eval -- --pairs 20 \
    --agent claude-opus-4-8 \
    --monitor claude-haiku-4-5
→ catch rate vs false alarms
→ AUC, refusals, and the misses