Blog
All articles. All pillars. All authors.
Detecting AI Agents in Your Codebase
A 3-tier detection hierarchy: Co-Authored-By commit trailers, environment variables (CLAUDE_CODE, CURSOR_SESSION), and TTY heuristics for identifying AI-generated code changes.
From 5 Agents to Production: Shipping 0diff in 20 Minutes
The full story: 5 parallel agents built 0diff in 45 minutes (2,356 lines, 44 tests), then a 20-minute polish session made it production-ready.
AI Tutoring for 250 Million African Students
The vision behind Deblo.ai: an AI tutor that speaks French, understands the African curriculum from CP to Terminale, costs pennies per question, and works on any phone.
100 Sessions Later: The Architecture of an AI Education Platform
FastAPI + SvelteKit + PostgreSQL + Redis + React Native. 24+ tables, 100+ endpoints, 60+ components, SSE streaming. The full architecture of Deblo.ai.
The Agentic Loop: 24 AI Tools in a Single Chat
Up to 10 iterations of LLM calls, 24 tools from file generation to code execution, background jobs for 30-minute tasks. The agentic heart of Deblo.ai.
System Prompts That Teach: Anti-Cheating, Socratic Method, and Grade-Level Adaptation
Six-layer prompt assembly: root identity, school hours detection, grade overlays from CP to Terminale, subject expertise, and exam mode. How we taught the AI to teach.
WhatsApp OTP and the African Authentication Problem
Email does not work. SMS is expensive. WhatsApp is universal. How we built authentication for Africa with WhatsApp OTP, Google OAuth, and student access codes.
Credits, FCFA, and 6 African Payment Gateways
USD-cent pricing, 13 currencies, Orange Money and M-Pesa, 3 payment gateways, webhook-driven confirmation, and a background poller. Monetizing an African SaaS.
Organizations: Families, Schools, and Companies on One Platform
Multi-tenant organizations with shared credit pools, join codes, access codes for phoneless students, and role-based membership for families, schools, and companies.
Six Languages, One Platform: i18n for Africa
French, English, Arabic (with RTL), Swahili, Portuguese, Spanish. How we built internationalization for a continent with hundreds of languages.
Observability: Tracking Every LLM Call in Production
AILog tracks every LLM call. SystemSetting enables config without redeploy. ExerciseResult measures learning. The admin dashboard behind the obscured route.
Why We Stopped Building Features and Polished the Dashboard Instead
We had a backlog of features to build. Instead, we spent a session making every sidebar look the same. Here is why that was the right call.