Deblo.ai
AI tutoring for 250 million African students
Educational platform for CP to Terminale with a Pro tier offering 101 specialized AI advisors across 14 business functions (finance, IT, HR, marketing, legal, ops, and more). French-first. Phone + WhatsApp OTP authentication.
Building Deblo
Six Hours From Empty Page to Apple Review — How We Submitted Déblo to the App Store, Live
Live walkthrough of submitting Déblo to the iOS App Store in six hours: what Apple’s validators rejected (a Unicode superscript), what we corrected (a Promotional Text wasted on third-party brands), and the iOS ASO mechanics almost everyone gets wrong.
Trust the Model, Tell It Less — How We Compressed Déblo’s System Prompts by 38%
Eight hours of prompt compression at the CEO’s directive: five system prompts shrunk from 138K to 85K characters (−38%), 15 verbatim French templates deleted, pricing context plumbed per country, and Déblo’s identity opened beyond Africa to AP/SAT, GCSE/A-Level, and IB.
The Day Déblo Refused a Correct Answer — Twice
A production trace showed Déblo K12 rejecting a Terminale student’s correct answer twice in a row. Eight hours of forensic work, four commits, one A/B-tested model rotation, and a 6-model benchmark later, the math tutor was fixed. Here is exactly what broke, what we changed, and what GPT-5.4-mini’s surprising failure on the Socratic test taught us about picking models for educational AI.
Web Claude Found the Bug. Then It Almost Made It Worse.
How a 270-line voice prompt for Deblo's Ultravox tutor was producing the same scripted greeting every call. Web Claude diagnosed it perfectly, then prescribed a fix that would have doubled the prompt size with non-existent backend hooks. The filter that kept the diagnosis and rejected the prescription.
Why I Had to Correct Web Claude Twice on Deblo's Home Page Strategy
How a 48-hour conversation with Web Claude almost led Deblo into the "ChatGPT for Africa" generalist trap, and why founder market knowledge had to override AI strategic suggestions twice. Plus: what serious AI-augmented product teams actually look like.
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.
Tasks, Goals, and Recurring Reminders
The AI creates tasks from conversation context. Recurrence engine, due-date notifications, org-scoped visibility, and threaded comments on homework assignments.
From Abidjan to 250 Million: The Deblo.ai Story
96 web sessions + 20 mobile sessions in 6 weeks. 24+ tables, 100+ endpoints, 24 AI tools, 101+ advisors. The complete story of building Deblo.ai from Abidjan.
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.
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.
RAG Pipeline: Document Search With pgvector and Semantic Chunking
PostgreSQL with pgvector for embeddings, Datalab API for semantic chunking, Mistral Reranker for top-k refinement, and context compression at 150K tokens.
AI Memory and Context Compression
Fire-and-forget conversation summarization, the save_memory tool, and context compression at 150K tokens. How the AI remembers across sessions for $0.00005 per summary.