Blog
All articles. All pillars. All authors.
Generating PDFs, Spreadsheets, and Slide Decks From a Chat Message
Six file generation tools: XLSX, PDF, PPTX, DOCX, HTML, MD. The AI plans the structure, generates via Python libraries, uploads to S3, and streams progress.
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.
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.
Why We Built a Programming Language From Scratch
Why Juste A. GNIMAVO and AI CTO Claude built FLIN, a programming language replacing 47 technologies, from Abidjan.
47 Technologies Replaced by One Language
FLIN replaces 47 technologies -- React, Next.js, Express, Prisma, Redux, and more -- with one unified language.
Interactive Quizzes With LaTeX: Testing Students Inside a Chat
Two-phase anti-cheat quizzes: the AI sends questions without answers, Redis stores the correct option, and the server validates. With full LaTeX math rendering.
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.
Building a Programming Language From Abidjan, Cote d'Ivoire
How Juste A. GNIMAVO built the FLIN programming language from Abidjan with AI CTO Claude and a $200/month budget.
Session 1: Project Setup and 42 Keywords
Session 1 of building FLIN: project setup, 42 keywords, 60+ token types, and the first lines of a language compiler.
Building a Lexer From Scratch in Rust
How we built FLIN's lexer in Rust: character stream to tokens, keyword recognition, and view mode scanning.
Pratt Parsing: How FLIN Reads Your Code
Pratt parsing in FLIN: how we implemented operator precedence, expression parsing, and control flow in Rust.
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.