Posts

OpenSpec Bringing Specification-Driven Development to a Research Prototype

Research prototypes have a particular failure mode - they work, and then they grow. What starts as a script to test an idea becomes a pipeline. The pipeline gains a frontend. The frontend gets tabs. New retrieval modes are added. A knowledge graph appears. An agent memory layer. Six months later, the codebase is genuinely complex — but the only documentation is the code itself, scattered comments, and whoever wrote it remembers most of what it does.This is exactly where the RAG assistant for historical research in the Indian Ocean found itself. Eight distinct subsystems — ingestion, chunking, embedding, retrieval, generation, knowledge graph, agent memory, evaluation — each with non-obvious constraints, silent failure modes and subtle interactions. No single file explained how they fit together or *why* certain decisions were made.

featured

SDD - The Spec as a New Social Contract

Spec-Driven Development — SDD — is, at its best, a proposed answer to this perennial failure of translation. But it is arriving in 2026 not as a project management reform but as an engineering methodology, carried into organisations on the back of agentic AI tools. And that origin shapes everything about its promise and its limits.

Before the Graph On the Necessity of Ontology Design

I have been dwelling into GraphRAG for a few weeks now, vibe coding in my spare time. I started vibe coding GRAPHOS — a Graph-based Research Assistant for Historical and Ontological Sources (I recently changed the project name to reflect the importance of ontologies in this piece of work) — I assumed the hard problem would be the ingestion pipeline. Parse the documents. Extract the entities. Build the graph. Let the system answer questions.I was wrong about where the hard problem was.

From Feature Requests to Customer Jobs - Basecamp's Root Cause Analysis Approach to Product Strategy

Product teams face a universal challenge, customers constantly request features, but building everything would create bloated, unfocused products. The traditional approach—either ignoring requests entirely or meticulously tracking them in spreadsheets—fails to extract the strategic intelligence buried within these requests. Basecamp's evolved methodology demonstrates how Jobs-to-be-Done interviewing transforms raw feature requests into customer-centric product strategy.

featured

Gherkin Syntax - The Rosetta Stone of Cross-Functional Alignment

In 1799, French soldiers discovered a stone tablet in Egypt that changed our understanding of ancient civilizations. The Rosetta Stone contained the same decree written in three different scripts—hieroglyphics, Demotic, and ancient Greek. Because scholars could read Greek, they could finally decode hieroglyphics.Your product team needs a Rosetta Stone.Not to decode ancient languages, but to translate between the four dialects we identified in Part 1 - customer outcomes, product capabilities, engineering logic, and business metrics. You need a syntax that all four groups can read, write, and understand without losing meaning in translation.That syntax already exists. You've probably seen it in your engineering team's test suites. It's called Gherkin.

Building an agentic RAG tool to support my hobby research into the history of the French Revolution in the Indian Ocean

Academic research generates an enormous volume of PDF documents—papers, theses, archival materials, and historical analyses. Across the years, I found myself interested into the history of French revolution in the Indian Ocean. This history and its impact spans over decades across multiple locations like the Mascarene Islands, India, and of course, France and the UK as well. Given the huge amount of information that my brain needs to process to get a good understanding of all the intricacies happening on at that time, I have decided to build a RAG pipeline powered by graph databases to help me out. This is perfect for a RAG system based on graph representation of entities. This experiment addresses that challenge head-on, building a Retrieval-Augmented Generation (RAG) system that transforms raw research PDFs into an intelligent, queryable knowledge base augmented with relationship understanding through graph technology.

Why Your Product Team Speaks a Different Language Than Your customers

Every product team has experienced this moment. You ship a feature you're certain customers need. The engineering was solid. The design was clean. The rollout was smooth. And then... crickets. Not because customers don't have the problem you're solving. They do. But because the way you understood their problem and the way they actually experience it exist in two completely different universes.

The Pragmatist Roots of Agile - John Dewey's Philosophy and Modern Software Development

The Pragmatist Roots of Agile - John Dewey's Philosophy and Modern Software Development. When the seventeen software developers gathered at the Snowbird ski resort in Utah in 2001 to draft the Agile Manifesto, they were articulating principles that would revolutionize how teams build software. What they may not have realized is that they were echoing ideas first developed nearly a century earlier by American philosopher and educator John Dewey. The parallels between Dewey's pragmatist philosophy and agile software development reveal a deeper truth - both represent responses to rigid, theoretical approaches that fail to account for the messy, adaptive nature of real-world problem-solving.

The Agent Memory Landscape - A PM Guide to Building Context-Aware AI Systems

AI agents, quite often, don’t remember. They are brilliant in the moment, terrible across moments. Every conversation is day one. Every interaction starts from zero ! That limitation—and the architectural challenge of solving it—has become close to fascination to me. LLMs and agents are nothing without memory and context. An agent that forgets is just an expensive API call. An agent that remembers becomes something closer to a very good friend or assistant ! The landscape of agent memory solutions has exploded in the past two years. For product managers building AI-native products, understanding this landscape isn't optional—it's foundational. Here's a map of the territory.

The Silent Kitchen - What Sébastien Bras Reminds Us About Building Products and Teams

We've all absorbed the mythology of the chaotic kitchen—the screaming, the clanging, the barely controlled chaos of a dinner rush. Gordon Ramsay has built an empire on it. "Yes, chef!" shouted at maximum volume. Pans slammed for emphasis. The kitchen as controlled explosion. The brigade system as military operation, with hierarchy enforced through decibels. This mythology is so pervasive that we accept it as the natural state of excellence under pressure. We assume that when stakes are high and standards are higher, chaos is not just inevitable but necessary—the very proof of seriousness, of commitment, of refusing to accept mediocrity.