Version 1.1

Retrieval Augmented Tumaini

Vectors from my life. They have direction, velocity, and are imbued with meaning.

2026.05.28

The Agent-Ready Web: Building an API of Self

For two decades, the web has been optimized for human perception—layout stability, visual polish, and interactive refinement. In doing so, it has become increasingly opaque to the systems that will define the next layer of information consumption: autonomous agents. If a site is not machine-readable, it becomes a context void. Content is not simply harder to access—it becomes structurally unreachable, buried beneath rendering layers, JavaScript execution paths, and middleware abstractions that obscure semantic signal.

Read Entry

2026.05.26

Speed, Constraints, and Absolute Efficiency: Wiring Linear to the AI Council

For a long time, the tech industry operated under a shared delusion: if we just added enough custom fields, mandatory dropdowns, and complex status workflows to a Jira board, we would somehow ship better software. We built a bloated, parallel simulation of our work, endlessly debating "story points" in what amounted to Agile Theater. The migration from legacy behemoths like Jira to Linear isn’t just a UI trend. It is a return to pragmatism. Linear assumes you are an adult who wants to ship code, not a cog in a micromanaged assembly line. For an autonomous, AI-driven workflow, Linear is the only tool that actually makes sense. Here is why the modern engine room runs on it, and how it physically controls my AI Council.

Read Entry

2026.05.25

Ideating in the Engine Room: Why Product Strategy Requires Architectural Friction

Most product management happens in a vacuum. We sit in sterile environments—endless Miro boards, perfectly formatted PRDs in Notion, and abstract roadmap spreadsheets. We draw a little rectangle on a canvas, label it "User Dashboard," and hand it off to the team. When you ideate without feeling the architectural friction, you aren't doing strategy. You are writing science fiction. The classic product failure mode is encapsulated in a single, dangerous phrase: "How hard can it be?" It is incredibly easy to ask for a "simple" feature when you don't have to wire it up. But the moment you drop the whiteboard and step into the engine room, the illusion shatters.

Read Entry

2026.05.22

The Tri-Brain Architecture: Outsourcing My Memory

When building a modern digital product—juggling the stateful complexities of Next.js, schema definitions in Payload CMS, and database migrations in Supabase—the cognitive load is crushing. The natural instinct is to dump all this context into one massive LLM chat window and expect the machine to sort it out. But treating an LLM like an omniscient oracle is a rookie mistake.

Read Entry

2026.05.21

The Auth Wall: Why AI Struggles with Stateful Systems

If you watch a demo for an AI coding environment like Cursor, the pitch is always the same: type a prompt, watch the code write itself, and deploy. A straight, frictionless line from idea to production. But actually pushing this Next.js and Payload CMS site live over the last week told a different story. The reality of building with autonomous tools isn't a straight line. It’s a series of messy, overlapping loops—and nowhere did that friction hit harder than when I tried to stand up Authentication.

Read Entry

2026.05.19

Hello World!

For years, my professional life has centered on guiding digital products, scaling service design, and leading engineering teams to build clean, intentional software. But a corporate roadmap or a traditional CV only tells half the story. To truly understand how modern digital design is changing, you have to get your hands dirty in the machinery. This website isn't a static digital business card. It’s a living laboratory. I wanted a self-hosted, independent space to experiment with the cutting edge of modern software execution—specifically, the massive paradigm shift happening in autonomous engineering workflows.

Read Entry