Jack Puccini
Good at starting things, working on the finishing part.
AI · Product & zero-to-one · Reasoning & decisions
Recent Writing
- Jul 6, 2026 · 6 min readAI
What Won't Change
Building for the present versus building on invariants - the constraints on the human side of the interface that will still be true in ten years.
- Jun 23, 2026 · 6 min readAI
My Current 'AI Stack' for 'Productivity'
The tools I actually use day to day - dictation, screenshots, coding agents, and a writing pipeline - and an honest take on whether any of it makes me faster.
- Mar 17, 2026 · 4 min readAI
Managing Agents, Not Programming Them
Reflections on designing agent systems by managing intelligent actors rather than prescribing rigid workflows.
- Mar 4, 2025 · 10 min readSoftware
Mutability and Immutability in Python
Understanding mutability and immutability in Python
- Dec 30, 2024 · 3 min readOther
Jane Street Puzzle - December 2024
My solution to Jane's street December puzzle, 'Games Night'
About
I get distracted by how things work. I'm wrong a lot, and mostly just try to be wrong faster than last time.
Everything has structure. Finding it lets you see the same thing through different lenses — a system, a product, a market, a decision — and I try not to respect the borders between them.
Recent Thoughts
Notes to myself, made public.
- Aug 26, 2026
At the moment I'm extremely bullish on two broad AI/tech trends going forward:
1 - Agents dynamically acquiring capabilities ‘at runtime’. Harnesses becoming simpler over time, and agents leveraging marketplaces (both free plugins and x402/MPP etc driven) to get what they need. Competitive dynamics of said marketplaces will also quickly make this approach blow past ‘all in one’ solutions (codex, Claude code etc..). There are a bunch of problems to be solved here - discoverability, reliability, reputation, security etc
2 - Huge amounts of opportunities and developments in UI/UX for software of the future as the way people interact with technology completely changes. Having now written that sentence, it sounds extremely generic even though I have very specific ideas in mind. In short, AI doesn’t have a taste problem - it's mainly a UI/UX issue. Once ultra fast + intelligent models become mainstream (which - looking at Cerebras etc - they soon will), totally different surfaces for facilitating iterative, taste-dependent work will explode. It's less about making AI have good defaults, and more about AI facilitating the intent -> implement -> judge -> iterate loop in the best/fastest way possible. - Jul 24, 2026
EZ
- Jul 24, 2026
Let's do somethinggggggggg