Projects

Any recipe is now a search away, and an AI will write you a new one in seconds. What a home kitchen still lacks is a companion: something that knows what your family likes, gets you through the cook with wet hands, and remembers how you made it last time. Most cooking apps answer with more scrolling, more pop-ups, and more screens to manage.

Sous is my attempt at the opposite: the ultimate home cook companion, and a calm one.

The prototype on our counter

The prototype is a working app running on a Pixel Tablet sitting on our kitchen counter.

This project is testing out a light non-consensus thesis I have: that in a multi-agent future, we'll all want an agent dedicated 100% to understanding 'us' and injecting that into every workflow with other agents.

Other agents will specialize in tasks, verticals, projects, types of work, etc. based on their harness and training. And they'll have access to our preferences, memory, data, etc. in many cases. But the thing that differentiates 'me' from anyone else, more than anything else, isn't actually captured well in those discrete files -- it's the taste, judgement, patterns and nuanced day to day things that can only be inferred from a large amount of experience and is best captured in weights, not in files.

This project experiments on that thesis that taste should live in one deep node that other agents consult, the way you'd ask the colleague whose judgment you trust rather than hand everyone a style guide. It started as a note to myself: "make a model that is purely embodying my taste - find right tech or way to encode this (maybe not text) and store it. Use as a way to learn a level deeper. And make a partner everywhere."

I didn't start with a model right off the bat. For now it's a thin agent storing a record of my judgments: what I approved, what I changed, what I rejected, and why. It manages, updates, prunes and accesses that record and interfaces with other agents in my workflows to see if having that dedicated expertise improves outcomes and alignment to 'my taste.'

Most tools today put inputs first — chats, docs, calls — and treat shared knowledge as the residue that's left over. Abuzz inverts that. The walk-in surface is what we're making, organized as a bento of live outputs. Conversations, drafts, huddles, and agent contributions feed those artifacts and are surfaced as their current best state. The one-liner I keep coming back to: _knowledge is the home; the room is where it gets made._

The prototype is a single self-contained HTML file (no build, no deps — open it and it runs) covering three surfaces: Home (the output-first walk-in), a Space called Memory design (a bound unit of work where a huddle is live, an artifact is being built, and three teammates plus a Cartographer agent are in the room), and Ask (⌘K synthesizes answers with citations to the primary source — voice call, doc, canvas note — not links). Agents (Cartographer, Researcher, Scribe) live inline with humans, distinct only by dashed circles and mono uppercase labels. No "✨ Ask AI" buttons, no segregated AI zone — they're teammates, not features.

The design tenets matter more than the surfaces. Calm over dashboard — aim for Tuesday morning office arrival, not command center; desaturate and remove motion before adding. Output-first — inputs are modalities, not the center of any view. Presence is grouped, not floating — compact avatar stacks, no Zoom-style bubble swarm. Live modalities are first-class but ephemeral — they can be opened, joined, archived, retrieved, and they sit beside the artifact layer rather than in front of it. Most "I should add X" instincts have already been considered and rejected; the prototype is supposed to feel quiet.

The interesting part isn't the mockup — it's the bet underneath. Five-to-fifteen-person remote teams already have voice, video, docs, chat, and a growing pile of AI features bolted onto each. Abuzz is testing whether you can collapse those into one surface where the agents are teammates and the artifact is the room. If it works, the daily experience of small remote teams becomes less bureaucratic, more alive, and more like sharing an office — which is the actual job of a workplace, and the thing we lost when we went remote.

A Gemini Deep Research run cataloging 33 named figures across AI labs, academia, investors, skeptics, and policymakers — each tagged with their public AGI timeline, their stance on takeoff speed, and the financial exposure that shapes (or doesn't shape) their position. The point isn't to call anyone dishonest; it's to make the incentive structure visible so the substantive arguments can be read against the right backdrop.

The output has five sections:

Embedded below.

A Claude Code skill that connects to personal finance tools via MCP and adds what they can't do on their own: forward-looking projections, scenario modeling, financial independence tracking, and investment thesis stress-testing. Five modes — financial picture, projection ("what if we buy a house?"), thesis workshop (five analyst personas debate an investment idea), meeting prep, and tax planning.

The centerpiece is an auto-generated HTML dashboard with Chart.js visualizations. Key metrics up top, then a scenario explorer where you toggle between income, business growth, and market return assumptions and watch 10-year net worth trajectories shift in real time. FI progress with Coast FI milestones, forward-looking goal feasibility, and portfolio allocation tracking. A collapsible "Go deeper" section holds portfolio perspectives (five AI personas synthesize investment recommendations from actual data) and an interactive scenario builder.

The thesis workshop mode is the most unusual piece — five personas (Macro Strategist, Market Mechanic, Fundamental Analyst, Wealth Steward, Challenger) each analyze an investment thesis in their own voice, then synthesize where they agree and disagree. The Challenger persona evolved from a generic Contrarian — instead of reflexive disagreement, it proposes falsification criteria for the thesis and names specific conditions that would prove you wrong.

What we learned building it

Pure research phase. Built a backtesting engine, fetched 18 months of multi-venue funding rate data, and ran an autonomous "Ralph Loop" that iterated through 12 rounds of strategy discovery without human intervention. Tested 100+ strategy variants across different entry timing, venue selection, concentration, and exit approaches. Key finding: single-venue concentration dominated, and no amount of multi-venue sophistication beat simplicity. Five critical backtester bugs found via adversarial verification.

Skills are reusable instruction sets that tell Claude how to handle specific tasks. Instead of re-explaining what you need every session, you invoke a skill and it just works. Built these from my own daily workflows running a startup, then packaged them for other operators. The coaching skill alone replaced hours of "let me think through this" solo time.

A Gemini Deep Research run that built a longitudinal view of corporate ethics failures across big tech — antitrust, privacy, labor, safety, content, and AI-specific violations from 2000 through 2024. Each incident was scored by impact (severity × scope × duration × precedent) and plotted on a per-company timeline, with the bubble size scaled to the impact score.

The headline pattern: a small number of companies carry most of the cumulative impact, and the distribution is not what most narratives assume.

The Meta-vs-rest gap is striking. So is OpenAI's score for a company that didn't exist meaningfully until 2022 — it took less than three years to accumulate impact comparable to companies with 20+ year histories.

Embedded below.

The essay that came out of building Sugarface. The core argument: building with AI is easy now, but the real unlock is building systems that improve themselves. Two specific tactics made the difference — a /handoff command that institutionalizes session wrap-up, and an enforced project diary that captures decisions and learnings. Between the two, agents started working, learning, and improving together over time.

A product suite for building math fluency and number sense at Zearn, one of the most widely-used math platforms in US elementary schools. As PM, I led the creation of Number Gym — a set of interactive practice experiences designed around the new Common Core math standards.

The key insight was mapping the standards into a progression that made mathematical sense, not just a checklist. We created proprietary IP about how the standards built on each other — which concepts were prerequisites for which, where the common misconceptions lived, and how to sequence practice so students built genuine number sense rather than just memorizing procedures.

Number Gym was the first product to fully implement the new Common Core standards for math fluency. It reached millions of students across the US through Zearn's school partnerships, making it one of the highest-impact products I've worked on by sheer reach.

An iOS game designed to make multiplication practice feel like play. Kids popped bubbles with numbers to solve multiplication problems, with adaptive difficulty that met each student where they were. Built as PM at a small NYC edtech startup focused on elementary math.

The game used spaced repetition principles — facts a student struggled with appeared more frequently — wrapped in a game mechanic that felt rewarding rather than remedial. We tested with classrooms in NYC public schools.