Work

Mission Control

Software Engineer · 2026–present · usemissioncontrol.com

Mission Control captures what expert workers know and never wrote down, and turns it into AI agents that run inside the customer's own environment. Nothing comes back to Mission Control. The customers sit in defense, aerospace, energy, manufacturing, and similar industries, so the constraints are hard: Microsoft identity, mTLS, customer-data privacy, protected execution, licensing. I own product and technical systems across those deployments. Most of the job is translation: ambiguous failures into explicit contracts, scoped authority, acceptance evidence, and rollout decisions.

It is the same bet as "Taste" is Not Ineffable: what an expert knows can be written down, and once it is written down, a machine can apply it.

engOS

I designed and drove engOS, an AI-native engineering control plane. It binds human intent and authority to implementation candidates, audit findings, evidence, repairs, and release state, with durable recovery and fail-closed publication. Process is proportional to risk, and requirements, accepted risk, evidence, ownership, and approval are visible before work ships. It reached 97% workflow adoption. Measured rework fell from 12.4% to 5.5%.

The certificate that would not work

A high-security customer had a browser-certificate failure with no clean reproduction. I turned it into a reproducible mTLS lab, traced the root cause across worker processes, and drove one-shot secret handoff plus concurrent identity isolation. I proved the underlying Chromium path locally and kept the customer's final acceptance explicit rather than assumed.

Fast Start

I helped build Fast Start, which lets a less-technical user describe a workflow in plain English and has AI construct the underlying automation. Less distance between what a customer means and a system that works.

Across all of it, I direct AI agents through implementation and adversarial review, and I own requirements, architecture, verification, and acceptance.

FollowUpEasy

Founder · 2026–present · followupeasy.com

Most professional relationships go quiet by accident. FollowUpEasy connects to Gmail, reads the whole mailbox, judges every relationship, and maps the ones worth keeping: where each one stands, what is owed, whose window is open. Then it drafts the follow-up in your voice. You approve every message. It never sends on its own.

I built and operate all of it: discovery, product design, architecture, Gmail OAuth, encrypted credentials, PostgreSQL, model inference, grounding, background workers, billing, analytics, deployment, debugging, human approval, and production operations.

The hard part is not the model. It is deciding what the product is allowed to do. It has explicit boundaries around unsupported output, sensitive relationships, duplicate work, spend, and sending authority, so it stays useful without silently taking a consequential action. One rule I keep coming back to: when the system cannot judge a relationship, it must fail open to "we don't know," never closed to "not a real relationship." The second kind of failure deletes real people from the map.

The thinking behind it is in While You Were Working, Half Your Network Disappeared.

Total Recall

Creator · 2026 · github.com/davegoldblatt/total-recall

Claude Code's default context management was broken for long projects, so I built a persistent memory system for it. The design is a write-gated, tiered architecture with correction propagation: a fact has to earn its place, a correction propagates everywhere the old claim lived, and stale or unauditable context gets limited instead of accumulating.

I built the whole thing with Claude Code in three hours and launched it on Hacker News. Then I managed the product cycle in public: triaged community feedback, rewrote the docs based on user complaints, answered architecture questions, and opened design issues for the most requested features. 200+ GitHub stars.

Cookie Calm

Creator · 2026 · Chrome Web Store · GitHub

I built Cookie Calm to take a small, repetitive annoyance out of browsing. The Chrome extension automatically rejects optional cookies and dismisses supported promotional popups, including newsletter signups, discount offers, and chat greetings.

I built on Consent-O-Matic's open-source rules and added guarded actions, popup dismissal, and per-site controls. Unknown consent forms stay visible; accepting cookies is an explicit opt-in fallback. Everything runs locally, with no account, telemetry, or remote AI. Open source under the MIT license.

Facebook

Product Operations Specialist, Search · 2007–2017

Employee #180. Ten years across product operations, from startup chaos through IPO to 2B daily queries.

I spent the bulk of my Facebook career on Search, including the Graph Search era, what Mark called Facebook's "Third Pillar," announced eight months after a rough IPO as proof the company could build beyond News Feed. It was one of the most technically ambitious projects the young company had undertaken: a privacy-aware index, NLP engine, and personalized search across 240 billion photos and 1 trillion connections, built by a team of 50+ led by the creator of Google Maps.

Underneath the launches I built and ran the readiness system: test plans, cross-office coordination, outsourced QA, and bug triage across 100+ engineers. Launches went out across Product, Engineering, Design, Legal, Privacy, Safety, PR, and Operations. That was the infrastructure that kept releases from blowing up.

The product had a fundamental usability problem the team was too close to see. The design concept was a "magical page title": no white search box, no search icon, just a clean blue line across the top of every page. It was an intentional, ambitious design thesis. But users couldn't find the search bar. We were flooded with bug reports: "my search bar is gone." I kept pushing eng, design, and product: just make it white. There was real resistance because the blue bar was the concept. We tested it. White outperformed the next best option by more than 2x.

That experience taught me something I've carried ever since: when the people building the thing can't see what's obvious to the people using it, someone has to be willing to say the simple, boring, correct thing out loud.

Wavechat

Founder · 2018–2020

After a decade inside a company that had everything, I went and built something with none of it: an audio-first social product, built and shipped end to end. I owned customer discovery, product decisions, technical architecture, delivery, hiring, fundraising, and iteration. It didn't work, but the experience fundamentally changed how I operate. I learned what it feels like to have no leverage and no safety net. It gave me a sharper lens on what founders actually need versus what they say they need, a distinction that defined how I invested for the next four years.

Vibe Capital

General Partner · 2021–2025

I started a deep tech and AI seed fund 18 months before ChatGPT launched, when most LPs weren't interested in the thesis: back founders who manipulate matter, bend energy, or rewrite biology. 40+ investments across AI infrastructure, semiconductors, robotics, biotech, space, and energy. Co-investors on various deals include Sam Altman, Alex Wang, and Lightspeed.

The part I'd do again was the work with founders through high-stakes decisions: operational focus, capitalization structure, when to hold and when to move. The kind of calls where five investors give five different answers and only one is right.

One example. Shapes: a 2021 investment in AI companions, over a year before ChatGPT. Cold inbound from the founders, stayed in contact, invested when AI friends sounded like a toy. Lightspeed led the seed round.

The fund wound down in 2025. I still support the portfolio.