Building

One person, a lot of agents, and a company on its second act.

Most of what I make is Groupthink. I started the company in 2021, shipped the first version of it in February 2023, and since May 2026 I have built the whole thing by myself, with AI doing the work a team of engineers used to do. Here is the story, with the numbers.

What Groupthink is

A relationship intelligence platform. It makes the dynamic between you and another person legible enough to act on, so your next meeting with someone is better than your last.

The unit is the relationship

Not the meeting and not the task. A relationship is a system that exists in the space between two people, and inside it the load-bearing points are the commitments you make out loud. Those are the checks we write with our mouths that our workload cannot cash.

The record is yours

This software has always been sold to companies, to manage their people. Groupthink inverts that. You are a node across many overlapping and temporary organizations, and the record of your side of them should survive changing jobs, tools, and AI vendors.

It compounds on its own

Every meeting, every paste, every detected name deepens what the system knows, whether or not you remember to file anything. A notetaker's summary is identical on meeting one and meeting fifty. This one gets better every day you do nothing.

What it is not: a meeting notetaker. Meet, Teams, and Zoom all transcribe and summarize for free. That was the whole problem, and it is where this story starts.

The arc

Five years, one category collapse, one team reduction, and a rebuild that worked. The unflattering parts are in here too, because without them the rest does not mean anything.

  1. 2021

    First Party Labs

    The company is incorporated as First Party Labs. Groupthink's first line of code is still two years away.

  2. February 2023

    Groupthink starts

    First commits land in the API and web repos on February 2nd. A tool for running better meetings: agendas, notes, the things a team needs to not waste an hour.

  3. 2024

    The category commoditizes

    Google Meet, Teams, and Zoom all ship native transcription and summaries, free, with no bot to add. The most common objection from new signups becomes the one we could not answer: why would I use this instead of what is already in my meeting tool?

  4. February 2025

    Peak team output

    287 merged pull requests in a month, from five people. It stood as the record for fifteen months.

  5. August 2025

    Three engineers cut

    Burn goes from $104K a month to about $70K, then $38K. Output goes with it. This is the part of the story that is not a growth chart.

  6. December 2025

    The trough

    17 merged PRs that month, then 15 in January. Two people, one of them part-time and reviewing only. The cost per shipped PR was worse than it had ever been with a full team.

  7. February 2026

    The rebuild starts

    Claude Code becomes the engineering team. 98 PRs in February, 113 in March, 127 in April. Slower than the team era, and improving every month.

  8. March 2026

    The repositioning

    Groupthink stops being a meeting notetaker and becomes a relationship intelligence platform. Meetings are inputs. What you know about a person after twenty of them is the output.

  9. May 2026

    Solo

    The last reviewer comes off. 424 merged PRs that month, past the old team record, at $71 per PR against $430 eleven months earlier.

  10. June 2026

    604 merged PRs

    More than double the best month the team ever had. The binding constraint stops being engineering throughput and becomes deciding what is worth building.

  11. Now

    The coach

    The product surface is an advisor that reads your record and tells you where a relationship actually is, and what the next move toward what you want from it looks like.

The numbers

What one person and a fleet of agents actually ships

Every figure below is a merged pull request count from GitHub or a line from the company's own books. Nothing is estimated, and the months that look bad are in the chart at the same scale as the months that look good.

604

merged PRs

June 2026, the best month in the company's history

The previous record was 287, in February 2025, with five people.

$50

per merged PR

All-in company cost that month

It was $430 per PR in June 2025, running a team of five on $104K a month.

$200

per month

What the engineering labor costs

A flat Claude plan. The same usage at list API prices would have run about $5,200 in June.

2,056

merged PRs

So far in 2026, through August 14

Across the API, web app, desktop app, iOS app, and marketing site.

Merged pull requests by month

Five people The reduction Solo, with agents
168
47
153
287
187
262
186
242
138
99
66
66
34
17
15
98
113
127
424
604
413
264
Nov 2024
Dec
Jan 2025
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan 2026
Feb
Mar
Apr
May
Jun
Jul
Aug

Engineering repositories only, so documentation and marketing work is excluded. August 2026 is partial, through the 14th. The dip in the middle is what it cost to lose a team, and the recovery on the right took four months of learning how to direct agents well.

How the work actually happens

People assume the interesting part is the model. It is not. The interesting part is the scaffolding around it, which took about six months to get right and is still changing every week.

The whole company is markdown in git

Strategy, decision log, runbooks, meeting notes, the operating principles, the relationship record. Not because it is tidy, but because it is what an agent can read. A page of English is a job description.

Work is issues under milestones that span every repo

A milestone exists in all five repos at once: product, API, web, website, marketing. It is the single answer to what ships, when, and what goes out with it.

Agents run in parallel, in isolated worktrees

Several at a time, each in its own git worktree so they cannot collide, each claiming its issue first so two never build the same thing. That collision cost a duplicated feature once, which is why the claim step exists.

The code review is also AI

Every PR gets reviewed before it merges. A human reviewer was the last role to go, in May 2026. The review is the final gate, not a pre-flight check.

Nothing is done until it is checked in production

Merged is not done. Deployed is not done. Done is the post-deployment checklist actually run against production, with the results written down. CI cannot exercise production, so a checklist that is never executed is theater.

The workflow runs ahead of the product on purpose

The hand-built version will always be ahead of what ships. That is not a gap to close, it is the roadmap arriving early. What works here gets built for people who will never open a terminal.

On the bench right now

Updated August 14, 2026

Commitment capture

Catching what was actually promised out loud, in the room, and holding it somewhere you will see it.

Text-message ingestion

Your real CRM is your calendar and your texts. Email landed first. This is the next signal.

The Connector

One-click OAuth so your other agents can read your record. The point of owning it is being able to hand it back to yourself.

Desktop recording reliability

Capture that works without a bot joining the call, on a machine you control.

GitHub, both directions

The work itself is context about the relationship. Connect to it rather than rebuild it.

Refining Today

The one screen that has to be worth opening every morning.

The honest part

None of this settles the question

A throughput chart is not product-market fit. I can ship more in a month than a funded team of five could, and I still spend most of my thinking time on whether the thing I am shipping is wanted. In July I wrote this down while sitting on a balcony in Rome, and it is still where I am:

Paying customers, low churn, low growth, low burn, and I am having a lot of fun figuring out how to build and launch major features completely solo with the help of AI. The only problem is, it is lonely and I am not sure I am making something people want.

The constraint stopped being engineering a while ago. It is deciding what deserves to exist, which no agent has done for me yet.

Read the whole post →

Also going on

Coaching

One-on-one with founders, executives, and operators, on building companies and on the career questions underneath that.

How I coach →

Writing

Twenty years of it, from the Mattermark era through now. All of it lives here rather than on a platform that can change its mind.

Read the archive →

Cooking

A whole-food, plant-based kitchen run to restaurant standards, at 5,280 feet, with the same systems thinking pointed at dinner.

See the kitchen →