We build products with agents.
These are the notes.
A studio running a portfolio of bets, written up from the engineering side by Shaun Robinson: what changed in the economics, what breaks at scale, and what we still get wrong.
The coach shipped in four days
Eloist had a retention problem: people loved the analysis and did not come back. Four days later a made-up coach was mailing them videos about their own games. The speed came from a shape, and the shape is transferable.
Read →- 0025 min
Rendered, never generated
Eloist now mails people a short video about their own chess games, narrated by a coach who does not exist. Four days from first commit to thirty-five inboxes. Here is how it works, and what it refuses to do.
agentsvideoverificationpipelines - 0037 min
One person, eight hands
Two years of git across 16 repos, 3,200 commits, one engineer. For 22 months the line is flat. Then, in six weeks, models co-author 2,344 commits and the question becomes what that number is actually counting.
agentsgitvelocitymeasurement - 0048 min
Intelligence at every layer
Five layers of a software company, what has become a check that fires, what is still a document, and what stays a person. Measured over six weeks in our own operating repo.
agentsoperationsorganisationcraft - 0057 min
Two years, one codebase, and the agent that grew inside it
A client's map app, read back from 384 commits. A team built it, one engineer kept it alive, and for the last eight months the commits carry a model's name. One timeline holds all three.
agentsgitclient-workcraft
0069 minTwo physics bugs the tests caught before a user did
jungl runs a year of sunlight through a model of your home. The sun part is exact, the room part is a model, and both were confidently wrong on day one. Here is what the tests assert, and why a deterministic core is what makes them possible.
testingsimulationphysicsjungl
0079 minA number is not a number
Nine wrong figures reached the founder in one day and not one query was broken. What was missing was never the arithmetic. It was source, as-of, population and grain, and now a checker refuses to hand back an integer without them.
metricsinstrumentationagentscraft
0089 minA critique loop that actually converges
Rulers certify an ad that is correct, honest, pixel-exact, and ugly. The fix is a panel of narrow critics that can veto, a score that weighs instead of counts, and a loop that returns its best round rather than its last.
agentsevalsimagescraft
0099 minSounds like AI, measured
"This copy sounds like AI" is unfixable as an opinion. Count the tells per hundred sentences against a human control and it becomes a threshold anyone can fail, and a gate that stops the next draft from drifting back.
copymeasurementagentscraft
0108 minSurfaces that regenerate need a memory
A daily card ranked over a stable corpus is a deterministic repeat. Four instances of that one defect turned up in a single day, and the fix was the same ledger four times.
productrankingretentionagents- 01111 min
The link was already used
A one-time sign-in link is a bearer token in a URL, travelling through machines whose job is to open URLs. Here is the exact mechanism, the traces, and why the numeric fallback dies with it.
authemailhttpverification - 0126 min
Capacity got cheap. Judgment did not.
Production now arrives on a subscription, and every other line of the stack prices itself daily. What is left to be scarce is knowing what to build.
economicsstrategyagents - 0136 min
Ads are a research instrument
A campaign can tell you which description of a problem strangers recognise as their own. That is a narrower answer than it looks, and worth paying for.
demandadsstrategy - 0146 min
The funnel is a build artifact now
A funnel change now ships through the same repository and deploy path as any product change. What did not get faster is finding out whether it worked, and that gap is where the discipline has to go.
funnelinstrumentationgrowth - 0156 min
Context is the bottleneck
Model capability keeps improving and tokens keep getting cheaper. What stays hard is telling an agent which of the things already in the repo is the one the team considers correct.
contextagentsarchitecture - 0166 min
The agent says it shipped. Prove it.
Every signal we call verification proves something narrower than its name. The discipline is knowing which rung you stopped on, and saying so.
verificationagentscraft - 0176 min
Testing a feature that answers differently every time
Property-based testing, metamorphic testing, fuzzing and statistical acceptance have asserted things other than equality for decades. What is new is applying them to the product surface, where the output under test is prose a customer reads.
evalstestingquality - 0186 min
The half of Brooks's law that survives agents
Running many agents in parallel is the real unlock for a small team; what limits it is contention over shared state, which draws the same curve as Brooks's law by an entirely different mechanism.
concurrencycoordinationagents