Lab notes.

One mechanism a day, written the day it bit us. Shorter and rougher than the essays — published while the bruise is fresh.

These are the daily tier of our research: small, honest write-ups of what running a company on an AI operating system actually breaks and teaches. Each one is a single generalizable mechanism, not a diary entry.

08.02The error message is a witness, not a judgeA 404 told us the database wasn't shared. The lookup had failed — but the explanation was wrong, and believing it would have silenced an ingest forever.
07.30Funny is a skeleton, not a garnishSprinkling jokes on a serious script fails. Extracting the structure of material we actually love, and pouring the facts into it, worked on the first read.
07.29The form decided before we didAn internal priority decision sat unratified for a month — then an outside form with one mandatory field made it for us, on the record.
07.28Grep your own slidesA pitch deck is a stack of claims wearing nice typography. Our brain grepped the codebase for every noun on one slide — and an opinion became a finding.
07.27The premise of a question is a claim“Should I open a PR?” reads as humility. It smuggles in an assertion — one doesn't exist — and nobody audits the premise of a question.
07.26A name that needs a footnote is a bug“The room, the person, you” read cleanly on the page — then fell apart the first time it was said aloud. Name layers by the question they answer.
07.25A landing page is a list of claimsWe shipped an argument page four times in a day — falsified, recency-audited, citation-verified. Persuasive register doesn't exempt a page from epistemic discipline.
07.24When the evidence itself is cachedWe chased a bug that didn't exist and nearly shipped a redesign that didn't exist either — both times judging evidence that wasn't the artifact we shipped.
07.23Writing it down is not decidingEvery fact in the record was true, and the record was still wrong: a well-argued candidate looks identical to a decision on the page.
07.22You can't accelerate a track recordCapability responds to effort. A verifiable record accrues at exactly one day per day — and only counts from the day you publish it.
07.21A second conversation is not a second opinionA returning enthusiast doubles your notes and moves your evidence count by zero. Count distinct people, not conversations.
07.20Not an information supermarketThe most useful thing we did to the product this week was delete four features nobody had built yet. Breadth needs a prosecutor, not just a sponsor.
07.19Winning on average, benched for varianceA model beat the baseline on pooled metrics and still got zero production weight. A promotion gate reads the distribution, not the mean.
07.18Cite the artifact, not the narratorAn agent pasted a link to a pull request it had computed, not observed. Before you state that something exists, read it.
07.17Cheaper isn't isolatedTiering bulk work to a cheaper model cut our burn and changed nothing about reliability: the cheaper model drinks from the same pool.
07.16Done isn't deployedA background agent that was never installed produces no errors — it produces nothing, which reads identically to “nothing went wrong.”
07.15Don't let the medic share a bloodstream with the patientOur self-healing agent needed model capacity to think — and was dispatched exactly when the run had exhausted it. The doctor died of the disease.
07.14Don't ask the agent to grade itself — run a competitionYou don't make an agent trustworthy by making it more self-aware. You make it trustworthy by putting it in a contest it can't referee.

One note a day, while we learn.

Get pinged when they land

or write to hello@rsrvlabs.com