A Summer of Sharpening

On August 29 the entire platform, 25 repositories, produced ten commits. In the June numbers post a day like that would have read as an outage: that workflow was merging 29 pull requests a day and I published the throughput as the story. But August 29 was one of the most productive days of the year. It produced two orchestrated research batteries, nine briefs and reports with 163 evidence captures behind them, and a policy research report with a claim ledger and a build loop that regenerated the document seven times in twenty minutes until its own verification passed. The work did not slow down this summer. It changed shape, away from output and into sharpening, and this post is about where the effort went.

The numbers are still here, because this is a numbers series and the series does not skip a down month. Since June 10: 3,829 commits and 2,084 merged pull requests across the fleet, with merges holding at the June baseline through July before easing in August; 492 new specification documents, peaking in July; and, rising through all of it, more than a hundred authored research documents that never touch git at all. Read as one metric, the summer decelerated. Read as a portfolio, the effort moved down the stack, out of typing and into four systems that make the typing count for more.

Memory that outlives the session#

The first investment extends the institutional memory system I wrote about in July, and it earned its keep by surviving its worst failure. Every working session is distilled overnight into structured facts, tens of thousands by now: decisions, open loops, hard-won gotchas, with redaction applied at ingest so the store is safe to back up. This summer it grew self-healing lanes: contradiction detection, staleness review, and loop closure, each gated by an evaluation suite that has to pass before a change to the pipeline ships.

The impact is quiet and constant. Sessions start already knowing what June decided. The standing rule is now that no session may declare "there is no record of that" without asking the memory system first, and the recall log shows it settling questions that would otherwise have been re-litigated from scratch. For a team of one, that is the difference between a career of experience and a goldfish with good tooling.

A screen that refuses to flatter me#

The second investment is the statistical screen that sits between market data and anything I might act on: an append-only ledger of every signal test, false-discovery-rate control across the whole family of tests, and a contamination review that killed an entire pool of early candidates rather than let them sneak through. Its confirmed-discovery count, after a summer of hardening, is zero. That number is the system working. I wrote in June that the most dangerous result I produce is the one I was hoping for; this is that sentence built into infrastructure, hobbyist research run for the engineering, and the engineering's first product is an honest null.

This summer the screen's ledger was compacted into immutable segments, its backup gap closed, and its research strategist re-enabled against a 48,000-cell test backlog it will drain over weeks without me touching it. Nothing it finds gets believed by default. That is the point.

A floor under the data#

Third, the data itself. Any long backtest quietly assumes you can see the companies that died, and most free data cannot. So the summer's data-mining push went at that assumption directly: regulatory filings as primary sources, company fundamentals reconstructed from EDGAR back to 2009, a delisting log assembled from Form 25 filings back to 2006, index membership history to define the universe honestly, 221 captured filings retained as evidence behind the synthesis. The result is a measured boundary instead of a vibe: I now know exactly which claims the free primary record can support, and the one gap that remains, prices for the dead names themselves, is named in the synthesis rather than papered over. The posture is measurement first; nothing gets certified for use until the floor holds.

A product built on paper first#

The fourth investment produced no code at all. A new product spent the summer as a stack of numbered rulings: competitive landscape, packaging and signing, pricing, trust and autonomy boundaries, release mechanics, each question argued to a decision before implementation gets to exist. This is the spec-first method from the April playbook applied at product scale, with the judgment front-loaded where changing your mind is cheap. When the building starts, it will start the way the best weeks of June did: from a brief that already removed the need to guess.

Refining the machine that does the work#

Underneath all four runs the same discipline, applied to the workflow itself. The operational lessons file is now 26 numbered entries, and the standing rule for each is that prose is advice; only a check is a guarantee. Lessons get promoted into enforced gates: pre-push validation that mirrors CI locally, guards that plant a deliberate failure to prove the watchdog still barks, a weekly pass that sweeps the week's corrections back into the files that caused them. The payoff showed up at the end of August, when a three-day integration wave merged 59 pull requests across 12 repositories with the gates doing the reviewing that used to be my evening. Refinement is not a pause in the work. It is the work that makes the next wave cheap.

Where that leaves it#

The series now has three points, and they measure different questions. April asked whether the workflow could ship at all. June asked how fast. This summer's answer is about what the speed runs on: a memory that compounds, a screen that cannot be flattered, a data floor that holds weight, a product argued out before it is built, and a machine that turns its own mistakes into gates. The fall gets to spend all of it. Productivity used to look like shipping. This summer it looked like sharpening, and the difference only shows up in next month's numbers.

---

Previous in the series:

• Ten days of June: the SDD velocity numbers, seven weeks in
• One week of SDD in production: the numbers
• SDD isn't about managing AI agents, it's about managing context