Runbook

1. Daily brief

Two a day. AM is the full brief. PM catches up on what broke since.

Why two. A reader opens a trusted site in the morning, and around the middle of the day wonders what is new, because there always is something. A site that never moves past breakfast teaches them to check once and forget it. The afternoon brief is there to reward the second visit.

Which means the PM has one job it cannot fail at: being new. A reader who comes back at three and finds the morning's five stories restated stops coming back at three.

• Same-day repeats need the Update marker. A story from the AM brief may appear in the PM only if it has genuinely moved, and the item has to lead with **Update.** and say what changed. python3 tools/dedupe.py compares every item against the last two days of briefs and fails the run on an unmarked repeat.
• The PM may be short. Three items on a quiet afternoon is an honest answer. Padding is the failure, not brevity.
• The PM drops sections it has not earned. No Editorial: the day's argument was made in the morning.
• Aim for twenty in the afternoon too, and take fewer without apology when the afternoon did not produce twenty.
• Both halves carry the same byline. It is one person's day and the afternoon piece is their follow-up on it.
• The AM run owns the three libraries. The floors in catalog.py brief are per day, and the morning run is what clears them. The PM adds to them opportunistically.
• Sunday runs all three. The weekly is a retrospective on the week; the briefs are the news. A reader opening the site on Sunday morning wants what happened overnight, and giving them an essay about the last seven days instead is answering a different question. The weekly also reads the week's seven daily briefs as its input, so skipping Sunday morning would starve it of the last day.

Both are the same thing: a ranked list of the AI news worth surfacing, most important first.

Front matter

Every daily starts with this block. The site reads it for the byline.

---
author: vera
---

Author is set by weekday, per PERSONAS.md: Mon/Thu → vera, Tue/Fri → elias, Wed/Sat → nour.

Structure

A brief is a ranked list of news stories and nothing else. There is no ## The Lead and no ## The Signal. Those were section names invented to hold stories, and a reader does not need to be told that the first story is the lead story: it is at the top.

# Daily Brief, August 10th 2026

> One paragraph, the way you would tell a friend who is into AI what is going on if you
> ran into them and had a minute.

## The headline for the biggest story

Body. What happened, then what it means. [A](url)[B](url)

## The headline for the second story

Body. [B](url)

… twenty of them, then:

## Editorial
## Sources

• Twenty stories minimum, ranked, heaviest first, thinning as it goes down. Take thirty on a heavy day; the floor is a floor, not a target.
• The headline is the H2. The site turns every H2 that is not Editorial or Sources into a numbered story, builds the contents rail from them, and gives each one an anchor. Nobody numbers anything by hand: move a story up and the number follows.
• Body under the headline, no bold restatement of the headline to open it. The old format needed one because the item was a bullet; it is a heading now.
• The standfirst is a paragraph, not a slogan. It is the thing a reader gets if they read nothing else, so write it as speech rather than as a subtitle.
• Editorial, Prediction Watch and Sources keep their names and sit at the end, in that order. They are not stories, so the site does not number them.
• The evidence strip renders at the foot of the page, after Sources, built from the tier markers. Most readers want the news; the ones who want the sourcing profile want it after they have read it.
• If a story bears on an open call, say so in that story and name the call. A bare T4 auto-links to the prediction.

Prediction Watch

The section where the day's news meets our open calls. Write it for somebody who has never read the ledger. The old version opened entries with a raw 2026-08-06-T4 and the phrase "moved toward", which told a reader nothing about what was claimed, which way it went, or when anyone finds out.

Every entry is one bolded label, then the claim in plain words, then what today did to it, then when it settles:

**More likely now: nobody solves prompt injection (T4).** We said no architectural fix
would reach broad adoption by next August. Auto mode is a filtering layer, which is
precisely what that call says will not be enough. Settles August 6th 2027.

• The labels are a closed set, so a reader learns them once: More likely now, Less likely now, No change, Supporting evidence, New call, Settled: we were right, Settled: we were wrong.
• Name the claim, not the ID. The prediction's own title field is already written in plain English, so use it.
• Write (Prediction F4), not (F4). The whole phrase becomes the link, so a reader can see where it goes before clicking. A bare F4 mid-sentence in a story still links on its own; the section whose entire job is pointing at predictions should say so.
• Use the full id when a suffix is ambiguous: (Prediction 2026-08-11-F1). Each issue numbers its calls from T1, so F1 names two different predictions today. An ambiguous reference is left unlinked and the build prints which one, because a confidently wrong link is worse than no link.
• Say when it settles, in words: "Settles August 6th 2027", never 2027-08-06.
• End with what did not happen. "Nothing settled today" is a real line and most days it is the true one.
• The China/open-weights check goes here when there is something to say, and in the run reply either way.

Put the source on the item

Every item carries its own link. Write the tier marker with the URL attached:

Meta says an open-weight Spark will follow. [A](https://research.meta.ai/blog/...)[B](https://www.bloomberg.com/...)

That renders as the same tier chip it always did, now clickable. A reader who wants to go deeper clicks the A next to the claim instead of scrolling to the foot of the page and guessing which of twelve sources backs which of seven stories.

Rules for it:

• One set of chips per item, at the very end of it. Not per sentence. Marking every clause turns the prose into a minefield, and a chip mid-paragraph interrupts the read. Write them wherever is natural: chips_last() in the generator moves linked chips to the end of their paragraph or list item at build time, so the placement holds either way.
• [A] is the primary, the announcement or filing itself. [B] is the best outlet write-up. A reader clicking A should land on the thing that happened, not coverage of it.
• A bare [C] still needs a URL. Secondhand is a reason to link, not an excuse.
• Unlinked markers still render, so a marker with no URL is not a build error. It is a gap, and it is on you to notice it.
• The ## Sources list stays complete, including sources no chip points at. The chips are the way in, not the bibliography.

Sweep the beats

Twenty stories is a floor that only clears if every beat gets swept. Skip a beat with nothing new rather than forcing an item, but say in your run reply which beats came back empty. A missed beat has to be a visible decision, and the China/open-weights beat is named explicitly every time, even to say nothing happened.

• Frontier models, capability results, notable papers
• Lab business: funding, org changes, senior departures, partnerships
• Policy and regulation (US federal/state, EU, China)
• Chips, memory, data centers, power
• AI markets: moves, earnings, IPO pipeline
• Safety and security incidents
• China / open-weight releases
• Research worth reading: papers, benchmarks, notable open-source
• Robotics and physical AI
• Legal: court rulings, IP, liability

The three libraries

These are separate outputs, not brief sections. The brief is the day's news. The libraries are discovery surfaces, and a run has not finished until all three have been fed. They do not depend on whether anything about them made the news: a good MCP server shipped on a quiet Tuesday is exactly what these are for.

Targets, not quotas. A thin day is better than padding, and padding is obvious: it reads as a list of things with nothing said about any of them. But three empty days in a row means the sweep is not being done.

Two of them do have floors, because both failed the same way on day one and neither failure is visible from inside the run:

Tools need a spread, on two axes. At least three of the four scale values, including something small (project or tool) and something at platform scale, across at least three categories; and both values of reason, so a day carries something you would not have found and something you have to act on. Both belong: novelty and consequence are each a good reason to list a thing, and the failure is a day that is all of one. The news is about the big labs, so a run that follows the news fills the library with ten models from four companies. The weekend project, the MCP server somebody shipped on Tuesday, the repo with four hundred stars that does one thing properly: nobody issues a press release about those, and they only appear if you go looking on purpose.

Ventures need named company spotlights, at least two a day, from at least two different accelerators. A link to a batch directory is a link to somebody else's list. A spotlight is one company: what it is doing, who is doing it and where they came from, and the terms. Set batch on a company record and it becomes one, which makes founders, deal, site and accelerator required and the note a deep dive rather than a caption. The breadth rule exists because YC has by far the best public directory, which is exactly why a section left alone becomes a YC newsletter. Techstars, Entrepreneur First, South Park Commons, AI House, Neo, Antler and a16z Speedrun all produce AI companies worth a page.

Check both with python3 tools/catalog.py brief, which reads today's additions and says what is missing. Schemas and where to look: §3b.

Charts

Include at least one chart whenever the day has a number worth seeing. Fenced JSON:

{"type":"bar","title":"2026 hyperscaler capex","unit":"$B", "data":[["Amazon",200],["Alphabet",180],["Meta",125],["Microsoft",115]]}

Types: bar (ranked magnitudes) · split (diverging +/−) · line (series over time) · donut (share of a whole). Optional keys: sub, note, unit, labelWidth. The label gutter sizes itself to the longest label in the widest theme, so labelWidth is only a floor, you do not need to set it. Charts inherit the reader's theme. See tools/charts.py.

Then

1. Append to data/timeline.jsonl: anything that will still matter in six months. One JSON object per line: id, date (ISO), display ("Aug 10"), precision (day/month/quarter), tags (one or more from the vocabulary in tools/timeline.py), headline, entities (names from data/entities.json), optional detail for the fuller account. Most events carry two tags, a funding round in an open-weights lab is MONEY and OPEN. Entities are what connect an event to the predictions and issues that touch it, so name them. Validate with python3 tools/timeline.py. Skip the ephemera.
2. Check data/predictions.jsonl: resolve anything whose criterion was met (see §4); note movement under Prediction Watch.
3. Confirm all three libraries were fed. The brief can be finished and the run still be incomplete. If a library got nothing, say which and why in the run summary rather than letting the gap pass silently.
4. Commit and push (§5).