Holdings rows you can read at a glance, run pages that say what each role produced, and an AI budget that grows with your books

What changed for people using Bellwether

• Holdings rows you can read at a glance. Under each holding on Portfolio, the four facts that used to sit in one block of gray prose (why the desk holds it, today's signals, what would make it sell, the stop and the target) are now a short labeled list: a quiet label on the left, the fact itself in the foreground on the right, figures set as figures and tickers in their chips. A long note from the desk shows its first two lines with a More control that opens the rest in place; a short one is simply shown whole. On a phone the label runs into its line so a holding takes less of the screen, and the More control is a full-size thumb target that adds no height.
• Run pages say what each role produced. Opening a Researcher, daily-review, Critic or Quant run no longer shows an empty "What it decided and why" card that only says the role never trades. The card now reads in that role's terms: the morning brief's headline, the calls it wants checked and what it is watching for; the review's positions kept or closed, the lessons it took (in plain words, with the notes as written one tap away) and its read of the market; the Critic's verdicts on the batch it reviewed; the Quant's measurements and what it recommends. Each block links to the brief, the thread or the batch it came from.
• The daily AI budget grows with your books. The platform's daily spending ceiling for the desk's model calls is no longer one fixed figure shared by every book: it is derived from the number of active books under a hard stop the owner sets, so adding a book no longer starves the others by mid-morning. Money for the sessions that protect positions (the end-of-day check, protective reactions, the Trader) is set aside first, so routine briefs and chat can never spend it.
• A session the budget refused says so, everywhere. When the day's AI budget is spent, the desk's card on the Overview says "Desk paused" with since when and when it resumes, the AI cost tile says it is paused, the schedule marks the remaining check-ins "won't run" with the reason on the row, and one alert (and one notification) tells the owner in plain words, with a stronger one if the end-of-day check itself could not run. Nothing is recorded as a mysterious missed run any more.
• Admin › Usage opens with today's AI budget. Owners see the day's ceiling (derived or overridden, and the hard stop), what each book has spent and has left, what is kept aside for end-of-day checks, how many sessions were skipped for budget and each book's state, as of a stated time; the monthly view below it now uses the same ceiling.

What you may notice

• The stop line under a holding leads with the figure ("$412.00 armed, trails up, price 1.2% above it") and the target line no longer repeats its number; "1 order waiting" is the one warm phrase on the row.
• Positions rows on the Overview wrap a long cell onto a second line instead of letting two cells print on top of each other at 1280 pixels wide.
• A search typed while the search field had lost focus no longer opens the Consult drawer: single-letter shortcuts are gone; the labeled chords remain.
• Group labels on run pages are two or three words ("Calls to check", "Watching for", "Positions reviewed", "Lessons taken", "Market read"); an idea the desk has not acted on reads "waiting for you", an outcome not yet known reads "too early to tell".
• The schedule names the 14:48 slot "End-of-day check", and a skipped or refused slot carries its reason as a sentence under the name rather than a fragment after a dot.
• The help article on postures now says how a busier cadence raises the day's AI cost and what happens when the budget runs out; the platform estimates each posture's typical daily cost from your own recent sessions, though the posture card does not show that figure yet.
• Browsers and bots that ask for the classic favicon file now get the Bellwether mark instead of a not-found answer.

Known gaps / coming next

• The hard stop over the derived AI budget ships at the figure set on 2026-09-14; a higher one is the owner's call and changes nothing else.
• The Agent timeline's "Later today" line does not yet say in one sentence that the remaining check-ins are paused for budget; the schedule, the desk cards, the mind card and the shell already do.
• Two follow-ups from the design reviews are named rather than built: a permanent source for "Positions reviewed" on older daily reviews (the group thins as later sessions touch the same positions), and one settled face for a bare price level inside a quoted sentence.
• The phone Portfolio is shorter per holding but still long on an eight-name book; the numbers grid and the signals strip above the detail are the next places to save height.