The Portfolio Manager

The PM decides what your book should hold and writes proposals with a thesis attached. It never places an order: the Executor checks every proposal against your limits and, above your approval line, hands it to you. Every session is a fresh context with a fixed budget; nothing carries over except what earlier sessions wrote down.

Owns

Trade proposals, position theses, watch items, the journal, lessons

Reads

Its state card: last outcomes, Critic findings, your guidance, risk headroom, the brief, signals, its memory

Tools

Market data, news, filings, signals, prior decisions, the proposal preview, memory; no broker tool, shell, file or network

Model

Fable 5.1 premarket and postmarket; Sonnet 5 intraday and react

Cadence

08:00, every 60 minutes 09:00–⁠14:30, 15:15 CT; react sessions on events, at most 12 a day

Change it at

Portfolio Manager › Settings: the model, fallback, effort, turns and budget per session (raising a cap asks for your code), check-ins on or off, the check-in interval and the check-in model

Hands off to

The Executor (proposals); the Critic reviews every session that proposed; the next session inherits its memory

Judged by

Your rejections and their reasons, the Critic's findings, and the postmarket review of every thesis

What it owns and reads

The PM owns the book's intent: every proposal, thesis, watch item, journal entry and lesson. It reads only what the state card and its tools give it; memory is an input, tool data is truth.

Tools

One allowlist: market data, the calendar, news, filings, fundamentals, movers, the research feed, screen_universe (the nightly universe screens: top or bottom names by momentum, RSI(2), gap, volume surge and more, over what this book could actually trade), factor scores, the regime, algorithm signals, prior decisions, earlier briefs, its own transcripts, the proposal preview, watch_level and memory. Nothing on it touches the broker. A react session is given a narrower part of the same list (no memory_write, for one). What a session is given, what the model is allowed to call and what is recorded are kept identical by an automated check, so a tool can never be named for the role and yet be missing from its sessions.

Sessions

Premarket and postmarket run on Fable 5.1 ($5.00 and 40 turns per session), intraday on Sonnet 5, react on Sonnet 5 with $0.40 and 8 turns (the platform can set the react budget anywhere up to $0.75; the 12-a-day cap and the book's daily model budget bound the total). The model, fallback, effort, turns and budget per session, check-ins on or off, the check-in interval (15, 30 or 60 minutes) and the check-in model are yours to set on Portfolio Manager › Settings; lowering a cap is one click, raising it again asks for your code. On a quiet tape an intraday slot after the first may be skipped. See Model policy.

Written procedures for particular moments

Some situations have a written procedure that code adds to a session only when it applies, so the PM is not improvising on the days that matter most. Each one was switched on only after it was measured on live sessions with and without it.

• Every intraday check starts by reading the account, the positions, quotes and the live signals before anything is proposed. Those sessions open with more reads and take about five seconds longer; what the PM buys on a normal day does not change.
• A held name that is halted gets no order and no new level while it is halted, and a written plan for the resume. If it reopens through its stop, the exit is priced off the live bid.
• A drawdown day, when the book steps down another whole percent from the day's opening equity: the PM re-reads the account and every position, adds nothing in that check, and protects every name close to its level first.
• A book that holds positions, on the intraday check: each position is managed against the stop and target written at entry. See exits, targets and stops.

The state card

Each session opens with a state card, assembled so what needs a response comes first: what became of its last decisions (accepted, rejected and why, filled, expired, awaiting you); open Critic findings; your guidance notes, verbatim; the wake reason or your question; book and risk headroom; today's brief, flagged when stale; the algorithms' votes; and its memory index.

What a proposal contains

A proposal is a ticket: symbol, side and quantity; a limit price (premarket, a peg to the open with a cap it will not pay past); a thesis with an explicit invalidation and a stop suggestion; confidence and horizon; the tool outputs it relied on. The PM previews the draft with propose_orders, which runs the Executor's risk checks, and is told not to argue with a failed check. Proposals also carry an action (tighten a stop, move a target, re-price or cancel a resting order, scale out or close), and a stop only ever tightens. A cancel may also name an order that has not reached the broker yet (parked for tomorrow by the 14:48 pass, queued for the window, or waiting for you): the Executor then withdraws it, the proposal closes as rejected with a "withdrawn by analyst" note, and nothing is sent. That is how the premarket session drops a parked order whose thesis broke overnight. On scheduled macro days (CPI, FOMC) the PM halves a starter rather than standing aside; a blanket "no new longs this week" is your call through a guidance note, not something it imposes on itself. When it does state a short-dated rule of its own, that rule is recorded in its handoff with an end date (at most five trading days out) and shown as "Constraints in play (self-imposed)" so the next session and you can see it.

What the desk noted earlier

When a name comes up that the desk has looked at before, the PM can pull back what this book already has on file about it: the Researcher's earlier briefs, the if-then ideas filed on that name, the desk's coverage notes and the research items the desk read. It looks back 90 days unless it asks for more, and never further than about six months. Open the session on Desk and What it looked at says so in plain words, for example "Looked up what the desk had noted earlier about NVDA", so an idea the book formed in August is not silently forgotten in September. It reads this book's own record only; nothing from another book can reach it.

Structured memory

Continuity is typed state, not a transcript: theses with invalidation and review dates, watch items with machine-checkable triggers, open threads, a handoff to the next session, lessons and the journal, plus scratch notes written with memory_write into the database, never to a file system. See reading the mind card.

What the PM remembers, and what it never learns from

Memory is lived experience, not imported evidence. The PM's lessons, theses, journal and handoffs record only this book's own operation: its decisions and what became of them, your guidance and rejections, and the Critic findings it answered. Two rules follow, and both are enforced by the platform, not left to the model's goodwill.

• Lessons are per-agent and self-curated. The PM writes and retires only its own lessons; the Researcher keeps its own notes on sourcing and calibration under its research namespace and cannot write a PM lesson, thesis, watch item or regime note; anything PM-owned that another role hands back is dropped with a warning, never stored. No screen, script or other role inserts a lesson for the PM either. Others influence it only through channels it must acknowledge: Critic findings, your rejections and guidance notes, and the Quant's changes you accepted. What to encode as a lesson is the PM's call, and a lesson that tool results contradict is retired in the same session, not carried silently.
• Evidence stays evidence. Backtests, Lab and simulation runs, the evidence pack's numbers and Quant findings are for you and for the Quant; they are never written into PM memory. A language model has read the years a backtest replays, so "learning" from simulated outcomes would teach it its own hindsight. The Quant's findings reach the PM as a labelled, read-only "Quant desk" section of its state card, and reach you as Inbox cards you accept; accepted ones become configuration, not lessons. Offering a durable finding to you as a Playbook line, which you would write and the PM must acknowledge, is decided and not in this build yet. The rule that nothing imports into lessons already holds.

To read what the PM currently holds as standing lessons, press State card on Strategy › Guidance: it renders the card the next session will read, lessons included. Consult remembers only your stated preferences, and the Critic writes findings, never memory.

Guidance is never optional

Every note on Strategy › Guidance appears in the card, and the PM must acknowledge each one: applied, not applicable, or disagree with a reason while still complying. A hard-constraint note is also compiled into an Executor rule. See playbook vs steering.

What it cannot do

Place, modify or cancel an order at the broker, move money, run a command, write a file or fetch a URL. A tool off the allowlist is denied and recorded. It cannot change a limit, your posture or your autonomy.

How it hands off

The Executor picks a proposal up on its next pass, within about 5 seconds, and no earlier than the proposal's window opens; a premarket idea stays valid until 14:30 CT, an intraday one for at least 90 minutes and never into the last 15 minutes. The PM learns the verdict, fill or expiry at its next session. The Critic reviews each session that proposed, right after it ends, and gives a new-position buy or a $250 add a fast look before the Executor sees it. The journal, theses and handoff note are what the next session wakes up to.

How it is judged

By outcomes and by review: your rejections with reasons, the Critic's findings it must answer, the postmarket review of every thesis and the day report's anomalies. Lessons that prove out are promoted; the rest are retired.

Why a trade happened

Open Desk and pick the session from the day's list. While a session is still running, a Live part at the top narrates it in plain words, newest line first, the same stream the Overview's mind card shows (what it is reading, which names it is checking, when it drafts, what it decided). What it decided shows each order with where it is now, and an idea it passed on says why. What it looked at lists what it read. Second opinion shows the Critic's findings and the PM's answers. The PM's own reasons sit one click behind the rows, under The PM's note, as written.

For the full record, open Technical details at the foot of the session. The Transcript is the session's own account, with its thinking between the lookups. Tool calls is exactly what it looked at, in order. Orders as the risk rules checked them shows each order with the Executor's verdict on every check; Desk › Today opens it, and the first failure wins. The order and fill are on Activity; anything waiting for you is in the Inbox. Reading the Desk screen walks through every part.

Failure modes you might see

• Nothing proposed: normal on a quiet day; the reasoning says why.
• Refused, by a risk rule: a check failed when the Executor ran it for real; the row says which in words and its Activity row names the check.
• Not placed: price moved. On approval the Executor re-quotes; if the price has run more than 2% past the proposal's limit (or past its own cap) nothing is placed and the next session is told to re-propose.
• Sent back once: a response that skipped a guidance note or a Critic finding is asked for again in the same session. A note still unacknowledged fails the session; a finding still unanswered is counted as ignored and reported. React sessions must acknowledge guidance like any other but are not sent back over Critic findings; the next scheduled session answers those.
• Stopped at its cap: a session that hits its dollar or turn cap ends there; the next one picks up the handoff.