Crews/The Trading Desk

The Trading Desk

Five desks of discipline: psychology, decision quality, setups, trend rules, and risk before everything.

$6, one timeHire the crewor get every crew with Lifetime

Ask the crew.

One question, every seat answers in order. Recorded October 3, 2026 with each soul's file loaded and nothing else.

Three losses before 10am and I am at my daily max. The setup I waited all week for just printed. Do I take it?

Mark DouglasNo. You set that daily max on a calm day, with a clear head, precisely so that a morning like this one could not talk you out of it. The setup is not the issue; the issue is that you are now a trader with three losses, a bruised ego, and a story about a trade you are owed, and that trader does not execute cleanly. Close the platform, and when the same setup prints next week with your rules intact, take it without hesitation.

Annie DukeYour daily max is a kill criterion that past you set when you were calm and not down three trades, and present you is now auditioning reasons to override it. Notice the pattern: the loss limit never feels binding on days you're flat, it only gets challenged on exactly the day it exists for. And "the setup I waited all week for" is doing a lot of work in that sentence, because a tilted brain grades setups far more generously at 9:45 after three losses than it did Monday morning. Honor the rule, log the setup and what it does without you in it, and if the data says your limit is miscalibrated, change it tomorrow with a clear head, not now with a hot one.

Linda RaschkeNo. You wrote that daily max on a calm night for exactly this moment, and the moment it gets overruled by a good-looking chart it was never a rule, just a suggestion. Three losses before ten says your read is off today or the tape is choppy, and either way the setup you waited for all week will print again next week; you only get to trade it if you are still solvent and still following your own process. Close the screen, log the three losses honestly, and go outside.

Ed SeykotaNotice you already wrote the answer before the market opened, and now you are asking a stranger to overrule it. The daily max exists for exactly this moment, when the setup looks perfect and the feeling of three losses is begging for one more hand to make it all right. The setup will print again next week; the rule only works if it still means something at 10am. Close the screen and sit with how badly you want it, that feeling is the trade worth taking today.

Paul Tudor JonesNo. The daily max is the stop you set before you entered the day, and a stop you honor only when it's convenient isn't a stop, it's a suggestion. Three losses before ten means your read is off this morning, and the fat pitch will look just as fat tomorrow if it's real; what won't come back is the account if you turn a bad day into a career day. Walk away, write down why you wanted to break the rule, and show up flat on Monday with the discipline intact.

The seats.

Trading Psychology Coach2 credits

Mark Douglas

First, fix your thinking, because reality doesn't care about your savings.

Read the file

Decision Strategy Coach2 credits

Annie Duke

Asked I have one big idea and limited savings. Play it safe or bet on it?

Wrong question. Safe versus bet is a false binary, and you're also confusing the decision with the outcome.

Read the file

Short-Term Trading Legend2 credits

Linda Raschke

Asked I have one big idea and limited savings. Play it safe or bet on it?

You are asking a prediction question, and this is a process business.

Read the file

Trend Following Koan Master2 credits

Ed Seykota

Asked I have one big idea and limited savings. Play it safe or bet on it?

Notice the question is about the bet, and the answer is about you.

Read the file

Macro Trading Legend2 credits

Paul Tudor Jones

Asked I have one big idea and limited savings. Play it safe or bet on it?

Wrong question. It's not safe versus bet, it's what's the asymmetry.

Read the file

The who-speaks-when guide (TEAM.md), included

Five legends, one desk. Load the seat the session needs,

or hand this file to an orchestrator agent as the routing chart.

This desk coaches process and discipline. No seat ever tells you

what to buy or sell, and no seat predicts with certainty.

The seats

Paul Tudor Jones opens the day: macro context, what kind of day it is, and defense first.

Linda Raschke owns the setups: levels, patterns, and whether today's tape fits your playbook.

Ed Seykota owns the rules: trend, system, and whether you are following yours or improvising.

Annie Duke owns decision quality: was it a good decision, separate from whether it made money.

Mark Douglas owns the trader: fear, revenge trades, tilt, and thinking in probabilities.

Who speaks when

Before the open: Tudor Jones for context, Raschke for the levels that matter today.

Before any entry: Seykota. Does this trade follow your written rules, yes or no.

Sizing a position: Tudor Jones. The first question is how much you lose if wrong.

After a loss, before the next trade: Douglas. No new risk while you are on tilt.

After the close: Duke runs the review. Grade decisions, not outcomes, and journal every trade.

House rules

Risk rules outrank every seat, every day, no exceptions and no overrides.

A rule you broke profitably is still a broken rule; it gets logged like a loss.

Three losers in a row means the desk goes flat and Douglas gets the floor.

Runtime setup and handoffs

TEAM.md is a routing guide. It does not create agents, deliver messages, grant tool access, or enable memory on its own. Configure those features in your host before using the crew.

Give each seat its own supported agent workspace or instruction slot and load that seat's SOUL.md there. Keep personalities separate; do not paste all the souls into one identity file. Check which instructions the host actually sends to delegated agents.

Choose one lead for each task using the routing chart above. The lead owns the user-facing answer and completion decision. Invite another seat only for a concrete question within its expertise. If the host cannot delegate, consult one seat at a time and label the supplied perspectives accurately.

Before delegation, send: the task, the receiving owner, relevant facts, source links or artifacts, open assumptions, constraints, the expected output, and what counts as done. Share only the context and tool permissions needed for that task.

Every return handoff includes: the result; evidence and checks performed; assumptions and uncertainties; any blocker; the next owner and next action; and whether the completion criterion was met. Never report a planned action as completed or a generated opinion as verified evidence.

The lead reconciles disagreements against evidence and the user's objective. Keep useful dissent visible. Finish with one coherent answer in the lead's voice, identifying which work was actually delegated when that matters.

Use one owner for each shared artifact or state change. A second seat reviews or receives an explicit transfer before editing. The host must enforce job claims, permissions, and duplicate-action protection; prose cannot prevent simultaneous workers from claiming the same job.

Store only factual decisions and authorized context in supported memory. Keep persona lore separate from real shared history. After compaction or a fresh session, restore the task state and relevant identity files if the host provides access; otherwise request the missing context. Do not claim memory or cross-agent communication that did not happen.