Directory / Journaling & post-trade review
Journaling & post-trade reviewBeginner#weekly-review#journaling#checklist

Propose one evidence-backed playbook change from the weekly review

On Sunday the agent compiles your mistakes and best trades from the journal and proposes at most one change to your written playbook, with the evidence. You approve or reject it.

How it works

  1. You paste or attach this week's journal rows, checklist log and exit-rule log (CSV/export from Google Sheets or Notion), along with the current playbook text; Grok does not read Google Sheets or Notion unless you provide them.
  2. The agent lists up to three biggest deviations from your plan and up to three best-executed trades, by process rather than by profit, using only rows that exist in the logs and inventing none.
  3. It proposes at most one change to your own written playbook, citing the rows that support it.
  4. You approve, edit or reject the change.
  5. You version an approved change in the playbook with the date and reason.

Copy-paste prompt

Run my weekly review using {{journal_sheet}}, {{checklist_log}} and {{exit_log}}. I am pasting the logs in this message. Use only what I provide; do not fetch Sheets, Notion or any other file.
1. List up to three largest deviations from my plan and up to three best-executed trades, only rows that exist in the logs; if the week has fewer trades or deviations, list only those and do not invent any. Rank process quality only by checklist adherence in {{checklist_log}} and exit-rule compliance in {{exit_log}}; ignore P&L.
2. Propose at most one change to {{playbook_file}}, citing the specific rows as evidence. Give the proposed wording as a diff I can paste. If the evidence is thin, propose no change.
3. Do not edit the playbook. Wait for my decision.

Guardrails

  • Human approves every rule change.
  • At most one change per week.
  • Your own playbook only.

What can go wrong

Changing several rules after one bad week makes it impossible to know what helped. One evidence-backed change per week is slow on purpose.

Why it helps

A playbook that changes slowly, with written reasons, compounds. One that changes after every loss doesn't.

aft-0006 and aft-0007 compute the numbers. This entry reads the journal, checklist and exit logs for process deviations and ends in one proposed playbook change that you approve or reject. It can use their stats as evidence but does not compute them.

Source and references

Original write-up by Agents for Traders. Background reading is linked below.

Spotted an error, or want your post removed? Email hello@agentsfortraders.com.

Educational content only. Not investment advice or a personal recommendation. No tickers, signals or trade alerts. Trading involves risk of loss.

Conteúdo exclusivamente educativo. Não constitui aconselhamento nem recomendação de investimento. Sem tickers, sinais ou alertas de negociação. Negociar envolve risco de perda.

Related use cases

Journaling & post-trade review

Review every closed trade in R-multiples, automatically

An agent runs a script on your closed-trade CSV to compute R-multiple and holding days (and MAE/MFE if you supply price history), then checks each trade's execution against the plan you wrote before entry.

Intermediate#journaling#r-multiples#weekly-review
Journaling & post-trade review

Summarise weekly journal stats by setup, with a minimum sample before any conclusion

Every weekend you paste pre-computed journal stats into an agent, which reports win rate, average R and expectancy by setup tag, regime and weekday, and labels any group below your minimum sample as not enough data.

Beginner#journaling#r-multiples#weekly-review
Discipline, checklists & psychology

Run your pre-trade checklist and log the answers

Before you place a trade, the agent asks your five checklist questions, flags chasing or names that are not in your plan, and gives you a timestamped log line to paste into your journal.

Beginner#checklist#journaling#beginner-friendly
Discipline, checklists & psychology

Check exit-rule adherence after the close

After the close, the agent checks each open position against the exit rules you wrote and reports which rules were met. It reports; you decide.

Intermediate#end-of-day#checklist#journaling
Journaling & post-trade review

Turn your trade journal into a setup library the agent keeps current

From your journal and post-trade reviews, an agent maintains one linked page per setup. Each page holds your written definition, example trades, common mistakes and stats computed in code; a separate dated log records every definition change.

Intermediate#journaling#weekly-review#r-multiples
Journaling & post-trade review

Get your agent to follow up on the promises you write in your journal

The agent pulls the commitments out of your journal notes, such as "next time I'll wait for the close", asks you about each one a few days later, and keeps a simple kept-or-broken record for your weekly review.

Intermediate#journaling#weekly-review#checklist