patrickz
Before you start
A chat assistant and five short, non-sensitive sample daily notes. A folder of text files is optional.
Why this lesson exists
Patrick’s weekly-review workflow compares stated goals with recorded behavior. The point is to find a usable pattern, not to ask a model to judge your character.
The idea this guide practices: Use AI as a mirror, not a judge.
Practice material
Fictional. Use it for every step below, or swap in your own later.
Goals for the week (fictional) 1. Complete two spreadsheet practice exercises. 2. Send one reviewed proposal draft to the team. Mon: Started late after meetings. 20 minutes on exercise 1; stopped at the IF formula. Blocker: meetings ran over. Tue: Started late after meetings. Outlined the proposal, 30 minutes. Blocker: waiting for budget numbers. Wed: Finished exercise 1 before lunch, 25 minutes. Blocker: none. Thu: Started late after meetings. Proposal draft half written; time not recorded. Fri: Asked a colleague to review the proposal draft. Exercise 2 not started. Blocker: afternoon workshop.
Do the exercise
State the intended week
Write two goals with observable outcomes, such as completing two practice exercises or sending one reviewed proposal.
Collect a small record
For each day record what happened, time spent and one blocker. Distinguish “not recorded” from “did not happen.” Remove other people’s private information.
Ask for evidence
Request a goal-by-goal comparison with a quotation or date supporting each observation. Ask the model to separate facts, tentative patterns and unanswered questions.
Choose one adjustment
Pick a single change you can test next week. Set a review date and a measure. Keep the notes as the source of truth instead of relying on the assistant to remember them. To turn the adjustment into a full trial with a baseline and a stop rule, continue with Turn a vague goal into a seven-day experiment.
A prompt to adapt
Replace the bracketed parts with your own details.
Compare these goals with these dated notes. For every observation cite a date or exact note. Separate recorded facts from hypotheses. Missing entries are unknown, not failures. Suggest three small experiments; I will choose one. Goals: [goals]. Notes: [notes].
What this looks like
Three notes saying “started late after meetings” support testing a morning study slot. They do not support a claim that you lack discipline.
Check your result
Use evidence from your output. A confident explanation from the AI is not enough.
If it isn’t working
If the review sounds like a personality diagnosis, ask it to describe only recorded actions. Reduce the input to one week and one goal.
Optional. Progress stays in this browser.
Where this came from
Adapted from the archived LinkedIn theme “My AI Read My Week, Compared It With My Goals, and Chose Violence.” See the post coverage and editorial method.
Prepared September 2026. Tools and interfaces change; use current official setup instructions. Session lengths are estimates.