patrickz
Before you start
A chat assistant, the short fictional transcript below and paper or a diagram editor.
Why this lesson exists
The archived posts behind “Turn Messy Inputs Into Visual Systems” connect observation, explanation and reconstruction. A useful visual reduces confusion while preserving what the source actually says.
Practice material
Fictional. Use it for every step below, or swap in your own later.
Newsletter planning call (fictional transcript) Jo: The spring newsletter needs to go out before the end of the month. Sam: I’ll collect the three event write-ups first. Jo: Once they’re in, Lee lays out the draft. Lee: Before it goes out, a manager may review the draft. I’ll ask. Sam: If nobody has reviewed it by Thursday, do we send it anyway? Jo: Not decided. Let’s raise it next week. Lee: After it’s sent, I’ll pin a printed copy to the noticeboard.
Do the exercise
Extract before designing
Ask for the people, decisions, sequence and unresolved questions in the notes. Correct this list before generating a diagram.
Choose the right shape
Use a timeline for sequence, a table for comparisons and a flowchart for branching decisions. Ask why the selected format fits the question.
Limit the visual
Use five to seven main elements and short labels. Mark uncertain relationships with a question or dotted line rather than drawing them as facts.
Trace it back
Compare every label and arrow with the source. Give the visual to another person and ask them to explain the process without your narration.
A prompt to adapt
Replace the bracketed parts with your own details.
Turn these notes into a visual explanation for [audience]. First extract facts and uncertainties. Recommend a timeline, table or flowchart and explain why. Use at most seven main elements. For each label and relationship cite the supporting sentence. Notes: [notes].
What this looks like
If the notes say a manager may review a draft, a diagram showing mandatory approval changes the process. Preserve “may” or flag the question.
Check your result
Use evidence from your output. A confident explanation from the AI is not enough.
If it isn’t working
If the diagram is crowded, separate the overview from details. If AI-generated lettering is wrong, put the text in an editable diagram instead of repeatedly regenerating the image.
Optional. Progress stays in this browser.
Where this came from
Adapted from the archived LinkedIn theme “Turn Messy Inputs Into Visual Systems.” See the post coverage and editorial method. One of the original LinkedIn posts ↗
Prepared September 2026. Tools and interfaces change; use current official setup instructions. Session lengths are estimates.