Breaking a task down into three chained prompts

1Why three prompts beat a single one

Breaking down is the most profitable technique to learn after the four ingredients. Ask for three things in a single prompt: you will get one done well, one half done, one not at all. Ask for the same three things in three messages, and all three come out usable. Research measures the same effect: splitting a problem into sub-questions handled in order takes a model from 16 percent to over 99 percent success on a composition exercise (Zhou et al., 2022).

The lesson's chain has three links. Prompt A produces a plan or a grid: the structure of a document, the criteria of a comparison, the columns of a table. You read it and correct it: this validation is the move that changes everything. Prompt B produces the content from the validated plan, with the source last and a rule for missing information. Prompt C reviews B's content against a short grid: does every statement have its page, its row, its article? Do the bullets respect the length?

In Copilot Chat, the chain runs in a single conversation: Microsoft confirms that the conversation history remains accessible and that each turn keeps the context. Two precautions. Open one conversation per task, and paste the full prompt again when the exchange grows long, rather than writing "like earlier". For prompt A or C, the "Think deeper" mode in the model selector, at the top right, hands the step to a slower reasoning model, which Microsoft documents for analysis and verification.

One last setting, the one behind this lesson's booster: when you do not need to see the reasoning, ask Copilot to reason step by step internally and deliver only the result. When you need traceability, ask instead for the quotations before the analysis.

Tap to enlarge

2A forty-page report turned into eight slides

A project manager must draw eight slides from a forty-page report he attaches, for an executive committee.

Weak prompt:

Make me a presentation of this report.

Copilot proposes twelve slides with vague titles, figures without page numbers and a conclusion that is not the report's. Everything has to be redone, nothing can be checked quickly.

Strong prompt, in three stages:

Prompt A. From the attached report.pdf, propose a plan in eight slides for an executive committee that has fifteen minutes. For each slide: a title and the key message in one sentence. Wait for my validation before writing anything.

(validation: I merge slides 3 and 4, I replace slide 7 with "risks and expected decisions")

Prompt B. For each slide of the validated plan above, write three bullets of 12 words at most. Under each bullet, give the figure or the quotation from the report that supports it, with the page number. If no passage of the report supports a bullet, write "to be sourced" instead of filling in.

Prompt C. Review the eight slides. List every bullet without a page number and every bullet over 12 words. Rewrite nothing, only flag.

The plan arrives in eight lines and is corrected in two minutes. The bullets come out sourced page by page. The review flags two "to be sourced" bullets and one bullet that is too long, corrected by hand before formatting.

What changes: the plan is his, not the model's, because he validated it before the writing. Every bullet points to a page, so checking takes five minutes instead of an hour. The gap is visible ("to be sourced") instead of being filled by a plausible invention.

3Split a chase-up email into three prompts

Three fictional sets of meeting minutes, written by you with no real data, are to be attached. Here is the starting prompt, to be broken down:

"Read the three attached minutes, summarise them, tell me which actions are late and write the reminder email."

Split it into three prompts. Prompt A extracts all the actions into a table (action, owner, due date, status, source file and line), with "to be specified" for any empty cell. Validate the table against the files. Prompt B calculates, as of 10 September 2026, the late actions and the number of days late, from the validated table only. Prompt C writes a 100-word reminder email per owner concerned, then reviews: every action cited in an email must exist in the table. The composer below helps you with each prompt; enable the "Propose an outline before writing" booster for prompt A.

Self-assessment grid: (a) three prompts with a goal and a format each; (b) a written validation between A and B; (c) no email mentions an action absent from the table.

Open the prompt composer