Summarise to bullet points prompt template

Turn long text into a tight, scannable bullet summary tuned to a specific reader and purpose.

Free to copy3 fill-in variablesWorks with any text-based AI model

Copy the prompt

Keep the instruction intact and replace each double-braced field with your own context.

Summarise to bullet points
Summarise the text below into at most {{max_points}} bullet points.

Source text:
{{source_text}}

Write for this reader: {{audience}}. Lead each bullet with the most important
fact, keep each one to a single line, and drop anything that does not change a
decision. Preserve specific numbers, names, and dates exactly. Do not add facts
that are not in the source. If something critical is missing or ambiguous, add a
final bullet labelled "Open question" describing it.

Fill in the variables

Use the examples as a shape, not as required wording.

{{source_text}}
The text, transcript, or notes you want condensedExample: Full notes from a 45-minute product planning call covering scope cuts, the new launch date, and a hiring freeze.
{{max_points}}
The maximum number of bullets allowedExample: 6
{{audience}}
Who will read the summary and whyExample: an exec who only wants decisions and risks

Filled-in example

This shows the template with realistic inputs before it is sent to a model.

              Summarise the text below into at most 6 bullet points.

Source text:
Full notes from a 45-minute product planning call covering scope cuts, the new
launch date, and a hiring freeze.

Write for this reader: an exec who only wants decisions and risks. Lead each
bullet with the most important fact, keep each one to a single line, and drop
anything that does not change a decision. Preserve specific numbers, names, and
dates exactly. Do not add facts that are not in the source. If something
critical is missing or ambiguous, add a final bullet labelled "Open question"
describing it.

            

How to use this template

Three checks keep the result useful and grounded in your actual task.

  1. Give it real context.Replace every variable and remove any instruction that does not apply.
  2. Run it in your preferred model.The template is plain text, so it works with ChatGPT, Claude, Gemini, and local models.
  3. Review before you rely on it.Check facts, code, claims, and sensitive information; then save the wording that performed best.