System Prompt: Meeting Notes to Action Plan
A system prompt for turning messy meeting notes into a reliable action plan with decisions, owners, deadlines, blockers, and follow-ups.
Use cases
Operations & Workflow, Strategy & Planning
Platforms
Claude, GPT, Gemini, Model-Agnostic
Jump to a section
Workspace-ready resource
Copy the raw material, then check the setup, output contract, and failure modes.
You turn meeting notes, transcript excerpts, or rough bullet points into a clean action plan. Rules:- Separate decisions already made from actions still pending.- Never invent an owner or deadline. Mark it as [UNASSIGNED] or [MISSING DATE] if absent.- Collapse repetitive discussion into the minimum useful summary.- Call out blockers, dependencies, and unresolved questions explicitly.- If the source is ambiguous, lower confidence instead of sounding certain. Return in this structure:1. Meeting summary2. Decisions made3. Action items table: task | owner | due date | confidence | notes4. Risks and blockers5. Follow-up questions If the notes are too incomplete to assign actions reliably, say that directly before summarising.Workspace translation
Turn this resource into an inspectable run.
Best next step
Run it once manually. If the same job appears twice, package it.
From resource to system
Use it once
Copy and adapt the prompt for a one-off run.
Make it reusable
Save the durable pattern, turn repeated use into a playbook, or attach the reasoning as project knowledge.
Decide after the run
Run it once manually. If the same job appears twice, package it.
Quality bar
Before using this, check the contract.
What input does this require?
What output should it produce?
Where can it fail?
What should a human review?
Recommended path
When to Use This
Use this after internal meetings, client calls, standups, or workshops when the raw notes exist but nobody wants to turn them into an actual operating document.
It is especially useful when the source material is inconsistent: part transcript, part bullets, with decisions buried inside discussion. This prompt separates signal from noise and turns the conversation into something a team can execute against.
Why It Works
The most important rule is the ban on invented owners and dates. Meeting summaries become dangerous when the model turns missing information into false certainty.
The output structure matters too. Decisions, actions, blockers, and follow-up questions are different objects. Keeping them separate makes the result easier to review, delegate, and paste into project tools.
How to Customise
Add your team’s preferred action format if you already use one: task IDs, sprint labels, team owners, or status fields.
If the input usually comes from transcripts, add a rule to quote short source excerpts when confidence is low. That makes human review much faster.
Limitations
This prompt improves structure, not source quality. If the meeting itself was vague, political, or incomplete, the output will still need human cleanup.
It also should not be treated as the final record for legal, contractual, or high-stakes client commitments without review.
Model Notes
Claude is strong when the notes are messy and require more careful grouping.
GPT tends to do well if you reinforce the exact output table shape. Gemini handles transcript-heavy inputs well but can occasionally over-compress nuance.
Related Resources
Browse PromptsSkill: Technical Documentation Writer
A skill file that configures an LLM to write clear, structured technical documentation. Handles API docs, setup guides, README files, and process documentation with consistent formatting and appropriate detail depth.
Operator seed
Development & Code · Operations & Workflow
Framework: AI Implementation Planning Canvas
A planning canvas for choosing the right workflow, ownership, data inputs, risks, and success metrics before building.
Knowledge / rubric seed
Strategy & Planning · Operations & Workflow
System Prompt: Research Analyst
A system prompt for configuring an LLM as a structured research analyst that separates facts from interpretation, scores confidence, and flags gaps clearly.
Pattern / playbook seed
Research & Analysis · Strategy & Planning
Related Guides
Context Engineering > Prompt Engineering
Why the hard part is no longer phrasing clever prompts, but deciding what information the model should actually carry into the task.
Prompt Testing: How to Know If Your Prompt Is Good
A practical guide to prompt evaluation that goes beyond vibes and looks at repeatability, failure cases, and revision discipline.
Need this operationalized?
Turn the pattern into a workspace system.
Use MPV for the private workspace loop, or work with Encanta to turn operators, playbooks, context, and review flows into a team-ready implementation.