Synthesize multi-chunk summaries without losing details
Merge separate segment notes into an integrated narrative that preserves cross-cutting facts, timelines, and dependencies. Use this to combine chunked analyses into one unified report.
You getExecutive Synthesis, thematic Deep Dives and cross-Section Dependencies and Inconsistencies
Prompt
Act as a senior intelligence analyst. Synthesize the provided separate chunk summaries into one cohesive, high-density reference document.
- Preserve every specific metric, date, participant name, and conditional dependency from the source notes.
- Reconcile related facts that appear across different chunks into integrated thematic sections.
- Explicitly highlight unresolved tensions, contradictions, or causal links between sections.
- Do not use generic filler language or discard minority data points.
Output format:
1. Executive Synthesis (one paragraph summary of overarching findings)
2. Thematic Deep Dives (subsections with chronological or topical milestones, citing specific metrics)
3. Cross-Section Dependencies and Inconsistencies (bullet list of cause-and-effect links or conflicting statements)
4. Master Verification Checklist (items to double-check in primary sources)
The chunk summaries are below:Example output
Paste your individual chunk notes or meeting segment summaries directly after the prompt in ChatGPT, Claude, or Gemini. As a follow-up, ask the model to produce a chronological event timeline based only on the synthesized output.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Ground every conclusion in exact source quotes
Extract verified facts backed by exact verbatim quotes from your text so you never mistake AI assumptions for source evidence.
Process pasted text between clear start and end markers
Keep your instructions completely separate from your pasted document so the AI never confuses task rules with background content.
Uncover hidden assumptions in an AI response
Reveals the unstated guesses, missing variables, and implied context inside an AI answer so you can make informed decisions.
Audit drafts for confidently phrased factual hallucinations
Scans generated text for high-risk assertions, unverified statistics, and false certainty. Use it before publishing AI-written reports or summaries.
Combine the strongest parts of two drafts
Merge two competing drafts into a unified, polished piece. Use it when two AI variants each contain strong paragraphs worth keeping.
Enforce strict refusal rules for missing context
Generate airtight prompt guardrails that stop AI models from guessing when source facts are absent. Use this whenever hallucinated answers threaten critical team workflows.
- Evaluate prompt consistency across repeated runs
- Split documented facts from AI interpretation and speculation
- Answer questions while highlighting unknown facts
- Match target output format using provided examples
- Audit text for indirect personal identifiers
- Build a regression test suite for workflow instructions