Prompt
Deep Research Prompt Template
Reusable Deep Research prompt that produces cited, structured reports every time.
1 min readupdated 2026-07-06
/ quick answer
Use with ChatGPT Deep Research, Gemini Deep Research, Perplexity Pro or Grok DeepSearch. Fill the 4 variables and run. Reusable Deep Research prompt that produces cited, structured reports every time.
Reusable Deep Research prompt that produces cited, structured reports every time. Use with ChatGPT Deep Research, Gemini Deep Research, Perplexity Pro or Grok DeepSearch. Fill the 4 variables and run. Copy the prompt below, swap the bracketed variables for your own context, and run it in any capable model. This prompt node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Context
Use with ChatGPT Deep Research, Gemini Deep Research, Perplexity Pro or Grok DeepSearch. Fill the 4 variables and run.
Prompt
You are an expert research analyst. Produce a report on: {{TOPIC}}.
Audience: {{AUDIENCE}}.
Timeframe: only sources from {{TIMEFRAME}}.
Goal: {{DECISION_TO_SUPPORT}}.
Required structure:
1) Executive summary (150 words, 3 bullet points).
2) Landscape overview.
3) Comparison table of the top 5 players (columns: pricing, differentiator, ideal customer, risk).
4) Trends and inflection points (with dates).
5) Recommendation for the audience above, with confidence level.
Rules: cite every non-obvious claim inline. Prefer primary sources (docs, official blogs, filings) over aggregators. Ignore SEO-farm content. Flag conflicting sources.Example Output
# Serverless GPU Providers 2026 **Executive summary**: Modal, Runpod and Beam lead on price-per-second... [inline citations continue]
Related Workflow
Related Tool Stacks
/ frequently asked
What does the Deep Research Prompt Template prompt do?
Use with ChatGPT Deep Research, Gemini Deep Research, Perplexity Pro or Grok DeepSearch. Fill the 4 variables and run.
Which AI models work with this prompt?
It is model-agnostic: it works with any capable general model. Replace the bracketed variables with your own context before running it.
What output should I expect?
# Serverless GPU Providers 2026 **Executive summary**: Modal, Runpod and Beam lead on price-per-second... [inline citations continue].
↳ connected nodes
Workflow↳ linked
Turn Deep Research Into a Weekly Executive Brief
Use an AI Deep Research agent every Monday to produce a cited market brief in 20 minutes.
Tool Stack↳ linked
AI Research & Knowledge Stack
Default toolset for analysts, founders and creators doing deep research with AI.
Prompt↳ linked
Sourced Research Brief Prompt
Produces a structured brief where every claim carries a citation.
Prompt↳ linked
Market Research Synthesizer
Compress 10-20 sources into a 1-page decision-grade brief.
Prompt↳ linked
Competitor Teardown Prompt
Deep-dive one competitor from public artifacts.
Dictionary↳ linked
Deep Research (AI)
Long-running AI research task that produces a cited multi-page report.