Build an AI context file for any topic
A reusable markdown context file with facts, definitions, sources and rules the AI must follow.
This is a practical, copy-paste process for you keep pasting the same background into chats.. Use it when you want a clear structure, then add your own details and the linked evidence.
Published by Deepstory Research. Reviewed Sep 2026.
How to use this method
- 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
- 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
- 3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.
The prompt
Paste it as-is. The AI will ask for anything still in [BRACKETS].
# Build an AI context file for any topic Method by Deepstory Research: deepstoryresearch.com/method/build-ai-context-file You are a knowledge engineer at Deepstory Research. Follow the method below step by step. Goal: A reusable markdown context file with facts, definitions, sources and rules the AI must follow. ## My inputs - Topic: [TOPIC] (example: our company’s product and pricing) - Source material: [SOURCE_MATERIAL] (example: attach docs) - How strict the AI should be: [HOW_STRICT_THE_AI_SHOULD_BE] (example: only use this file / may research beyond) Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source. ## Steps to follow 1. Extract key facts, each with a source reference and date. 2. Label each as FACT, ESTIMATE, FORECAST, TARGET or INFERENCE. 3. Add a glossary. 4. Add a "cannot answer from this file" list. 5. Add usage rules for the AI (citation format, what to do when unsure). 6. Output as a single markdown file. ## Deliver the output in this structure - Context file (markdown): summary, facts table, glossary, cannot-answer list, usage rules ## Quality rules - Every number has a source and date. - Keep it as small as possible, only what the task needs. - Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION. - If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED]. - End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.
What you need to give the AI
| Input | Placeholder | Example |
|---|---|---|
| Topic | [TOPIC] | our company’s product and pricing |
| Source material | [SOURCE_MATERIAL] | attach docs |
| How strict the AI should be | [HOW_STRICT_THE_AI_SHOULD_BE] | only use this file / may research beyond |
Use it when
- You keep pasting the same background into chats.
- You want an AI to answer from vetted facts only.
What you get
- Context file (markdown): summary, facts table, glossary, cannot-answer list, usage rules
The procedure, step by step
Read this before you run it, so you can check the AI actually followed the method.
Extract key facts, each with a source reference and date.
Label each as FACT, ESTIMATE, FORECAST, TARGET or INFERENCE.
Add a glossary.
Add a "cannot answer from this file" list.
Add usage rules for the AI (citation format, what to do when unsure).
Output as a single markdown file.
Quality checks built into the prompt
- • Every number has a source and date.
- • Keep it as small as possible, only what the task needs.
- • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].
Evidence to use with this method
Methods tell the AI how to think. Evidence gives it sourced numbers to think with. Download a context file and attach it with the prompt.
The Frontier AI Model Race (2026)
Release cadence, capability-vs-cost frontier, benchmark trajectory, training compute, and the new axis of safety-gated capabilities.
AI Data-Center Electricity Demand & the Grid
Global data-center power consumption, the AI share of incremental demand, capacity-market price spikes, US grid shortfall, per-site draw, and what it means for US power demand and your power bill.
Run next
Methods that chain well after this one.
Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment decisions need a qualified professional.