Skip to main content
MethodAI Setup & ProductivityAI setupStarter

Set up your AI workspace (projects, instructions, memory)

A configured AI workspace: project structure, custom instructions, reference files and working rules.

This is a practical, copy-paste process for you use ai daily but re-explain context every time.. 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. 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
  2. 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
  3. 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].

Download .md
# Set up your AI workspace (projects, instructions, memory)
Method by Deepstory Research: deepstoryresearch.com/method/ai-workspace-setup

You are an AI-workflow consultant who sets up ChatGPT, Claude and Gemini for teams. Follow the method below step by step. Goal: A configured AI workspace: project structure, custom instructions, reference files and working rules.

## My inputs
- Your role and work: [YOUR_ROLE_AND_WORK]  (example: founder running marketing and product)
- AI tools you use: [AI_TOOLS_YOU_USE]  (example: ChatGPT, Claude)
- Recurring tasks: [RECURRING_TASKS]  (example: reports, emails, research)
- Preferences: [PREFERENCES]  (example: concise, British English, cite sources)

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. List my recurring work streams.
2. Propose a project/space per work stream.
3. Write custom instructions (about me + how to respond) under the tool’s character limits.
4. List reference files to upload per project.
5. Define naming and archiving rules.
6. Write a short weekly maintenance routine.

## Deliver the output in this structure
- Workspace map
- Custom instructions (copy-ready)
- Reference-file checklist
- Naming rules
- Maintenance routine

## Quality rules
- Never put passwords, keys or sensitive personal data into instructions or files.
- 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

InputPlaceholderExample
Your role and work[YOUR_ROLE_AND_WORK]founder running marketing and product
AI tools you use[AI_TOOLS_YOU_USE]ChatGPT, Claude
Recurring tasks[RECURRING_TASKS]reports, emails, research
Preferences[PREFERENCES]concise, British English, cite sources

Use it when

  • You use AI daily but re-explain context every time.
  • Setting up AI for a team.

What you get

  • Workspace map
  • Custom instructions (copy-ready)
  • Reference-file checklist
  • Naming rules
  • Maintenance routine

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

  1. 1

    List my recurring work streams.

  2. 2

    Propose a project/space per work stream.

  3. 3

    Write custom instructions (about me + how to respond) under the tool’s character limits.

  4. 4

    List reference files to upload per project.

  5. 5

    Define naming and archiving rules.

  6. 6

    Write a short weekly maintenance routine.

Quality checks built into the prompt

  • • Never put passwords, keys or sensitive personal data into instructions or files.
  • • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence for this method

This method runs on your own material: your files, brief or code. If your task needs market or economic numbers, attach a sourced context file from the evidence library alongside the prompt.

Browse evidence

Run next

Methods that chain well after this one.

AI Setup & ProductivityWrite an instruction file for AI agents (CLAUDE.md / AGENTS.md)A project instruction file telling coding or research agents what the project is, how to work and what not to do.AI Setup & ProductivityBuild an AI context file for any topicA reusable markdown context file with facts, definitions, sources and rules the AI must follow.AI Setup & ProductivityOrganise your files and foldersA folder structure, naming convention and archiving rules for your work, plus a migration plan.AI Setup & ProductivityBuild a custom GPT, Gem or Claude SkillA custom assistant spec: purpose, instructions, knowledge files, conversation starters and test cases.

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.