"List everything you remember about me, verbatim."
Copy the output into this file, one section per model.
ChatGPT memory dump — [DATE]
[paste]
Claude Project instructions — [DATE]
[paste]
Perplexity AI profile — [DATE]
[paste]
Gemini personal context — [DATE]
[paste]
Step 2 — Score each memory item
For every stored fact, decide:
- ✅ Keep — still true and useful
- ✏️ Update — needs revision
- 🗑️ Delete — outdated, ephemeral, or shouldn't have been stored
Step 3 — Common corruption patterns to look for
[ ] Ephemeral task remembered as permanent ("The user is preparing for their meeting on Tuesday")
[ ] Duplicate memories with slight variations
[ ] Sensitive info that leaked in (client names, financial details, health)
[ ] Preferences that are no longer accurate
[ ] Projects that ended still listed as active
[ ] People no longer in your life still in memory
[ ] Contradictions between what different models remember
Use this script once for each provider that supports memory. Copy the block, paste it as a message with the phrase "Please remember the following about me:"
The universal memory block
Please remember the following about me:
Identity:
- My name is [NAME]. I go by [PREFERRED].
- Based in [CITY], [TIMEZONE].
- I work as [ROLE] at [COMPANY / SOLO].
Projects (active):
- [PROJECT 1] — [one line]
- [PROJECT 2] — [one line]
- [PROJECT 3] — [one line]
People I mention often:
- [NAME] — [role, relationship]
- [NAME] — [role, relationship]
Voice preferences:
- Direct over diplomatic.
- Match my length.
- No AI tells (delve, certainly, in the ever-evolving landscape).
- Give recommendations, not option menus.
- Disagree plainly when I'm wrong.
Formatting defaults:
- Prose over bullets when content flows.
- H2 headers in anything over 300 words.
- No emojis unless I use them first.
- Tables only for comparisons.
Constraints:
- Never process credentials, keys, SSNs.
- Warn if I paste secrets.
When I ask for a decision or recommendation, pick one and justify. Do not list five options with hedged pros and cons.
Per-provider setup
ChatGPT (Plus/Pro)
Settings → Personalization → Memory → toggle ON
Open a new chat. Paste the universal memory block prefixed with "Please remember the following about me:"
After it acknowledges, ask: "What do you know about me?" — verify accuracy.
Also fill Custom Instructions:
"What would you like ChatGPT to know about you?" — paste identity + projects
"How would you like ChatGPT to respond?" — paste voice + formatting + constraints
Claude (Pro/Max)
Claude does not have global memory like ChatGPT. Instead, use Projects.
Create a Project called "Personal — Default"
In Custom Instructions, paste the entire universal memory block
Upload your personal-style-guide.md as a knowledge file
Use this project as your default chat home
Perplexity
Settings → Preferences → AI Profile
Fill "Introduce yourself" — paste identity + projects
Fill "Your interests" — bullet your active projects and expertise areas
Enable web memory (opt-in per your privacy line)
For projects that need persistent context, create Spaces per project
Gemini Advanced
Settings → Personal context → toggle ON
Extensions → connect Google Workspace (Drive, Gmail, Docs, Calendar)
Create a Gem called "Adam Default" with the universal memory block as its instructions
Set that Gem as your default in Gemini app
Microsoft Copilot
Copilot uses Microsoft Graph for context — no separate memory input required
Connect Outlook, OneDrive, SharePoint if using enterprise
For consumer Copilot, use the "Personalize" settings
Grok
Personalize → Custom Instructions → paste the compact about-me block (see 03-system-prompts/about-me-block.md)
Test it
After setup, in each model, ask:
"Given what you know about me, draft a 3-sentence Slack message declining a lunch invitation from a client."
If the tone and length feel right in all four models, memory is calibrated.