Memory and Context Bleed.
Why flat memory leaks. How scoped memory fixes it. How to audit what dequid knows about you.
Context Bleed.
Every “memory” feature in every AI product is the same thing: text prepended to your message before the model sees it. The model has no independent storage. It just reads what it's handed.
Products like ChatGPT, Claude, and Gemini collect everything they learn about you into one pool and hand it all to the model every time. That means a fact about your dating life can surface inside a CEO email. A casual thing you said about your health shows up in a customer pitch. The fact you mentioned you hate meetings shapes advice you asked for about your engineering architecture.
This is Context Bleed — the failure mode of flat memory. The model isn't misreading you; it's reading exactly what it was handed. The problem is in the architecture, not the model.
Three primitives.
Memory in dequid comes in three kinds. Each has its own surface in the Memory sheet.
All three land in the system prompt before your message — but only after persona scoping filters them.
Per-persona exclusion.
Fresh memory reaches every persona.
When a new memory is extracted, it lands in your global Memory pool and all your personas can see it. This is intentional: new things you say are probably relevant until you decide otherwise.
You decide what each persona can't see.
Open a persona → Memory tab. Tick any phrase, memory, or context block to exclude it from that persona. The memory stays in your pool — other personas still see it. This one doesn't.
The mental model: Memory is a shared library. Each persona has its own reading list from that library. Exclusion is just crossing a book off a persona's list — the book stays in the library.
How memory gets created.
Automatic extraction
Three seconds after a chat turn ends, a background job reads the last 20 messages and extracts 0–5 memorable facts about you. You'll see a badge in chat when new memories were saved. The model used is low-cost and fast; extraction never blocks your response.
Manual add (About You)
Open Memory → About You → "Add a phrase". Type whatever you want the model to know. Manually-added phrases are pinned — they survive automatic rebuilds and won't be overwritten.
Manual add (Context blocks)
Open Memory → Context → "Add block". Give it a title and write the body. "My tech stack", "Voice rules", "Current project". Use this for anything structured that you want the model to follow exactly.
Audit and edit.
Open the Memory sheet from the sidebar (brain icon under Library). Three things to look for:
- Wrong or stale facts in Memories. The extractor is good but not perfect. Delete anything incorrect — it's one click, no confirmation.
- Cross-domain facts in About You. If your phrases list has “preparing a board deck for Series B” and “gluten-free diet” side by side, ask whether every persona should know both. If not, open the persona that shouldn't know and exclude it.
- Context blocks that have drifted. “Current project” may no longer be current. Update it or delete it. Context blocks you toggle off globally don't reach any persona until you turn them back on.
The Inspect panel in chat shows you exactly which memories reached the model for a given message — open it and look at the Memory Prefix layer to verify what actually got through.
Web vs Mac
Same product, two data paths. Three lines to pick the right one.