PACT is a research tool that makes AI reasoning permanent, addressable, and reproducible. Not a chat. A structured notebook where every prompt and response becomes a citable, chainable artifact.
Every AI chat response is ephemeral — when the conversation ends, the reasoning is gone. PACT treats each response as a permanent, addressable cell stored in a local database.
Chain cells across discussions using cell references. Each step receives the full prior response as context — not a summary. Build analyses that would be impossible in a single prompt.
Built as a VSCode extension with local SQLite storage — your research stays on your machine.
Every prompt and response is saved permanently. Restart PACT and your research is exactly where you left it.
Reference any prior response in any new prompt — across discussions, across notebooks. Full context, not summaries.
Each notebook has an optional system prompt. Set the AI's role once — it applies to every discussion silently.
Export any notebook as a formatted PDF. Share research with physicians, colleagues, or anyone — no PACT required.
Compare two responses side by side with sentence-level highlighting. See exactly how models differ.
Export as .pact files. Other researchers import and continue exactly where you left off.
From the first prototype to real medical research using progressive chaining.
Introducing PACT — why treating AI responses as permanent, addressable cells changes everything about research.
The architecture behind notebooks, discussions, cells, and the SQLite reasoning ledger.
Five progressive prompts, cross-discussion cell references, and an 84-page clinical analysis exportable for a physician visit.
Observations and updates from building and using PACT — less formal than a Medium article, more considered than a tweet.
View all posts →PACT is in active development. Beta access is available for researchers, physicians, and domain experts who want to shape how structured AI research works.
Or email directly: nikolaj.ivancic@gmail.com