MECE — Mutually Exclusive, Collectively Exhaustive — is drilled into every consultant from day one. Structure your analysis into buckets that don't overlap and cover everything. Issue trees, frameworks, waterfall charts. It's how you solve complex problems at places like Bain & Company, and after years there, it's how I solve everything.
So when I started designing an AI memory system, my first instinct was predictable: build a beautiful MECE folder structure. Projects, Areas, Resources, Agents, Archive. Clean, exhaustive, non-overlapping. I was proud of it. It made perfect sense.
To me.
A few days in, I asked myself a question I should have asked before writing a single line of code: "How do I actually remember things?"
Not how I analyze them. How I remember them.
The answer wasn't "in MECE trees." It was "by association." I remember what's relevant because I use it often. I remember connections between topics, not their position in a hierarchy. My memory isn't a filing cabinet — it's a web of things that feel related.
And an LLM works exactly the same way. It doesn't care about your folder structure. It reads context, finds relevance, and responds.
"That's how I think — but not how I remember."
MECE is a thinking tool. Incredibly powerful for breaking down a problem. But it's a terrible memory tool. Forcing AI memory into MECE folders is like organizing your bookshelf by spine color — it looks organized but doesn't help you find anything faster.
I eliminated all hierarchical folders. A flat lake of documents with two simple categories: NEURONS (what I know) and ENABLERS (how things work). A compiler reads everything and produces a single optimized file.
A Bain alumnus abandoning MECE — the most sacred framework in consulting — to design a better system. The irony isn't lost on me. But the system works better because of it.
MECE is how you think. Memory doesn't work that way — not for humans, and not for AI. The sooner we stop organizing AI memory for human browsing, the sooner we'll build systems that actually work.
EIDARA is the open-source project that came from this realization. GitHub · Website