TL;DR
AI forgets, cannot see what lives in your notes and calls, and answers with full confidence anyway.
The fix is a Second Brain: plain files, one record per project and one per client, that every tool and person reads before work starts. The free Second Brain Starter is where to begin.
I write Code Meet AI, the newsletter where I document how I actually use AI to ship real products, receipts included. New guides land there first.
I use a Second Brain every day: plain files that Claude Code and my other AI tools read before they start work. Counted on 22 October 2026, it holds 645 memory files, 119 skills, 41 commands and 640 session reports. This is why I have one, and why I think you should too: six places AI goes wrong across projects, and the file that fixes each.
AI started as prompting. You typed a question, it typed back, and the whole skill was in how you asked.
Then it became context engineering. Same model, but now you decide what it reads before it answers: your files, your rules, your examples.
Then came tools. With MCP the model stopped only talking. It could open your inbox, read your calendar, run a command, and react to what came back.
That is a good place to be. AI is better than it has ever been, and every week a new tool does something that looked impossible last year.
So why does it still go wrong when you have more than one project?
One thing did not come with the upgrade: a place where the project lives. The model can read whatever you point it at, but it does not know what to point at. With three or four projects it forgets what you told it last week, it cannot find the file that holds the answer, and it fills the gap with something that sounds right.
The AI forgets too
When a team forgets why a project works the way it does, we call it a communication problem. With AI the same thing happens in three ways.
It forgets. Every new chat starts from zero, so last week's work is gone.
It has no access. The answer sits in a note, a call or someone's head, and the model never sees it.
It is confident anyway. This is the one that hurts.
A person who does not know says "I do not know". The AI says the wrong thing in the same calm voice it uses when it is right. You read a clean answer, you think it is 100% true, and you have no way to check. Worse, the wrong part goes into the chat and becomes context, so the next answer builds on it. One dumb thing, said once, gets repeated as if it was settled.
You explain the same project again and again
Say it is Monday. You open a chat to get help with your app, and you spend twenty minutes saying what the product is, who it is for, what you built last week and what must be left alone. The answers are good.
On Wednesday you switch to another tool for another job, and it knows nothing. You type the whole thing again from memory, and the detail that mattered most, the one that would have stopped the bug, is the one you forget.
The easy fix is one project record. A single file at the root of the project that says what it is, who it is for, the current state and the next action. Every tool reads it before it does anything. You write the explanation once, and each chat starts where the last one stopped.
Decisions get made and then vanish
Suppose you decide to use A instead of B. A is the payment provider with the fees you can live with, and B is the one your partner liked. You agree on a call, you hang up, and nobody writes it down.
Three weeks later the AI suggests B, politely, with good reasons. Your partner says "see?", and you spend an hour on a decision you already made.
So keep a decision file. One line per decision: what you chose, what you turned down, why, who decided and the date. Write it right after the call, in the file the next session reads.
The reason is the part people drop first, and it is the part that stops the argument from coming back.
The AI reopens what you already settled
Take the other side. You did write the decision down, in a notes app, in a doc, in a chat from last month. The AI never saw it, so it treats the question as open and argues for B again.
Writing it down is half the job. The other half is telling the model it is settled. Keep a short list of closed decisions inside the project record, each with its reason, in the part that is read first. A decision with a reason attached is much harder to reopen by accident.
Context leaves with the person
This version costs money. Take one client account. The account lead knows the client was promised a faster turnaround last spring. They know the client said no to one format, and that approvals go through one person on Fridays. None of it is in the CRM, which keeps deal values, dates and activity but has no field for the promise or the reason behind it.
Then the account lead goes on holiday, or leaves. The next person meets the client without the history, and the AI helps them no more than it helps anyone else, because it cannot read what was never written.
The fix is one client record per account. It holds the brief, the dated decisions with reasons, what the client said no to, the promises made and the next action. Whoever covers the account, person or AI, reads it first. The record outlives the person.
Each tool keeps its own copy, and the copies drift
Claude, Cursor, Codex and Gemini each want their own rules file. You change a rule in one of them on Tuesday. A month later two of the four disagree, and the AI follows the old one without telling you.
Keep one rules file as the source. Give each tool a one-line file that points to it, and link one shared skills folder into each tool's own path. The copies stop existing, so they cannot drift.
Files go stale, and the AI trusts them
Last month you moved the project from Firebase to Supabase. The record still says Firebase. The AI reads it, writes for the old database with full confidence, and the result breaks in a way that looks like a bug in your own work.
A wrong file is worse than no file, because nobody doubts it. Put a last-checked date on each section, and check the record whenever the project changes: you swap a tool, a client leaves, a decision is reversed. A rule that a script can test becomes a hook, which runs at a fixed point whether the model agrees or not. A rule that needs judgement stays in the record, as a request.
What a Second Brain is, in one sentence
A Second Brain is a set of plain files, one record per project and one per client, that every AI tool and every person reads before work starts, and that gets written back after each decision. It is a folder with a discipline attached.
The layout follows ICM, the Interpretable Context Methodology: a small routing file points the AI to the one file it needs, so it does not have to load everything.
This is mine, drawn as a graph. Every dot is a note, and the lines are the links between them. When the AI starts a session, this is what it can walk through instead of starting from zero.
What to do this week
Count the repeats. For five working days, note each time you explain the same thing to an AI tool, and which tool it was. The count tells you which record to build first.
Write the decision line. After each call or chat where something gets decided, add one dated line to the project file: the decision, the reason, the owner.
Run the leave test on one account. Pick one client. Ask whether the next person could open one file and find the promises, the no's and the next action. If not, that file is your first client record.
A plain Markdown starting point for all of it is in the free Second Brain Starter. For how to sort the folders once you have a few records, see how to organise your files for AI, Episode 11 of Using AI, properly.
This one came from Code Meet AI, the newsletter where I write up the setups I actually run on my own projects.
Top comments (0)