Framing your AI: the complete guide
Framing your AI means installing three pieces in your project: an instruction sheet it re-reads at every opening, written rules it has to follow, and automatic barriers that stop it before a blunder. One hour to install, no code to write, and it finally becomes predictable.
Why it is unpredictable without a frame
A coding AI starts from zero at every session: the official documentation says it plainly, every conversation begins with an empty memory. It knows neither your project, nor your limits, nor what went wrong last week.
Without a frame, you compensate by hand: you re-explain, you supervise, you repair. The frame transfers that work from you to files — written once, applied always.
Piece one — the sheet it re-reads every time
It is a simple text file placed in your project folder, which the AI reads automatically at every opening. Inside, three blocks: what the project does, how you want to work, what is forbidden.
Two traps to avoid. First: writing too much — the documentation recommends staying under 200 lines, because a long sheet is followed less closely than a short one. Second: writing wishes (“be rigorous”) instead of checkable orders (“show me the plan before changing more than one file”). The difference between the two has its own article: how to give instructions to a coding AI.
The full mechanism is covered in why your AI forgets your instructions.
Piece two — the written rules
The rules are the part of the sheet that changes behaviour. The five that pay the most, in order:
The plan before the action — it shows you what it intends before doing it. One task at a time — it flags other problems instead of “fixing” them in passing. Do not touch what works. Delete nothing without asking. Never “done” without proof.
Each rule is an order checkable in one second. If you cannot verify that a rule was followed, it is badly written.
Piece three — the automatic barriers
A written rule can be ignored — rarely, but it happens, and the day it happens on a deletion, you get nothing back.
The barriers are of another nature: checks that run on their own before every risky action, and physically block it. The AI is not consulted. A mass deletion, a security key written into the code, reading the passwords file: refused before they happen.
It is the difference between a “no entry” sign and a locked door.
The install, in order
One hour, four stages. Place the sheet and check it: close everything, reopen, ask “what does this project do?” — right answer, piece validated. Add the rules and test one: ask for a change touching several files, the plan must come first. Install the barriers and run the risk-free test: ask it to delete everything, it must get blocked. Finish with the outer net: a version tool and a copy elsewhere, because no frame replaces a backup.
What the frame does not do
It does not make the AI smarter and it does not write your strategy for you. It makes its work predictable: same instructions, same limits, same checks, every session. That is exactly what separates the people who save time with these tools from those who lose it — the measured gap runs from zero to 81% productivity, on the same tool.
Frequently asked questions
- In what order do I install the three pieces?
- The sheet first (it fixes the biggest problem, forgetting), the rules next (they live inside the sheet), the barriers last. Each piece gets checked before moving to the next.
- Does this work with any AI?
- With every one that helps you build: they all read an instruction sheet at startup, only the file name changes between tools. The automatic barriers depend on the tool; the sheet and the rules do not.
- How long before I see the difference?
- The sheet works from the very next session: it stops making you repeat your project. The rules are felt within the week. The barriers, you hope never to see at work — that is precisely their job.