Last reviewed:
What is the map-and-territory principle in AI?
The map is not the territory. What you give an AI — prompt, files, context — is only a representation of the work. The real work happens elsewhere: in the code, the file, the constraints of the ground. The gap between the two is your unknowns. That is where, and almost only where, a mission derails.
The quality of an AI-assisted mission is capped by your ability to clarify its unknowns — not by the power of the model.
01Origin
The phrase belongs to Alfred Korzybski's general semantics: a map can be useful, detailed, beautiful — and still be wrong about the ground it describes. A subway map is not the subway.
Engineer Thariq Shihipar (Claude Code team, Anthropic) brought it back to work with recent models. His observation: the more capable a model becomes, the more the limiting factor shifts from the model to the human. An agent doesn't act on the territory, it acts on the map. Wherever the map is silent, the agent decides on its best guess of your intent — often plausibly, rarely rightly.
02The four unknowns
Before launching a task, place it in these four boxes. Each calls for a different strategy. The grid follows the logic of the Johari window.
| What you know | What you don't know | |
|---|---|---|
| Aware | Known knownswhat you write in the prompt. The foundation, rarely enough on its own. | Known unknownswhat you know you haven't decided yet. |
| Unaware | Unknown knownsthe implicit: obvious to you, never written, recognised the moment you see it. | Unknown unknownswhat you don't know you don't know. This is where missions derail in silence. |
03Why it matters
With a capable model, getting a result is no longer the problem. Getting the right result is. A model produces convincing output even when it misread your intent, which makes the error costly: you find out late.
There are two ways to use AI. Ask it for an answer to copy. Or ask it to help you see what you couldn't. The first erodes your autonomy over time; the second strengthens it.
04The method, in three phases
Before — frame and reveal
Blind-spot pass to hunt the unknown unknowns, reverse interview (one question at a time), concrete references rather than descriptions, a risk-sorted plan with your decisions up top.
During — hold the course
A living decision log, a written hypothesis before each step, a restatement requested before any execution.
After — verify and harden
A quiz on the result, pitching the choices as if to a decision-maker, an explicitly non-complacent review.
A long task almost always fails for one of two reasons: not enough time spent clarifying the unknowns, or a plan with no margin to adjust when the agent hits one.
FAQ
What is the map-and-territory principle applied to AI?
The map is what you give the AI: prompt, files, context. The territory is where the work actually happens: the codebase, the client file, the concrete constraints. The gap between the two is your unknowns, and that is where missions derail.
What are the four unknowns?
Known knowns (what you write), known unknowns (what you know you don't know), unknown knowns (the implicit, obvious but unwritten) and unknown unknowns (what you don't know you don't know). Each box calls for a different strategy.
Why isn't a good prompt enough?
With a very capable model, the bottleneck is no longer the model but your ability to clarify your unknowns. A prompt that is clear about the wrong assumptions produces a plausible but wrong result.
Does this only concern code?
No. Any mission delegated to an AI has its unknowns: audit, writing, strategy, translation. The grid applies wherever a gap exists between the instruction and the ground.
Do you need to be an expert in the subject to use it well?
No. The method is precisely about surfacing what you don't know. You can deliver in a domain you barely master if you reveal your unknowns instead of ignoring them.
How do you reveal your unknowns with AI?
Before executing: blind-spot pass, reverse interview, concrete references, a risk-sorted plan. During: a decision log and restatement. After: a quiz and a non-complacent review.
Get the guide as a PDF
The full method guide « map and territory »: 14 pages, the detailed step-by-step and a library of ready-to-copy prompts.
PDF · 14 pages · FR / EN / ES · delivered in under a minute
See also
Further reading
Thariq Shihipar — A Field Guide to Fable: Finding Your Unknowns (Anthropic)
Sources
- Thariq Shihipar — « A Field Guide to Fable: Finding Your Unknowns », équipe Claude Code, Anthropic, 2026. https://x.com/trq212/status/2073100352921215386
- Author's example prompts (GitHub Pages). https://thariqs.github.io/html-effectiveness/unknowns/
- Alfred Korzybski — Science and Sanity (sémantique générale), 1933. https://en.wikipedia.org/wiki/Alfred_Korzybski
- Fenêtre de Johari / Johari window. https://en.wikipedia.org/wiki/Johari_window