TALAMANA · THE AI LITERACY MAP FOR ARCHITECTURE AND DESIGN · The Brief · AGE 16—18 · POSITIONAL · METHOD

Decode the messy brief

Find the project inside the brief, and decide which contradiction is the design problem.

When to use

When a client's brief arrives long, messy and contradictory — a two-page email, a WhatsApp thread, a Pinterest board and a feeling — and before you generate anything from it.

The method

Read the whole brief once without taking notes. Then pull out, in this order: the intent (what the project is for, in one sentence); the user groups; the spatial priorities; the mood words the client used; the information that is missing; the contradictions ("open and airy" beside "privacy from the road"); and the questions to ask the client before concept work. A model can do this first sorting pass quickly: give it the brief and the list. Your job is the second pass. Find the project inside the structure, rank the drivers, and decide which contradiction is the design problem rather than a mistake.

Watch for this

Summarising instead of decoding. A summary repeats the client's words in fewer words. A decode finds the five things the project actually turns on, and two of them are usually things the client never wrote.

The Lab's note

The order above — read once, then intent, users, priorities, mood, gaps, contradictions, questions — is the Lab's way of decoding a brief, refined in teaching. The profession calls the discipline architectural programming and has other sequences for it. Ours is the one where, when a decode misses the project, we can point to the step that was skipped.

Try it

Take a real two-page client email, or the sample brief your studio uses. Reduce it to five design drivers in priority order. Then list every pair of stated wants that conflict, and for each pair propose the resolution the brief itself points to.

Prove it

Given a messy brief, show that you found the project inside it — the ranked drivers and the governing contradiction — and not only a tidier version of the text.

How it works

This is architectural programming, Peña's problem seeking, as it has been practised since 1969 — now with a machine doing the first sorting pass. The model is good at sorting text into named fields and at noticing contradictions you read past. It is poor at knowing which contradiction matters, because that depends on a site, a client and a budget it has never met. The generate-the-brief card on this map runs the same skill in the other direction.

What this idea builds on

What this idea opens up

Sources

Open this idea on the map · The complete map · Logika · RBDS AI Lab, India · revised every edition.

Age grows from 11 at the centre to 22 at the edge, and six sectors show the learning strands. Tab into the map and the arrow keys step from idea to idea, following the links where there is one. Enter opens the idea under the cursor, and E reads out its links and the reason recorded on each. Press slash for Search, question mark for the full key list, and Escape to leave. Open Ideas for the complete readable list, including what each idea builds on and what it opens up.

LOGIKA · RBDS AI LAB INDIA
ON-RAMP · AGE 11 · FIRST ENCOUNTERS, NOT GATES — IDEAS · — DEPENDENCIES
DONE
OPENS NEXT
SOLID — STANDS ON