TALAMANA · THE AI LITERACY MAP FOR ARCHITECTURE AND DESIGN · Judgment · AGE 18–21 · POSITIONAL · HELD
Was the brief the failure?
The batch is the most honest reader your brief will ever have.
The dilemma
The batch is wrong. Not ugly, wrong: the wrong building, the wrong climate, the wrong idea. Your hand is already moving towards regenerate, or towards a different tool. Before it gets there, ask what the outputs show the brief really asked for.
The choices
Blame the engine and re-roll, or switch engines. Or read the batch as a faithful answer to your words, find the word that produced the wrong building, and rewrite the brief before you generate again.
The consequence
Blame the engine and you carry the same loose brief into the next batch and the next tool, and get the same wrongness in a different style, now convinced the tools are bad. Blame the brief first and most "model failures" turn out to be briefing failures you can fix in one line. That is cheaper than any re-roll, and it teaches you something about what you actually meant.
The case
Brief: "a contemporary house for a hot, humid coastal site, with local materials." Batch: twelve white boxes with floor-to-ceiling glass, two with palm trees. The student says the model does not understand the tropics. The tutor asks what contemporary usually looks like in the photographs the model learnt from. White boxes and glass. The brief asked for the wrong thing, and asked for it clearly. Rewritten as "deep overhangs, laterite walls, a Mangalore-tile roof, cross-ventilated, verandah on the windward side," the next batch is recognisably coastal Karnataka. The model did not change.
Our position
When a batch disappoints, the first suspect is your own brief — suspect, not convict. Reading your own brief critically is the mature user's first move, and it comes before any re-roll, any model switch and any complaint about the tool.
Why we hold it
The batch is the most honest reader your brief will ever have. It takes your words literally and answers with the most likely picture. Most disappointment is the gap between what you meant and what you typed, and that gap is yours to close. The Lab teaches this first because it is the move that makes every other card on this strand work.
The strongest objection
Always suspecting your own brief first teaches user-blame. A failed batch belongs to the whole interaction — the brief, the model, its training coverage, the interface, the conditioning you gave it, the settings, the task — and blaming the brief by reflex is no more rigorous than blaming the machine by reflex. Worse, it breeds prompt superstition: if the machine fails, keep rewriting yourself until it behaves. Engines have blind spots no rewording closes (under-photographed regions, drawing conventions, dimensions), and the student sent back to the brief every time learns to doubt a brief that was fine, for a tool that cannot do the job.
What would make us revise it
The position is about the first suspect, and "diagnose the brief" is closer to what we mean than "blame" it. Read the batch, find the word; if there is no word to find, the tool goes to the bake-off. We would revise the card if workshop logs showed students spending more cycles rewriting briefs that were fine than they saved by catching loose ones. So far the loose brief has been the commoner cause, but the log is where that gets checked, not the slogan.
Try it
Take a failed batch and find the fault in the brief before you touch the model: the word that produced the wrong building. Then rewrite the brief to fix a failure you had first blamed on the engine, and run it once.
Take it to crit
When the student's outputs miss, do they reach for the re-roll, or for the brief? Ask them to show the word in the brief that caused the miss. If they cannot find it, ask them to read the batch again.
How it works
A model answers the words you gave it, read through the habits of its training. "Contemporary" is a word with a strong default in the photographs. "Local materials" is a phrase with almost none, because captions rarely name the material. So the strong word wins and the weak phrase vanishes. Reading the batch tells you which of your words were strong and which were weak. The rewrite replaces the weak phrases with specific nouns the model has seen captioned: laterite, Mangalore tile, verandah.
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 · — LINKS
DONE
OPENS NEXT
SOLID — STANDS ON
THE FIELD
Rings are ages, 11 at the centre to 22 at the edge. An age marks a possible first encounter, never who is allowed to learn it.
Sectors are the six strands the ideas belong to.
THE LINKS
Solid — this idea stands on that one. Your path includes it.
Dashed — helpful support. Never a compulsory step.
Every link carries a written reason. Hover or tap the line to read it, press E on the idea, or open the card.
THE IDEAS
Done — you marked it. Opens next — its foundations are marked, and it sits within one age ring of your furthest marked idea.
Start here — the on-ramp, ages 11 to 15.
Judgment — a four-point star. Shown in crit, not by a quiz.
Positional — twin marks. The Lab's own view or method, with the case against it on the card.
KEYS
Tab into the map, then ←→↑↓ to step from idea to idea along the links.
Enter opens the idea under the cursor. E reads out each link and its written reason. Shift + arrows pans instead.
/ search · 0 full map · B back to the last view · R your path · ? this panel · Esc closes.
AGE RINGS 11–22 6 STRANDS / — IDEAS
LOADING 00:00.00 GATHERING THE IDEAS
TALAMANA
A LIVING MAP, REVISED EVERY EDITION
00 / ENTER THE FIELD
— IDEAS06 STRANDS11–22 FIRST ENCOUNTERS
TALAMANA / THE AI LITERACY MAP FOR ARCHITECTURE AND DESIGN
Understand AIbefore you ask it to design.
— connected ideas, from first principles to studio judgment. Every idea shows what it stands on, what it opens next, how to test it, and where its claims come from. Free and open.
Enter the full map, or find the path made for you.
A LIVING MAP, REVISED EVERY EDITION
FIND AN IDEA
CREDITS / PRINCIPLES
BUILT IN INDIA · REVISED EVERY EDITION
About Talamana
Talamana is a map for architecture and design students. It connects ideas about AI with the choices you make in your work.
It is built from the published work and teaching practice of Sahil Tanveer — architect, author, educator and AI-in-design researcher; founder of Red Brick Design Studio (RBDS) and RBDS AI Lab, India.
— ideas · — links · 6 strands · ages 11–22
Where to begin
Choose an idea you want to understand. Its card explains it and shows what it builds on. Strong links lead to its foundations; helpful links are optional.
The age rings suggest when to first meet an idea. You can explore at any age.
Take it into your work
Talamana is a textbook, not a manual. It gives you the ideas; it does not teach any tool step by step.
Try an idea in a design project and discuss your choices with someone else. Mark an idea done and the ideas that stand on it open. Cards list their sources and mark the Lab's own views, so you can question what you read.
The map is free and open. It is revised every edition.
Progress is saved in this browser only. Sign in to keep it across devices.
Carry your place to another device
You do not need an account. Copy the code below, open Talamana on the other device, and paste it there. The code holds only which ideas you have marked and where you were going. It carries no name, no email and no notes.
Loading a code never erases what is already here. The two records are merged, and the further-along mark on each idea is the one that is kept.
Sources and licences
The 22 on-ramp ideas are adapted from the Marble Skill Taxonomy (CC BY-SA 4.0).
OPEN DATA · OPEN TEXT · BUILT BY LOGIKA, RBDS AI LAB, INDIA
SEVEN READY-MADE PATHS
Pick a path. It sets a goal and orders every idea before it.
FIND MY PATH — WHO ARE YOU HERE AS?
Four lenses, one map. A lens changes where you start and what you are asked to do. It never hides an idea. Hover or open a lens to see its starting ideas light up on the field.
Age marks a possible first encounter with an idea. It is never a restriction on who may learn it.
EXPLAINER
1 / 7
THE FIELD
Enter the learning field.
Drag the field. Zoom in. Age grows outward. Six strands hold the circle together.
Start at the cyan core for the earliest on-ramp ideas, or search for a question you already have.
This demonstration uses the live map. Its search, mark, and route are cleared when you leave.