The method

What is the Council Method?

The Council Method, also called the Council Methodology, is a way of working with AI created by Jason Santiago and taught in his book Let the AI Be Smart. Instead of asking one AI model and trusting the answer, you put the same question to several different models. Each model investigates independently, without seeing the others. Every claim has to name its source before it counts, because agreement is not verification. Only what survives that cross-examination gets synthesized into a final answer a human signs. The method solves a specific problem: a single AI model gives you a confident answer whether it is right or wrong, and on real work, confident and wrong gets expensive.

Why one model is never enough

A single AI response is one witness's account. It may be excellent. It may be wrong. It will sound the same either way, because fluency is what these systems are best at. The book puts it plainly:

One response is not a verdict. It is testimony.

Let the AI Be Smart

You would never convict on one witness in a matter that counted. The Council Method applies that standard to AI answers that matter: business decisions, technical choices, anything you will have to stand behind later.

Why independent investigation comes first

In a Council run, every model answers blind, before seeing any other answer. This is not a detail. If models see each other's answers first, the first confident voice anchors the room, and you get an echo instead of an investigation. Independence first, conversation second.

Then you read the results by where the disagreements cluster. Divergence is not a nuisance. It is the signal. Where the models fork is exactly where the real question lives.

Why agreement is not verification

Consensus is cheap. Four models agreeing costs you nothing and proves you nothing.

Let the AI Be Smart, Chapter 8

Models trained on similar data can be wrong together. So the method demands provenance before consensus: every claim must name where it came from, and every claim must survive an attempt to kill it, before it earns a place in the final answer. Claims that cannot name a source get demoted. They can never sneak into the verdict dressed as facts.

The verdict stays human

The end of a Council run is not an average of the answers. It is a decision: what everyone established, what only some did, what remains unresolved and gets carried forward on the record. And a person signs it. The machine can make the answer survivable. Only you can make it yours.

Where it came from

Jason Santiago developed the method on production work, not in a lab. As a commercial construction superintendent, wrong answers carry schedule, money, and safety costs, and a confident guess is the most dangerous kind. The turning point was a real build where one model confidently invented a software component and could not see its own error, and a second model spotted it instantly. The lesson generalized: stop asking one machine to be right, and start building a room where being right has to survive the room.

In practice

A Council run has a simple shape. You brief several models with the same real context. Each investigates independently. You collect the answers, force every load-bearing claim to name its source, and press on the disagreements until they resolve or get recorded as open. Then you synthesize a verdict and sign it. The full protocol, including how to run it with one model, three, or five, is taught in the book and available as a free tool: the Council Protocol.

The Council Method was developed by Jason Santiago and is taught in full in Let the AI Be Smart.