# The LLM Council
Stop Your Yes-Man AI and Build a Board of Advisors That Argues Before It Agrees

- Price: $12.99 (Kindle ebook)
- Level: Advanced
- Pages: 196
- Best for: Anyone whose AI agrees with everything they say
- You finish with: Five advisors that answer independently, peer-review anonymously, and return one verdict with the dissent named
- Series: The Zero-Human Team, book 2 of 3
- Buy on Amazon: https://amzn.to/4ohkST9
- Web page: https://youcanbuildthings.com/books/llm-council

## What you get

Your AI tells you what you want to hear, then builds a flawless case on a cracked premise. Build the council that argues before it agrees: five independent advisors, anonymous peer review, one verdict you can trust. The complete system Karpathy sketched and nobody finished, as Claude Code skills you run this weekend.

Your AI takes your premise as ground truth and builds an elegant case on top of it. If the premise is cracked, you do not get pushback, you get a flawless tower on a broken floor. The fix is not a sharper prompt. It is a council: a panel of AI advisors that attack the question from five angles, peer-review each other anonymously, and hand back one verdict with the dissent shown. This is the complete council system Andrej Karpathy sketched and nobody finished, built as Claude Code skills you run this weekend. Nearly 200 pages, and every build chapter ships a council that actually runs.

## Chapters

1. The Yes-Man Tax: The silent cost of running every important decision past one agreeable model, and the turn toward a council.
2. What a Council Actually Is: The four-box flow: independent answers, anonymous peer review, and a chairman that returns one verdict.
3. Why One Model Lies to You: The three ways a single model leads you wrong (hallucination, sycophancy, bias) and which a council fixes.
4. Build Your First Council This Weekend: A working five-advisor /council Claude Code skill, one command, no two-terminal setup.
5. The Chairman: From Five Opinions to One Verdict: The anonymous ranking and the chairman that turns five opinions into one verdict with the dissent named.
6. Design Your Own Council: A parameterized template and an archetype library so you convene the right council for any decision.
7. The Multi-Model Council: Route GPT, Claude, Gemini, and Grok through OpenRouter so no single vendor's blind spot decides the verdict.
8. The Code-Review Council: A /review-council where Codex, Claude, and Gemini argue over your diff and block on any real bug.
9. Your AI Board of Advisors: A standing /board for pricing, hiring, and go/no-go calls where a yes-man is most expensive.
10. The Verification Council: A /verify council that fact-gates a claim and reports SUPPORTED, CONTRADICTED, or an honest UNVERIFIABLE.
11. Is It Just 5x Slower?: The honest cost reckoning, parallel execution, and the guardrail against a council faking consensus.
12. Your Council Operating System: Tie every council into one operating system with a one-line guide for which to convene when.

## Free guides from this book

- [AI Code Review with a Multi-Model Council](https://youcanbuildthings.com/articles/ai-code-review-council.md): Make Codex, Claude, and Gemini argue over your diff and block on any single real bug. Build a multi-model AI code review council that catches what one misses.
- [Build a Multi-Model AI Council with OpenRouter](https://youcanbuildthings.com/articles/multi-model-ai-council-openrouter.md): Route one question to GPT, Claude, Gemini, and Grok through OpenRouter so no single vendor's blind spot decides your answer. The multi-model council build.
- [Build an AI Board of Advisors That Argues Back](https://youcanbuildthings.com/articles/ai-board-of-advisors.md): Stop making pricing and hiring calls with a yes-man AI. Build an AI board of advisors: four roles that pressure-test the decision and return one honest verdict.
- [How to Build an LLM Council in Claude Code](https://youcanbuildthings.com/articles/build-llm-council-claude-code.md): Build a five-advisor LLM council as a Claude Code skill that runs five independent AI advisors on one decision, in one command, with no two-terminal setup.
- [How to Verify AI Claims with a Council](https://youcanbuildthings.com/articles/verify-ai-claims-council.md): Fact-gate a claim with a four-check AI council that returns SUPPORTED, CONTRADICTED, or an honest UNVERIFIABLE. How to verify AI claims instead of trusting one.