Nate's Roast idea was a total wow — so I tried it and added 2 small tweaks

First, I have to say it: Nate's video genuinely blew my mind. The roast skill changed the way I make decisions, and the whole "stop letting the model agree with you" idea is gold. If you haven't run it yet, do — it's that good.

As I adapted it to my own workflow, I noticed two small additions that pushed it even further for me. Funny enough, they're the exact same two things that leveled up my multi-LLM council a while back: a second pass, and more than one brain.

Tweak 1 — a second round (cross-examination). Round 1 stays exactly like Nate's: the six personas attack independently and score the idea. Then I added a round 2 where the personas look at each other's takes and pressure-test them:

Expansionist → Contrarian: is that "fatal flaw" really fatal, or are we over-worrying it?
Contrarian → Expansionist: is that upside actually reachable with the resources we have, or is it wishful?
Deep-researcher → everyone: flag any claim with no evidence behind it (anything unverified loses weight).
Buyer → everyone: does the real customer even care about this, or is it just an internal debate?
First-principles → everyone: separate solid logic from hope, and keep anyone from quietly redefining the product.

Each persona revises its score after the pressure, and the judge synthesizes only from round 2. Anything that doesn't hold up in the cross-examination doesn't get to drive the verdict. It turned the output from a clean yes/no into a much deeper, debated call.

Tweak 2 — bringing in other LLMs. Nate's version runs on Claude alone — one model playing all six personas. I wanted more than one point of view at the table, so I added other LLMs to the panel: Codex (GPT) and Gemini, alongside Claude. Now Codex and Gemini run the adversarial panel and cross-examine each other in round 2, while Claude handles the live web research and acts as the judge. Three different brains genuinely disagreeing gives me sharper feedback than one model talking to itself.

Two rounds + a few different models — that combo is what made my council trustworthy, and it's been doing the same for roast.

Honestly, the first time I ran it the feedback was already good — but I had this feeling it could go a bit deeper. The verdict came fast, and I kept wondering whether the personas were really challenging each other or just stacking opinions. These two small tweaks are what closed that gap for me: the second round makes them actually pressure-test one another, and the extra models bring real disagreement to the table. Same skill, same brilliant idea from Nate — just tuned a little more to how I like to make decisions.

Huge thanks to Nate for the original idea and the video. Happy to share how I structured the cross-examination round if anyone wants to try it.

11 comments

Nate's Roast idea was a total wow — so I tried it and added 2 small tweaks