Stop Writing Tone Instructions. Layer Them. - Isadora Martin-Dye, Isadora & Co
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
If your LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →'s persona drifts or collapses over long sessions, this breaks voice control into four distinct layers—identity, mode, examples, and a deterministic post-generation veto—so you know which mechanism to fix instead of piling more instructions into one prompt.
Key quotes
“I'm not programming a robot, I'm managing a brilliant intern with an incredibly high IQ and a terrible EQ.”
Isadora Martin-Dye
“They will say something technically perfect and socially catastrophic in the same confident sentence.”
Isadora Martin-Dye
“Instructions are probabilistic. Permission is deterministic.”
Isadora Martin-Dye
“In a multi-tenant system, identity must never have a default. A missing brand identity is a crash, not a fallback.”
Isadora Martin-Dye
“users aren't testing your brand voice, they are trusting it”
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
