We use analytics and advertising tools by default. You can update this anytime.
Manage optional tracking categories. Necessary cookies stay on so the site can function.
Author
Mike Taylor is the head of evals at Every and a co-author of "Prompt Engineering for Generative AI" (O’Reilly).
Its new model turns fuzzy questions into probabilities fast and cheaply enough to check an AI agent’s work as it goes
After years of self-employment, I went full-time at Every. Here’s why.
The case for keeping your AI on a need-to-know basis
How chain of thought works to get better responses
I tested 12 AI models on real human behavior—the best one costs less than a penny per 100 responses
The company gets pragmatic in AI’s expensive era
Here's what they said (and how you can ask them, too)
Repeat AI tasks with self-consistency sampling to get better results
The skills that make AI agents reliable are identical to the skills that make human teams effective
AI engineer and Every columnist Michael Taylor recently stopped by our New York office for a tutorial on how the prompt optimization tool works
Everyone hates making presentations. Too bad it’s so hard to automate them with AI.
Every's consulting team answers 400 executives on strategy, skeptics, governance, and restructuring for AI
Choose the best model for the work you do
Your leadership team already knows how to manage AI. They just don't know that yet.
A look inside Mike Taylor’s writing workflow—and the work he still does himself
A new tool that 'evolves' your prompts may be the next step in getting LLMs to do precisely what you want
Here’s what my AI simulated interview taught me about getting the most out of a conversation
You just have to survive the onboarding, the 404s, and 80 things called Copilot to find it
I made AI clones of my boss, a GitHub exec, and my CEO. They knew every rule the real people follow but never knew when to break one.
How I went from ‘this is slop’ to work I’m willing to publish under my name
Mike Taylor
Natalia Quintero
