Blog

Notes from the Prompting Lab

Here at Libretto, we're trying to turn prompt tinkering into prompt engineering. This means we do a lot of empirical experiments on what works and what's just hype when it comes to prompt engineering, and here on our blog is where we share what we've learned.

Yes, AI Models Like GPT-4o Change Without Warning. Here’s What You Can Do About It.

What I Wish I'd Known About SOC2 Compliance: One Founder's Take

Yes, AI Models Like GPT-4o Change Without Warning. Here’s What You Can Do About It.

Your AI Prompts Are Failing, and You Probably Don’t Even Know

Building an LLM-based App with Libretto, part 2

Vibes at Scale: Libretto Makes LLM-as-Judge Easy, Understandable, and Dependable

Building an LLM-based App with Libretto, part 1

Prompt Engineering Should Be Fast, Automated, & Fully Empirical — Here’s Libretto’s Approach

How many few shot examples should you use?

Do LLMs want us to say the magic word?

Are the best few-shot examples applicable across models?

Does it matter which examples you choose for few-shot prompting?

Stay Ahead in AI Development

The Libretto newsletter