Prompt Recipes
LLM Confidence Score: 4 Recipes That Ship (2026)
An LLM confidence score tells you how sure the model was. Which providers return logprobs in 2026, what to do on Claude which returns none, and 4 copy-paste recipes.
6 min read111
Tag
#claude api
3 posts tagged.
Prompt Recipes
tool_choice: 4 Recipes That Ship (2026)
tool_choice in 2026: four copy-paste recipes to force any tool, pin one named tool, forbid tools for a turn, or leave it on auto, in Claude and OpenAI, each with the failure mode that bites.
6 min read108
Prompt Recipes
Stop Sequences on Claude: 4 Recipes That Ship (2026)
Stop sequences in 2026: four copy-paste recipes that cut a model off at a delimiter, bound a JSON object, force one section, and stop an agent from faking its own turn, plus where they break.
6 min read175