Prompt Recipes
LLM Temperature Settings: 6 Recipes That Ship (2026)
Six copy-paste LLM temperature and top_p recipes for 2026: the exact setting per task type, why it works, and the failure mode it prevents.
5 min read210
Category
Prompt-Recipes
31 posts in this category.
Prompt Recipes
Least-to-Most Prompting: 6 Recipes That Ship (2026)
Least-to-most prompting for LLMs in 2026: six copy-paste recipes that decompose a hard problem into ordered subproblems and feed each answer forward, with the receipt, the reasoning, and the failure mode for each.
4 min read121
Prompt Recipes
System Prompt vs User Prompt: The Placement Rules That Ship (2026)
System prompt vs user prompt in 2026: five copy-paste placement recipes with the same instruction shown in both lanes, plus the injection failure mode that makes lane choice a security decision.
5 min read111
Prompt Recipes
Prompt Compression: Recipes That Ship (2026)
Six copy-paste prompt compression moves for 2026 with real before and after token counts. Cut manners, redundancy, and agent history. No library required.
4 min read109
Prompt Recipes
Few-Shot Prompting Examples That Ship (2026)
Eight copy-paste few-shot prompting examples that ship: classification, JSON extraction, tone, refusal, edge cases, message-history shots, and dynamic example selection.
7 min read218
Prompt Recipes
ReAct Prompting: 6 Copy-Paste Recipes That Ship (2026)
ReAct prompting interleaves reasoning and tool calls: Thought, Action, Observation, repeat, until the model has enough to answer. It is how a plain prompt becomes an agent. Six copy-paste ReAct recipes below, each with the failure mode that bites first. Tested July 2026.
4 min read134
Prompt Recipes
Zero-Shot Prompting: 5 Recipes That Ship
Zero-shot prompting is the right default for most tasks in 2026. Five recipes that make instruction-only prompts reliable, plus the exact point to add one example.
4 min read113