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.
Tag
10 posts tagged.
Six copy-paste prompt compression moves for 2026 with real before and after token counts. Cut manners, redundancy, and agent history. No library required.
Six copy-paste few-shot prompting examples that ship: classification, JSON extraction, tone matching, refusal, edge-case teaching, and format locking.
A terse, production-first prompt engineering cheat sheet for 2026: fifteen patterns, each with a one-line rule, its failure mode, and a link to the full recipe.
Five paste-ready role prompting recipes for 2026: domain expert, audience, format contract, adversary, and voice, each with its failure mode.
Five paste-ready chain-of-thought prompting examples for 2026, each with its failure mode, plus when reasoning out loud makes the answer worse.
Five paste-ready prompt chaining recipes for 2026: extract-then-reason, draft-critique-rewrite, route, map-reduce, and generate-then-gate, each with its failure mode.
Five paste-ready meta prompting recipes: make the model write, critique, rubric, and template your prompts, each with its failure mode. Plus the honest part: when meta prompting just wastes tokens.
Four prompt-layer defenses against prompt injection that measurably help, three that are theater, and the one architecture rule that actually keeps you safe. With paste-ready prompts and each failure mode.
Extended thinking changed in July 2026: on Claude Sonnet 5 and Opus 4.8 you use adaptive thinking and effort, not budget_tokens. Three recipes and the gotchas.
Three production Claude tool use recipes tested on Sonnet 4.6, Opus 4.7, and Haiku 4.5 with current pricing. Plus the two failure modes nobody warns you about. June 2026.