Recipes
Prompt Chaining: 5 Recipes That Ship (2026)
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.
3 min read29
Author
Sam Q.
Sam Q. ships prompt recipes at PromptAttic. Terse by default. Tests everything before writing it down.
Recipes
Prompt Injection Defenses That Hold Up (2026)
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.
4 min read25
Recipes
Few-Shot Prompting Recipes That Ship (2026)
Five copy-paste few-shot prompting recipes for July 2026: lock output format, tone, labels, and edge cases. Each with the prompt and the exact case where it breaks.
3 min read38
Recipes
Claude Extended Thinking: 3 Recipes That Ship (July 2026)
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.
3 min read34
library
Claude Tool Use: 3 Recipes That Ship + 2 Failure Modes (June 2026)
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.
8 min read87
recipes
Claude Structured Output: 3 Prompt Recipes That Ship (June 2026)
Three production-grade Claude structured output recipes for June 2026. Invoice extraction on Sonnet 4.6, support triage on Haiku 4.5, NL to SQL on Opus 4.7. Real cost per call. Three failure modes the docs do not warn you about.
7 min read52
Ship-fast
Ship this prompt as an app: the one-file pattern
Wrap a good prompt in one route handler: validate input, call the model, validate output, return typed JSON. No agent framework, no vector DB, no queue. A prompt plus a POST endpoint is a shippable feature. Add the rest only when a real user complains. Ship the prompt, not the platform.
1 min read45
Eval
A 5-line eval that catches 80% of hallucinations
Before you ship a generated answer, run one cheap second call that checks it against the source. Ask: is every claim in the answer supported by the provided context? Get back yes/no plus the first unsupported claim. Reject on no. Five lines of glue, catches the bulk of confident fabrications.
2 min read52
Routing
Cheap-then-deep routing: Haiku 4.5 first, Opus 4.7 only when it earns it
Route every call to Haiku 4.5 first. Ask it one thing: can you answer this with high confidence? If yes, ship its answer. If no, replay the same request to Opus 4.7. You pay premium tokens only on the hard 10–20%. Net cost drops ~70% with no quality loss on easy traffic.
1 min read49