[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"glossary-plan-and-solve-prompting::en":3,"gloss-cluster-plan-and-solve-prompting::en":23,"gloss-next-plan-and-solve-prompting::en":9},{"slug":4,"category":5,"name":6,"definition":7,"meta_desc":8,"faq":9,"schema_markup":9,"related":10},"plan-and-solve-prompting","prompt-eng","Plan-and-Solve Prompting","Plan-and-solve (PS) prompting is a zero-shot technique that tells the model to first devise a plan by breaking the task into ordered steps, and then carry out that plan step by step. Introduced by Wang et al. (2023), it was proposed as an upgrade to the well-known zero-shot chain-of-thought trigger \"Let's think step by step,\" which often skips or muddles intermediate steps. By explicitly asking for a plan before execution, PS reduces missing-step and calculation errors without needing any hand-written examples. For SaaS builders, the appeal is that it's essentially free — a single, reusable instruction added to the system or user prompt — and it needs no curated few-shot examples to maintain. A typical phrasing: \"Let's first understand the problem and devise a plan to solve it. Then, let's carry out the plan and solve the problem step by step.\" It's a sensible default upgrade over bare zero-shot CoT for reasoning tasks, though for the hardest problems, example-based or decomposition methods still tend to win.","Plan-and-solve prompting tells the model to devise an ordered plan first and only then execute it step by step — a zero-shot upgrade to chain-of-thought.",null,[11,14,17,20],{"slug":12,"name":13},"chain-of-thought-prompting","Chain-of-Thought Prompting",{"slug":15,"name":16},"least-to-most-prompting","Least-to-Most Prompting",{"slug":18,"name":19},"skeleton-of-thought","Skeleton-of-Thought",{"slug":21,"name":22},"zero-shot-prompting","Zero-Shot Prompting",[24,28,31,34,36,39,42,45,48,51,54,57],{"slug":25,"category":5,"name":26,"updated_at":27},"analogical-prompting","Analogical Prompting","2026-08-24T02:46:37+00:00",{"slug":29,"category":5,"name":30,"updated_at":27},"automatic-prompt-optimization","Automatic Prompt Optimization",{"slug":32,"category":5,"name":33,"updated_at":27},"chain-of-density","Chain of Density (CoD)",{"slug":12,"category":5,"name":13,"updated_at":35},"2026-08-24T02:46:36+00:00",{"slug":37,"category":5,"name":38,"updated_at":27},"chain-of-verification","Chain-of-Verification",{"slug":40,"category":5,"name":41,"updated_at":35},"chunking","Chunking",{"slug":43,"category":5,"name":44,"updated_at":35},"constrained-decoding","Constrained Decoding",{"slug":46,"category":5,"name":47,"updated_at":35},"context-stuffing","Context Stuffing",{"slug":49,"category":5,"name":50,"updated_at":35},"delimiter","Delimiter",{"slug":52,"category":5,"name":53,"updated_at":27},"directional-stimulus-prompting","Directional Stimulus Prompting",{"slug":55,"category":5,"name":56,"updated_at":27},"emotion-prompting","Emotion Prompting",{"slug":58,"category":5,"name":59,"updated_at":35},"few-shot-prompting","Few-Shot Prompting"]