{"uid":"cap_C9SAJShRVHQZWBuwZgfbZ","slug":"pqs-onchainintel-net-6522be89","name":"PQS Score - 8-Dimensional Prompt Quality Breakdown","description":"PQS score - 8-dimensional prompt quality breakdown across 5 frameworks with top fixes","url":"https://pqs.onchainintel.net/api/score","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"prompt":{"type":"string","description":"Prompt to score"},"vertical":{"type":"string","description":"Domain: software/content/business/education/science/crypto/general/research"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.025","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.025/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.025","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.025","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_CxidegUkaUfaOeyHRU_1P","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.025","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scores a single prompt across 8 quality dimensions using 5 evaluation frameworks and returns a ranked list of top fixes","exampleAgentPrompt":"Score this prompt for me across all 8 quality dimensions and tell me the top fixes: 'You are a helpful assistant. Summarize the following article in bullet points.' I want to see how it breaks down across the 5 evaluation frameworks before I actually send it anywhere expensive.","exampleUseCases":[{"title":"Refine customer support agent prompts","prompt":"My support team is getting inconsistent responses from our customer service agent. Can you analyze this prompt across all 8 quality dimensions and tell me which areas are weakest and how to fix them? 'You are a support agent. Help customers with their issues.' I want to understand what's making it underperform before we invest in fine-tuning."},{"title":"Validate RAG system prompts","prompt":"We're building a retrieval-augmented generation system and I want to make sure our retrieval prompt is solid before we start feeding it real queries. Score this one across all the quality dimensions and show me the top improvements: 'Find relevant documents for the user question.' What does the multi-framework analysis tell us about its effectiveness?"},{"title":"Audit prompt quality before deployment","prompt":"Before we deploy these prompts to our production LLM pipeline, I need a comprehensive quality audit. Can you break down this prompt across all 8 dimensions using your 5 frameworks and give me a priority list of fixes? 'Extract key information from the text.' I want to see where the weak spots are so we don't waste tokens on a mediocre prompt."}],"resultDescription":"Returns an 8-dimensional quality score for the submitted prompt, a per-dimension breakdown across 5 evaluation frameworks, and a prioritized list of the most impactful fixes to improve the prompt's overall PQS score.","failureModes":["Empty or missing prompt body returns a 400 validation error","Prompt exceeds maximum token length causing a 413 or truncation error","Payment not attached or insufficient USDC results in a 402 payment required response","Malformed JSON body returns a 400 parse error","Service unavailable or timeout returns a 503 or 504"],"whenToPreferThis":"Choose this endpoint when you need a detailed, multi-dimensional quality breakdown of a single prompt with actionable fix recommendations — especially before committing budget to a paid LLM call. Prefer this over the pass/fail preflight when you need more than a binary gate and want to understand exactly which dimensions are weak and how to improve them. Use it over the batch endpoint when you are iterating on a single prompt and need granular per-dimension scores.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:33:25.202Z","isFirstParty":false}