{"uid":"cap_zgt5DlFr3gnQWlsGyzYfv","slug":"pqs-onchainintel-net-f13253af","name":"PQS Full Analysis - Prompt Quality Score with Before/After Outputs","description":"PQS full analysis - optimized prompt plus before/after outputs","url":"https://pqs.onchainintel.net/api/score/full","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"prompt":{"type":"string","maxLength":10000,"minLength":1,"description":"Prompt to score"},"vertical":{"enum":["software","content","business","education","science","crypto","general","research"],"type":"string","default":"general","description":"Domain: software/content/business/education/science/crypto/general/research"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.125","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":"$0.125/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.125","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.125","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Lm83ZgOLVM6iCkBdUgbud","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.125","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs a full 8-dimensional prompt quality analysis returning the optimized prompt plus before/after LLM outputs to show the improvement","exampleAgentPrompt":"Run a full PQS analysis on this prompt I'm planning to send to GPT-4: 'Summarize the following document for a business audience' — give me the 8-dimension quality score, the optimized version of the prompt, and show me the before and after outputs so I can see the difference.","exampleUseCases":[{"title":"Validating chatbot prompts before deployment","prompt":"I need to make sure our customer support chatbot prompt is solid before we push it live. Can you run a full PQS analysis on it? I want to see the quality score across all 8 dimensions, what needs fixing, and side-by-side outputs showing how much better the optimized version performs."},{"title":"Debugging underperforming RAG retrieval prompts","prompt":"Our RAG pipeline isn't returning relevant documents like it should. Can you analyze the retrieval prompt we're using with PQS? Show me the full quality breakdown, the optimized version, and real before-and-after outputs so I can understand what's going wrong and prove the fix works."},{"title":"Justifying prompt rewrites to stakeholders","prompt":"I want to rewrite our data extraction prompt to improve accuracy, but leadership wants evidence it'll actually work. Can you give me a complete PQS report with the current prompt's score, the optimized version, and concrete before-and-after LLM outputs demonstrating the improvement?"}],"resultDescription":"Returns the full prompt quality analysis including an 8-dimensional score breakdown across 5 frameworks, the optimized version of the input prompt, the raw LLM output from the original prompt, the LLM output from the optimized prompt, and the top recommended fixes — letting the caller see exactly how much improvement the optimization delivers.","failureModes":["Empty or missing prompt input returns a validation error","Prompt too long may exceed token limits","Model parameter specifying unsupported target model returns an error","Payment failure or insufficient USDC balance blocks the call","Malformed request body returns a 400 error","Downstream LLM unavailability causes a 503 or timeout"],"whenToPreferThis":"Choose this endpoint when you need the complete picture: not just a score but also the rewritten prompt and concrete before/after LLM outputs proving the improvement. Use it when you want to justify prompt changes to a stakeholder, debug why a prompt is underperforming, or validate that an optimized prompt genuinely produces better results — rather than just getting a pass/fail or a score alone.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:40:10.212Z","isFirstParty":false}