{"uid":"cap_jDOBLEGonS8yJaPJMZ_Mr","slug":"sec-intel-agentdiet-dev-web-distillation-bm25-budget-controlled-a9217f7e","name":"Web Distillation & BM25 Budget-Controlled Prompt Compression","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://sec-intel.agentdiet.dev/v1/prompt-compress)","url":"https://sec-intel.agentdiet.dev/v1/prompt-compress?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","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":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_M-cy4a7inkEIXZ9qgPC5O","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compressed Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt for LLM consumption.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into budget mode with the query 'payment intents' and a max token ceiling of 500 tokens, so I can feed just the relevant parts to my LLM without blowing my context window.","exampleUseCases":[{"title":"Token-budget RAG document grounding","prompt":"Pull https://openai.com/pricing and compress it into budget mode focused on the query 'GPT-4o token costs', keeping it under 300 tokens — I need to inject just the relevant pricing info into my prompt without wasting context."},{"title":"Stripe docs agent context injection","prompt":"Distill the built-in Stripe docs at builtin://stripe-docs into structured mode so my agent can get clean JSON tables of API endpoints and metadata without parsing messy HTML."},{"title":"Competitive research page summarization","prompt":"Take the raw HTML I'm pasting from a competitor's pricing page and distill it into Markdown mode — I want a clean, readable summary my agent can reason over without all the navigation and footer noise."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, a 'status' field ('ok'), optional 'cache' metadata (HIT/MISS, latency_ms), and optional 'billing' details.","failureModes":["URL is unreachable or returns non-200 — distillation fails with an error status","max_tokens too low to produce meaningful content — may return minimal or empty excerpt","HTML input is malformed beyond recovery — structured/skeleton modes may degrade","BM25 query returns no relevant passages within token budget — sparse excerpt returned","x402 payment not fulfilled — 402 response blocks execution","Rate limits or upstream fetch timeouts for slow target URLs"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content or large HTML documents into an LLM context window while minimizing token cost and maximizing relevance. It is uniquely suited for agentic RAG pipelines where you need BM25-ranked, query-focused excerpts within a strict token budget, or when you want clean Markdown/structured JSON from a URL rather than raw HTML. Prefer it over generic scrapers when ROI proof (tokens saved, cost saved) is needed for auditing, or when the target is Stripe documentation via the built-in alias.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-24T16:55:49.184Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-distillation-bm25-budget-controlled-a9217f7e"}