{"kind":"crawlcheck-resolve","v":1,"schema":"https://crawlcheck.io/schemas/resolve.json","domain":"deepset.ai","answered_at":"2026-10-19T02:25:25.200Z","reading":"Each section is declared (what the site says about itself), observed (what CrawlCheck was served) or not_measured, with when it was observed. There is no overall score: decide on the section your action depends on.","status":"measured","subject":{"domain":"deepset.ai","host":"www.deepset.ai","path":"/","report_id":"0cf16wuup7","scanned_at":"2026-10-15T23:03:12.063Z","score_version":32},"freshness":{"observed_at":"2026-10-15T23:03:12.063Z","age_hours":75.4,"latest_report_id":"0cf16wuup7","is_latest":true,"newer_scan_exists":false,"last_second_reading_at":null,"note":"observed_at is when CrawlCheck fetched the site; nothing here says the site is unchanged since","last_verified_at":"2026-10-15T23:03:12.063Z","fresh_until":"2026-10-22T23:03:12.063Z","stale":false,"fresh_policy":"an answer is fresh for 168 hours after observed_at; each action below has its own maximum age. last_verified_at is the latest reading of this domain by any enrolled observer."},"observers":{"primary":{"version_tag":null,"vantage":{"kind":"cloudflare-worker","colo":null}},"independent_readings":0,"by_field":"https://crawlcheck.io/api/corroboration?domain=deepset.ai","directory":"https://crawlcheck.io/.well-known/crawlcheck-observers.json","samples_by_network":{"networks":0,"samples":0,"groups":[],"window":"the latest 12 independent readings kept for this domain; the primary scan (Cloudflare) is not counted here"}},"crawl_policy":{"state":"declared","observed_at":"2026-10-15T23:03:12.063Z","source":"https://www.deepset.ai/robots.txt","http_status":200,"path_tested":"/","agents":[{"agent":"Googlebot-Image","label":"Google image crawler","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Googlebot-News","label":"Google News","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Googlebot-Video","label":"Google video crawler","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Storebot-Google","label":"Google Shopping","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Mediapartners-Google","label":"Google AdSense","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"APIs-Google","label":"Google push delivery","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"BingPreview","label":"Bing page preview","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"msnbot","label":"Microsoft legacy crawler","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Slurp","label":"Yahoo Slurp","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Yandex","label":"Yandex (umbrella token)","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"coccocbot-web","label":"Coc Coc","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Facebot","label":"Meta link crawler","role":"social","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Magpie-crawler","label":"Magpie AI","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"img2dataset","label":"img2dataset image corpus","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"AwarioRssBot","label":"Awario RSS","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"AwarioSmartBot","label":"Awario smart","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"TurnitinBot","label":"Turnitin","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"archive.org_bot","label":"Internet Archive","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"ia_archiver","label":"Internet Archive (legacy)","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"AhrefsBot","label":"Ahrefs link index","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"SemrushBot","label":"Semrush crawler","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"MJ12bot","label":"Majestic link index","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"DotBot","label":"Moz link index","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"rogerbot","label":"Moz site crawler","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"DataForSeoBot","label":"DataForSEO","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"BLEXBot","label":"WebMeUp link index","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Yeti","label":"Naver","role":"regional","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"YoudaoBot","label":"Youdao","role":"regional","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Exabot","label":"Exalead","role":"regional","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Sogou web spider","label":"Sogou","role":"regional","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"YisouSpider","label":"Yisou","role":"regional","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"360Spider","label":"360 Search","role":"regional","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Sosospider","label":"Soso","role":"regional","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"meta-webindexer","label":"Meta web index","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"omgili","label":"Webz.io omgili","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"cohere-training-data-crawler","label":"Cohere training corpus","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"PanguBot","label":"Huawei PanGu","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Ai2Bot-Dolma","label":"Allen Institute Dolma","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"FriendlyCrawler","label":"FriendlyCrawler ML","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"VelenPublicWebCrawler","label":"Velen","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"MyCentralAIScraperBot","label":"MyCentral AI","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"DeepSeekBot","label":"DeepSeek","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"ICC-Crawler","label":"NICT ICC","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"GoogleOther","label":"Google non-search fetch","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Google-CloudVertexBot","label":"Vertex AI agent build","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"CloudflareBrowserRenderingCrawler","label":"Cloudflare Browser Run /crawl","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Cloudflare-AutoRAG","label":"Cloudflare AutoRAG","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Peer39_Crawler","label":"Peer39 ad context","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"AdsBot-Google","label":"Google Ads quality","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"AmazonAdBot","label":"Amazon Ads","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"AdIdxBot","label":"Microsoft Ads","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Twitterbot","label":"X link preview","role":"social","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"LinkedInBot","label":"LinkedIn link preview","role":"social","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"facebookexternalhit","label":"Facebook link preview","role":"social","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Pinterestbot","label":"Pinterest","role":"social","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Slackbot-LinkExpanding","label":"Slack unfurl","role":"social","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"OAI-SearchBot","label":"ChatGPT search index","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"ChatGPT-User","label":"ChatGPT live fetch","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Claude-SearchBot","label":"Claude search index","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Claude-User","label":"Claude live fetch","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"PerplexityBot","label":"Perplexity index","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Perplexity-User","label":"Perplexity live fetch","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Gemini-Deep-Research","label":"Gemini research agent","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"MistralAI-User","label":"Le Chat live fetch","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"DuckAssistBot","label":"DuckDuckGo AI assist","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"YouBot","label":"You.com","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"PhindBot","label":"Phind","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Kagibot","label":"Kagi","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Copilot-User","label":"Microsoft Copilot fetch","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Meta-ExternalFetcher","label":"Meta AI live fetch","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Googlebot","label":"Google Search and AI Overviews","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"bingbot","label":"Bing and Copilot index","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Applebot","label":"Apple and Siri","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Amazonbot","label":"Amazon","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"DuckDuckBot","label":"DuckDuckGo","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"YandexBot","label":"Yandex","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Baiduspider","label":"Baidu","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Seznambot","label":"Seznam","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Neevabot","label":"Neeva","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"PetalBot","label":"Huawei Petal","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"GPTBot","label":"OpenAI training and index","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"ClaudeBot","label":"Anthropic training","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"anthropic-ai","label":"Anthropic legacy agent","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Claude-Web","label":"Anthropic legacy agent","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Google-Extended","label":"Gemini training","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Applebot-Extended","label":"Apple training","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"CCBot","label":"Common Crawl","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Bytespider","label":"ByteDance","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"meta-externalagent","label":"Meta AI training","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"FacebookBot","label":"Meta legacy","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"cohere-ai","label":"Cohere","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Diffbot","label":"Diffbot knowledge graph","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Omgilibot","label":"Webz.io","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"ImagesiftBot","label":"Imagesift","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Timpibot","label":"Timpi","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"AI2Bot","label":"Allen Institute","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Scrapy","label":"Generic scraper framework","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"SemrushBot-OCOB","label":"Semrush AI corpus","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Applebot-Extended-Ads","label":"Apple ads corpus","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"TikTokSpider","label":"TikTok","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"QuillBot","label":"QuillBot","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Webzio-Extended","label":"Webz.io extended","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"ProRataInc","label":"ProRata","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"AwarioBot","label":"Awario","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Amzn-SearchBot","label":"Amazon search eligibility, separate from Amazonbot","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Amzn-User","label":"Amazon live fetch for Alexa questions","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"MistralAI-Index","label":"Mistral search index for Vibe","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"MistralAI-Training","label":"Mistral training crawl","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"OAI-AdsBot","label":"OpenAI ChatGPT ads page validation","role":"tool","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Google-Agent","label":"Google user-triggered agent, acts on the web","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"Google-GeminiNotebook","label":"Gemini Notebook user-supplied URL fetch","role":"answer","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"GoogleOther-Image","label":"Google common crawler, public image URLs","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"GoogleOther-Video","label":"Google common crawler, public video URLs","role":"train","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false},{"agent":"ExaSearchBot","label":"Exa AI search index, Web Bot Auth signed","role":"search","allowed_homepage":true,"allowed_path":true,"has_own_group":false,"wildcard_rules_shadowed":false}],"signal_conflicts":[],"note":"robots.txt governs access and Content-Signal governs use; both are what the site declares, not what it serves"},"delivery":{"state":"observed","observed_at":"2026-10-15T23:03:12.063Z","url":"https://www.deepset.ai/","identity_basis":"every identity was sent by CrawlCheck from its own network; none is the named operator's own crawler","identities":[{"identity":"anon","label":"Unnamed client","role":"control","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"gptbot","label":"GPTBot","role":"train","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"claudebot","label":"ClaudeBot","role":"train","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"oaisearch","label":"OAI-SearchBot","role":"answer","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"claudesearch","label":"Claude-SearchBot","role":"answer","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"perplexity","label":"PerplexityBot","role":"answer","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"googlebot","label":"Googlebot","role":"search","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"browser","label":"Mobile browser","role":"browser","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"bingbot","label":"Bingbot","role":"search","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"applebot","label":"Applebot","role":"search","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"amazonbot","label":"Amazonbot","role":"train","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"bytespider","label":"Bytespider","role":"train","status":403,"words":127,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"metaexternal","label":"Meta-ExternalAgent","role":"train","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null},{"identity":"ccbot","label":"CCBot","role":"train","status":200,"words":696,"blocker":null,"redirected_to":null,"x_robots_tag":null}]},"machine_files":{"state":"observed","observed_at":"2026-10-15T23:03:12.063Z","files":[{"path":"/robots.txt","status":200,"content_type":"text/plain; charset=utf-8","bytes":43,"verdict":"ok"},{"path":"/sitemap.xml","status":200,"content_type":"application/rss+xml; charset=utf-8","bytes":42159,"verdict":"ok"},{"path":"/sitemap_index.xml","status":404,"content_type":"text/html; charset=utf-8","bytes":54196,"verdict":"absent"},{"path":"/wp-sitemap.xml","status":404,"content_type":"text/html; charset=utf-8","bytes":54196,"verdict":"absent"},{"path":"/llms.txt","status":200,"content_type":"text/plain; charset=utf-8","bytes":9034,"verdict":"ok"}],"read_before_page":[{"path":"/sitemap.xml","bytes":42159,"kind":"machine"},{"path":"/llms.txt","bytes":9034,"kind":"machine"},{"path":"/robots.txt","bytes":43,"kind":"machine"}],"hashes":"every fetched body's SHA-256 is in the sealed manifest: https://crawlcheck.io/api/artifact/870616b17583bd4cf22b1c8ebd257a10aee13ba16528d0e2c449b8774f01ee3f?body=1"},"capabilities":{"state":"observed","observed_at":"2026-10-15T23:03:12.063Z","checked":[{"kind":"a2a_agent_card","url":"https://www.deepset.ai/.well-known/agent-card.json","status":404}],"declared":0,"by_safety_class":{},"verified":0,"mismatches":0,"invocation_rule":"capabilities are read from declarations only; nothing is invoked. Later verification may call read_only_public operations alone; every other class needs the site owner's authorisation and a test account, and unknown is never called","certificate":{"id":"ccap1:d27ed0c4bc1062bddb20b6dca3c77e6dcf4c8eedc5ed88ce56a6fe562734b0f2","signed":true,"entry":"https://crawlcheck.io/api/registry/capabilities?domain=deepset.ai","verify":"https://crawlcheck.io/api/registry/capabilities/verify?domain=deepset.ai"},"items":"https://crawlcheck.io/api/capabilities?domain=deepset.ai"},"entity":{"state":"observed","observed_at":"2026-10-15T23:03:12.063Z","name":"deepset","wikidata_item_found":true,"links":[{"url":"https://www.linkedin.com/company/deepset-ai/","state":"corroborated","why":"the target page references deepset.ai back"},{"url":"https://x.com/deepset_ai","state":"corroborated","why":"the target page references deepset.ai back"},{"url":"https://www.youtube.com/channel/UC5dfn9m310oyt-cbeegfvZw","state":"unverifiable","why":"HTTP 429 — the platform refuses or fails datacentre readers; the claim can be neither confirmed nor accused from here"},{"url":"https://github.com/deepset-ai","state":"corroborated","why":"the target page references deepset.ai back"},{"url":"https://haystack.deepset.ai/","state":"corroborated","why":"the target page references deepset.ai back"}],"states":"corroborated = the linked page links back; unreciprocated = readable and does not; unverifiable = could not be read from here"},"mcp_registry":{"state":"observed","listed":0,"import_finished_at":"2026-10-14T20:03:09.131Z","import_run":1,"import_servers":43267,"why":"the official MCP Registry lists no remote MCP endpoint on this domain (import finished 2026-10-14)","url":"https://crawlcheck.io/api/mcp/servers?host=deepset.ai"},"content_clock":{"homepage":{"url":"https://www.deepset.ai/","observed":true,"content_sha256":"b1aa46d9aeaedfdc3b699777ae9770505b94b50594368179d030186f18fbbf67","first_observed":"2026-10-10T16:52:09.667Z","last_read":"2026-10-16T00:34:04.990Z","changes_observed":0,"main_content_last_changed":null,"unchanged_since_first_observed":"2026-10-10T16:52:09.667Z","declared":{"last_modified_header":"2026-10-15T01:02:27.000Z"},"date_moved_words_did_not":null,"api":"https://crawlcheck.io/api/v1/content-clock?url=https%3A%2F%2Fdeepset.ai%2F"},"reading":"When the main content (not the bytes) of these URLs last changed, from CrawlCheck's own reads. Full history and the page's declared dates: the api link."},"self_claims":{"observed":true,"first_read":"2026-10-10T05:11:15.939Z","last_read":"2026-10-16T00:18:10.730Z","reads":5,"claims":[{"type":"address","value":"165 Broadway, One Liberty Plaza, 23rd Floor, New York, NY, 10006","status":"current","first_seen":"2026-10-10T05:11:15.939Z","last_seen":"2026-10-16T00:18:10.730Z"},{"type":"address","value":"Zinnowitzer Str. 1, Berlin, 10115","status":"current","first_seen":"2026-10-10T05:11:15.939Z","last_seen":"2026-10-16T00:18:10.730Z"},{"type":"founded","value":"2018","status":"current","first_seen":"2026-10-10T05:11:15.939Z","last_seen":"2026-10-16T00:18:10.730Z"}],"api":"https://crawlcheck.io/api/v1/claims?domain=deepset.ai","reading":"what the site says about itself on its own pages, with when CrawlCheck first and last saw each value; not a statement that the claim is true"},"read_equivalence":{"url":"https://deepset.ai/","observed":true,"verdict":"equivalent","checked_at":"2026-10-16T00:34:15.234Z","first_observed":"2026-10-10T07:10:00.582Z","ai_identities_served":"3 of 3","identities":[{"identity":"gptbot","verdict":"equivalent","text_ratio":1,"instruction_like_text":false},{"identity":"claudebot","verdict":"equivalent","text_ratio":1,"instruction_like_text":false},{"identity":"perplexity","verdict":"equivalent","text_ratio":1,"instruction_like_text":false}],"api":"https://crawlcheck.io/api/v1/read-equivalence?url=https%3A%2F%2Fdeepset.ai%2F","reading":"whether the main text served to AI identities is the same text a person sees in a browser, from one simultaneous read of the homepage; evidence and the differing sentences at the api link"},"rights":{"observed":true,"path":"/","read_at":"2026-10-17T20:17:40.670Z","api":"https://crawlcheck.io/api/v1/rights?domain=deepset.ai","reading":"one value per use for the homepage, with the signal that decided it; signals considered, conflicts and per-path answers at the api link","train":{"value":"not_declared","decided_by":{"signal":"robots.txt","url":"https://deepset.ai/robots.txt","evidence":"access is open to GPTBot, ClaudeBot, Google-Extended, CCBot, Applebot-Extended, meta-externalagent on / and no signal states whether train is allowed"},"conflicts":0},"ground":{"value":"not_declared","decided_by":{"signal":"robots.txt","url":"https://deepset.ai/robots.txt","evidence":"access is open to OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User on / and no signal states whether ground is allowed"},"conflicts":0},"summarize":{"value":"not_declared","decided_by":{"signal":"robots.txt","url":"https://deepset.ai/robots.txt","evidence":"access is open to OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User on / and no signal states whether summarize is allowed"},"conflicts":0},"cite":{"value":"not_declared","decided_by":{"signal":"robots.txt","url":"https://deepset.ai/robots.txt","evidence":"access is open to OAI-SearchBot, Claude-SearchBot, PerplexityBot, Googlebot, Bingbot on / and no signal states whether cite is allowed"},"conflicts":0},"transact":{"value":"not_declared","decided_by":{"signal":"robots.txt","url":"https://deepset.ai/robots.txt","evidence":"access is open to ChatGPT-User, Claude-User, Perplexity-User on / and no signal states whether transact is allowed"},"conflicts":0}},"findings":{"access":"public","rule":"the top finding in full; the rest by title, severity and path (a licence for this domain opens them)","items":[{"fid":"f1:b72c7b9bd085eca2b959","decision_id":"d1:e69d7a6fa8c9d118f28a","code":"PAGE_IS_MOSTLY_CODE","severity":3,"path":"/","title":"Almost nothing a machine receives from this page is readable text","rule_revision":1,"span_id":"d4b902cf198cfb39","state":"persisted","valid_time":{"valid_from":{"after":null,"by":"2026-09-18T02:53:59.496Z"},"valid_to":null,"recorded_at":"2026-09-18T02:53:59.496Z","superseded_at":null,"superseded_by":null,"earlier_intervals":0,"before_bt1":true},"observations_linked":1,"trust":{"freshness":{"observed_at":"2026-10-15T23:03:12.063Z","last_observed":"2026-10-15T23:03:12.063Z","held_since":"2026-09-18T02:53:59.496Z","state":"persisted"},"confidence":{"level":"reproduced","means":"seen again: repeated on CrawlCheck's own network, or in more than one scan","basis":["seen in 6 scans since 2026-09-18","the decision names the 1 fetch it read"],"sample":{"cross_network":"not_applicable","why":"this finding does not depend on the requesting identity or network, so other networks' readings neither confirm nor contradict it","readings":1,"diversity":{"readings":1,"observers":1,"distinct_networks":1,"networks":{"cloudflare":1},"distinct_countries":0,"countries":{}},"scans":{"seen":6,"could_have_seen":null,"interval":null,"why":"scans that could have seen this finding are counted from 2026-10-08; this finding was first seen before that, so only the scans that saw it are known"},"interval":null,"interval_of":null,"note":"interval: the 95% Wilson score interval for the share, from k of n; it is wide when n is small, and that width is the point. networks: autonomous systems the readings arrived from (two observers on one network are one network). countries: where the connection was measured; CrawlCheck's own reading leaves from a Cloudflare data centre and carries no country here."}},"contradictions":[]},"score_effect":{"decision_id":"d1:e69d7a6fa8c9d118f28a","code":"PAGE_IS_MOSTLY_CODE","path":"/","severity":3,"level":"medium","points":0,"cap":"C","binding":true,"letter_now":"C","letter_without_it":"A","same_level_others":0,"says":"Caps the letter at C. Without it the letter would be A (score 88). Moves no points; the score is built from the measured rows."},"root_cause":null,"corroboration":{"status":"not_applicable","reading":"this finding does not depend on the requesting identity or network"},"explain":{"mcp_tool":"explain_finding","arguments":{"id":"d1:e69d7a6fa8c9d118f28a"},"url":"https://crawlcheck.io/api/explain?id=d1:e69d7a6fa8c9d118f28a"},"disputes":[]},{"title":"The homepage is reached through a chain of redirects","severity":1,"path":"/","locked":true},{"title":"Visitors and crawlers are being served an old copy of this page","severity":1,"path":"/","locked":true}],"summary":{"total":3,"serious":1,"by_severity":{"Medium":1,"Note":2}},"withheld":"Every finding is listed by title, severity and path. The top one carries its code, detail and evidence; the other 2 are locked (locked: true) and need a licence or the fix service: https://crawlcheck.io/pricing"},"confidence":{"identities_answered":{"n":13,"of":14,"ratio":0.929},"vantages":1,"vantage_state":{"state":"single_vantage","means":"only one network read this site near the scan; nothing here is cross-checked","networks":1,"readings":1,"countries":0,"findings_contested":0,"findings_cross_confirmed":0,"states":{"single_vantage":"only one network read this site near the scan; nothing here is cross-checked","insufficient_samples":"more than one network read it, but fewer than 3 readings: too few to state agreement","cross_confirmed":"two or more networks read it, 3 or more readings, and no finding is contested between them","network_divergence":"networks disagree on at least one finding","regional_divergence":"networks in more than one country disagree on at least one finding: what is served depends on where the request comes from"}},"note":"counts and ratios only - there is no composite confidence number, because the parts do not combine into one honestly","sample":{"readings":1,"observers":1,"distinct_networks":1,"networks":{"cloudflare":1},"distinct_countries":0,"countries":{},"window_hours":6,"all_time":{"independent_readings":0,"networks":[]},"reading":"readings of this domain within 6 hours of the scan: CrawlCheck's own plus every independent observer's, with the networks and countries they arrived from","note":"interval: the 95% Wilson score interval for the share, from k of n; it is wide when n is small, and that width is the point. networks: autonomous systems the readings arrived from (two observers on one network are one network). countries: where the connection was measured; CrawlCheck's own reading leaves from a Cloudflare data centre and carries no country here."}},"contradictions":{"site":[],"between_networks_open":[],"locked_findings_not_shown":2},"evidence":{"report":"https://crawlcheck.io/r/0cf16wuup7","machine_record":"https://crawlcheck.io/api/v1/machine-record?id=0cf16wuup7","manifest_sha256":"870616b17583bd4cf22b1c8ebd257a10aee13ba16528d0e2c449b8774f01ee3f","verify":"https://crawlcheck.io/api/verify?id=0cf16wuup7","bundle":"https://crawlcheck.io/api/bundle?id=0cf16wuup7","offline_verifier":"https://crawlcheck.io/crawlcheck-verify.mjs?v=b22547e95463d03e","verify_this_answer":"save it as answer.json, then: node crawlcheck-verify.mjs answer.json"},"impersonation":{"state":"no_lookalike","verdict":"no_lookalike","brand_frame":"Tranco top 10,000 (Y83YG)"},"actions":{"v":1,"decisions":"allow | warn | require_confirmation | block | unsupported","rule":"decided from this answer's own sections at signing time; an agent's own policy may be stricter, never looser","read":{"decision":"allow","minimum_assurance":"reachable","assurance_found":["declared","reachable"],"needs":"robots.txt lets AI agents read the path, and the page was served to at least one AI-crawler identity","why":"8 of 9 AI-crawler identities were served the page","doubts":[],"max_age_hours":168},"cite":{"decision":"allow","minimum_assurance":"reachable + entity observed","assurance_found":["declared","reachable","entity observed","read_equivalent"],"needs":"everything read needs, plus an observed entity and no contradiction the site makes with itself","scope":{"covers":["access: robots.txt and what was actually served to AI-crawler identities","permissions: the rights and content signals the site declares","identity: the entity the site declares and who has proven control of the domain","provenance: when, from where and by whom it was observed, signed and logged"],"does_not_cover":"whether the content is true, accurate, current or complete; a cite decision says the source may be cited and attributed, not that what it says is right"},"why":"8 of 9 AI-crawler identities were served the page","doubts":[],"max_age_hours":168},"connect":{"decision":"unsupported","minimum_assurance":"conformant","assurance_found":[],"needs":"a declared capability that CrawlCheck invoked read-only and found to behave as declared","why":"the site declares no capability to connect to","doubts":[],"max_age_hours":72},"transact":{"decision":"require_confirmation","minimum_assurance":"action_ready","assurance_found":[],"needs":"owner-verified identity and an action-ready capability; CrawlCheck does not certify transactions, so a human confirms","why":"CrawlCheck does not certify transactions; a human confirms every financial, identity or irreversible action","doubts":[],"max_age_hours":24},"administer":{"decision":"block","minimum_assurance":"never automatic","assurance_found":[],"needs":"high-privilege operations are never authorised by a public record","why":"never authorised by a public record","doubts":[],"max_age_hours":0}},"absences":[{"what":"sitemap","path":"/sitemap_index.xml","result":"absent","at":"2026-10-15T23:03:12.063Z","from":{"observer":"crawlcheck-worker","network":"cloudflare","directory":"https://crawlcheck.io/.well-known/crawlcheck-observers.json"},"checked":[{"method":"GET","url":"https://deepset.ai/sitemap_index.xml","status":404,"redirects":"followed"}],"scope":"GET https://deepset.ai/sitemap_index.xml answered HTTP 404 at 2026-10-15T23:03:12.063Z. The file was not served at this path then; this says nothing about the same content at another path or a later time."},{"what":"sitemap","path":"/wp-sitemap.xml","result":"absent","at":"2026-10-15T23:03:12.063Z","from":{"observer":"crawlcheck-worker","network":"cloudflare","directory":"https://crawlcheck.io/.well-known/crawlcheck-observers.json"},"checked":[{"method":"GET","url":"https://deepset.ai/wp-sitemap.xml","status":404,"redirects":"followed"}],"scope":"GET https://deepset.ai/wp-sitemap.xml answered HTTP 404 at 2026-10-15T23:03:12.063Z. The file was not served at this path then; this says nothing about the same content at another path or a later time."},{"what":"a2a_agent_card","result":"absent","at":"2026-10-15T23:03:12.063Z","from":{"observer":"crawlcheck-worker","network":"cloudflare","directory":"https://crawlcheck.io/.well-known/crawlcheck-observers.json"},"checked":[{"method":"GET","url":"https://www.deepset.ai/.well-known/agent-card.json","status":404,"redirects":"followed"}],"scope":"Every location CrawlCheck checks for a a2a agent card answered not found (404). No declaration of this kind was served at those URLs at that time; one served elsewhere, or added later, is not covered."},{"what":"mcp_registry_listing","result":"absent","at":"2026-10-14T20:03:09.131Z","from":{"observer":"crawlcheck-worker","network":"cloudflare","source":"registry.modelcontextprotocol.io"},"checked":[{"method":"registry import","url":"https://registry.modelcontextprotocol.io/v0/servers","run":1,"servers_read":43267,"finished_at":"2026-10-14T20:03:09.131Z"}],"scope":"The official MCP Registry, read in full (import finished 2026-10-14T20:03:09.131Z), lists no remote MCP endpoint whose host is deepset.ai or a subdomain. Servers not listed in that registry are not covered."}],"control":{"state":"unproven","proofs":[],"organization":null,"claim":"https://crawlcheck.io/registry/deepset.ai/claim","why":"nobody has proven control of deepset.ai to CrawlCheck, so who stands behind the site is unconfirmed","note":"control says who answers for the domain, not whether it is safe; it does not change any decision in this answer"},"transparency":{"state":"included","log_id":"crawlcheck-resolve-log-v1","leaf_hash":"8f3943b596a14ea08d42a4e3f302a142ce0148fe8e014332446b2288583fc920","batch":565,"index":2,"batch_size":6,"path":["9401284d0df3f1ce375d49fea14b28ac17c94dc892541fe804ff5d376a44f47d","75ca278ab7077d685fbdfae448ebd8eeec1290be664e3d30f5012a7cac625849","c083c8cdc4ce03be5b26c280bc3383c2196ace852d8b391328b9fb90458755a9"],"sth":{"kind":"crawlcheck-log-sth","v":1,"log_id":"crawlcheck-resolve-log-v1","batch":565,"first_index":122078,"batch_size":6,"tree_size":122084,"batch_root":"73e20508b740fb497fc1f5caa0b99e9cf29b636f0ce4624ad079bee2b24434b6","prev_sth_sha256":"c2baee222e022ff68aea332e70c62f1895a0e72662d6a9a4a81f67c8c9b91521","created_at":"2026-10-15T23:32:29.042Z","rules":{"leaf":"SHA-256(0x00 || canonical JSON of the answer's decision content)","tree":"RFC 9162 Merkle tree hash over this batch's leaf hashes, sorted","chain":"prev_sth_sha256 is the sha256 of the previous batch's signed tree head; batch numbers are consecutive and tree_size grows by batch_size"},"code":{"version_id":"c77492f6-f643-42dd-a52d-bd37df0caf18","script_sha16":null,"state":"no_receipt","deployed":null,"build_log_entry":null,"score_version":32,"scoring_policy_sha256":"d3c9c95d409dae4e90b8e868ff113e631e445e33c14a0cc008dda144293821b3","decision_rules_sha256":"18dd5636e0896692ab518050cb401744edea2e6f1086dff94fead314959bdc3e","check":"https://crawlcheck.io/api/v1/builds/c77492f6-f643-42dd-a52d-bd37df0caf18"},"sha256":"235b4a8f266aa64f96b60184a5d5e50b90d299d178248d467661a67bd0635b72","signature":{"v":1,"alg":"Ed25519","kid":"1hHmE3fo1rg5Ig70wuFtJ5wBc7G-sUTgUJkxyPWFRps","over":"sha256","message":"crawlcheck-data-v1\n235b4a8f266aa64f96b60184a5d5e50b90d299d178248d467661a67bd0635b72","sig":"ZBnB7B2sDSwtoC4zujd-pBqRqaGE6pRod-Mz3SkZD0DQFblX5n69GEwJ3aJcZ_442OfoyJ8_JE5LejGgjESLBQ","signed_at":"2026-10-15T23:32:29.169Z","key":{"kid":"1hHmE3fo1rg5Ig70wuFtJ5wBc7G-sUTgUJkxyPWFRps","jwk":{"kty":"OKP","crv":"Ed25519","x":"5TmKCOx0TTHepq7HwyXBHvGQpVCSBd2lV8cLzYVqFxQ"},"published_in":"https://crawlcheck.io/.well-known/http-message-signatures-directory"},"canonical":"sha256 over canonical JSON of every field except sha256 and signature"}},"witnesses":"https://crawlcheck.io/api/v1/log/sth/565","content_rule":"leaf = SHA-256(0x00 || canonical JSON of the answer's decision content); see https://crawlcheck.io/api/v1/log"},"assurance_ladder":{"v":1,"level":"declared","order":["declared","discovered","reachable","conformant","owner_verified","authorized","reliable","action_ready"],"rungs":[{"rung":"declared","state":"reached","why":"robots.txt policy declared"},{"rung":"discovered","state":"not_reached","why":"nothing an agent could call was found (no OpenAPI, MCP card, A2A card or registry listing)"},{"rung":"reachable","state":"reached","why":"AI-crawler identities were served the page"},{"rung":"conformant","state":"not_reached","why":"nothing declared to test"},{"rung":"owner_verified","state":"not_reached","why":"nobody has proven control of deepset.ai to CrawlCheck, so who stands behind the site is unconfirmed"},{"rung":"authorized","state":"not_reached","why":"the domain's owner has published no authorization for agents"},{"rung":"reliable","state":"not_measured","why":"reliability is measured for MCP endpoints over time; none on this domain is on the panel"},{"rung":"action_ready","state":"not_reached","why":"not yet: discovered, conformant, owner_verified, authorized, reliable"}],"rule":"level is the highest rung with every rung under it reached; a rung is reached only on measured evidence, not_reached when measured and short, not_measured when there was nothing to measure. The ladder describes evidence; each action's decision is still made in actions"},"code":{"version_id":"6929574e-df21-45a5-8a92-5b8ba41cc9aa","script_sha16":"85c9b9b6c9a512ed","state":"attested","deployed":{"at":"2026-10-18T20:02:49.319Z","commit":"2bf491f55991","run":"39161431635"},"build_log_entry":597,"score_version":32,"scoring_policy_sha256":"d3c9c95d409dae4e90b8e868ff113e631e445e33c14a0cc008dda144293821b3","decision_rules_sha256":"18dd5636e0896692ab518050cb401744edea2e6f1086dff94fead314959bdc3e","check":"https://crawlcheck.io/api/v1/builds/6929574e-df21-45a5-8a92-5b8ba41cc9aa"},"sha256":"722ad1582f4f0d623498f018db866217f593ee4165c8b5a9d9dbc866dd8ea8bf","signature":{"v":1,"alg":"Ed25519","kid":"1hHmE3fo1rg5Ig70wuFtJ5wBc7G-sUTgUJkxyPWFRps","over":"sha256","message":"crawlcheck-data-v1\n722ad1582f4f0d623498f018db866217f593ee4165c8b5a9d9dbc866dd8ea8bf","sig":"ZzFm9Q0WZM0aUQAAFwEvEO9xYJOZjNtmGUP2g-plUH2NXoXzkhX23aoBhQkDea8Jbl2KTg0WcGuUNEdfnaUYAw","signed_at":"2026-10-19T02:25:25.240Z","key":{"kid":"1hHmE3fo1rg5Ig70wuFtJ5wBc7G-sUTgUJkxyPWFRps","jwk":{"kty":"OKP","crv":"Ed25519","x":"5TmKCOx0TTHepq7HwyXBHvGQpVCSBd2lV8cLzYVqFxQ"},"published_in":"https://crawlcheck.io/.well-known/http-message-signatures-directory"},"canonical":"sha256 over canonical JSON of every field except sha256 and signature"}}