{"schema_version":"onlylabs.public_signal.v1","title":"Cloudflare (Workers AI) Writing: How we built Cloudflare's data platform and an AI agent on top of it","description":"Cloudflare (Workers AI) writing signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/3ff9ebe9-4c55-4470-909c-fceecec21d07","json_url":"https://onlylabs.fyi/signals/3ff9ebe9-4c55-4470-909c-fceecec21d07/signal.json","generated_at":"2026-06-07T21:14:08.444279+00:00","org":{"slug":"cloudflare","name":"Cloudflare (Workers AI)","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/cloudflare","dossier_json_url":"https://onlylabs.fyi/labs/cloudflare/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/3ff9ebe9-4c55-4470-909c-fceecec21d07","signal_json":"https://onlylabs.fyi/signals/3ff9ebe9-4c55-4470-909c-fceecec21d07/signal.json","source":"https://blog.cloudflare.com/our-unified-data-platform/","lab_dossier":"https://onlylabs.fyi/labs/cloudflare","lab_dossier_json":"https://onlylabs.fyi/labs/cloudflare/dossier.json","analysis":"https://onlylabs.fyi/analysis/cloudflare","analysis_json":"https://onlylabs.fyi/analysis/cloudflare/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/cloudflare/evidence.json","category":"https://onlylabs.fyi/neoclouds","category_json":"https://onlylabs.fyi/neoclouds.json","category_feed":"https://onlylabs.fyi/neoclouds/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","topic":"https://onlylabs.fyi/topics/talking","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml?category=neocloud","data_business":null},"answer_pack":{"answer":"Cloudflare (Workers AI) published How we built Cloudflare's data platform and an AI agent on top of it. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Low-traction blog post, not a notable release · How we built Cloudflare's data platform and an AI agent on top of it How we built Cloudflare's data platform and an AI agent on top of it 2026-05-28 Brian Brunner.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","signal_desk":"talking","source_context":{"source_url":"https://blog.cloudflare.com/our-unified-data-platform/","source_host":"blog.cloudflare.com","occurred_at":"2026-05-28T13:00:00+00:00","first_seen_at":"2026-06-05T22:32:14.118742+00:00","date_source":"rss.item_date","context":null},"context_markers":[{"label":"Lab","value":"Cloudflare (Workers AI)","source":"signal"},{"label":"Signal desk","value":"talking","source":"signal"},{"label":"Source host","value":"blog.cloudflare.com","source":"source"},{"label":"Author","value":"Brian Brunner","source":"source"},{"label":"Notability","value":"Low-traction blog post, not a notable release","source":"signal"},{"label":"HN","value":"Trino praised for multi-source joins, PII handling; correction on ASF status.","source":"source"},{"label":"Watch term","value":"Data pipeline","source":"evidence"},{"label":"Watch term","value":"Infrastructure","source":"evidence"},{"label":"Watch term","value":"Safety and alignment","source":"evidence"},{"label":"Watch term","value":"Agents and tool use","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://blog.cloudflare.com/our-unified-data-platform/"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-07T21:14:08.444279+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/3ff9ebe9-4c55-4470-909c-fceecec21d07/signal.json","dossier_json":"https://onlylabs.fyi/labs/cloudflare/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/cloudflare/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/cloudflare/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml?category=neocloud","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","evidence_focus":["post title","source URL","captured page text","HN traction","linked model or paper references","publication date"],"extraction_questions":["Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Which writing reframes a recent release, model, hiring wave, or policy stance?","Which posts mention data, evals, infrastructure, safety, or deployment workflows?"],"signal_questions":["What public theme, launch framing, or research direction does this writing signal expose?","Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Do the 6 related writing signals show a repeated pattern?"],"output_fields":["org","theme","public_framing","traction","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, keep conclusions tied to category-specific strategy, source evidence, and follow-up questions.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/3ff9ebe9-4c55-4470-909c-fceecec21d07/signal.json","required":true},{"label":"source","url":"https://blog.cloudflare.com/our-unified-data-platform/","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/cloudflare/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/cloudflare/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Cloudflare (Workers AI)'s writing signal \"How we built Cloudflare's data platform and an AI agent on top of it\" for neocloud strategy."},"semantic_triples":[{"subject":"Cloudflare (Workers AI)","predicate":"published","object":"How we built Cloudflare's data platform and an AI agent on top of it","text":"Cloudflare (Workers AI) published How we built Cloudflare's data platform and an AI agent on top of it."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"is classified as","object":"writing signal","text":"How we built Cloudflare's data platform and an AI agent on top of it is classified as writing signal."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"belongs to","object":"talking desk","text":"How we built Cloudflare's data platform and an AI agent on top of it belongs to talking desk."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has evidence coverage","object":"1 captured evidence page","text":"How we built Cloudflare's data platform and an AI agent on top of it has evidence coverage 1 captured evidence page."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has captured page count","object":"1","text":"How we built Cloudflare's data platform and an AI agent on top of it has captured page count 1."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has readable page count","object":"1","text":"How we built Cloudflare's data platform and an AI agent on top of it has readable page count 1."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has related signal count","object":"6","text":"How we built Cloudflare's data platform and an AI agent on top of it has related signal count 6."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has analysis playbook objective","object":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","text":"How we built Cloudflare's data platform and an AI agent on top of it has analysis playbook objective Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has source host","object":"blog.cloudflare.com","text":"How we built Cloudflare's data platform and an AI agent on top of it has source host blog.cloudflare.com."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has lab","object":"Cloudflare (Workers AI)","text":"How we built Cloudflare's data platform and an AI agent on top of it has lab Cloudflare (Workers AI)."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has signal desk","object":"talking","text":"How we built Cloudflare's data platform and an AI agent on top of it has signal desk talking."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has source host","object":"blog.cloudflare.com","text":"How we built Cloudflare's data platform and an AI agent on top of it has source host blog.cloudflare.com."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has author","object":"Brian Brunner","text":"How we built Cloudflare's data platform and an AI agent on top of it has author Brian Brunner."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has notability","object":"Low-traction blog post, not a notable release","text":"How we built Cloudflare's data platform and an AI agent on top of it has notability Low-traction blog post, not a notable release."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has hn","object":"Trino praised for multi-source joins, PII handling; correction on ASF status.","text":"How we built Cloudflare's data platform and an AI agent on top of it has hn Trino praised for multi-source joins, PII handling; correction on ASF status.."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has watch term","object":"Data pipeline","text":"How we built Cloudflare's data platform and an AI agent on top of it has watch term Data pipeline."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has watch term","object":"Infrastructure","text":"How we built Cloudflare's data platform and an AI agent on top of it has watch term Infrastructure."}]},"intelligence":{"signal_desk":"talking","answer":"Cloudflare (Workers AI) published How we built Cloudflare's data platform and an AI agent on top of it. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Low-traction blog post, not a notable release · How we built Cloudflare's data platform and an AI agent on top of it How we built Cloudflare's data platform and an AI agent on top of it 2026-05-28 Brian Brunner.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","semantic_triples":[{"subject":"Cloudflare (Workers AI)","predicate":"published","object":"How we built Cloudflare's data platform and an AI agent on top of it","text":"Cloudflare (Workers AI) published How we built Cloudflare's data platform and an AI agent on top of it."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"is classified as","object":"writing signal","text":"How we built Cloudflare's data platform and an AI agent on top of it is classified as writing signal."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"belongs to","object":"talking desk","text":"How we built Cloudflare's data platform and an AI agent on top of it belongs to talking desk."},{"subject":"How we built Cloudflare's data platform and an AI agent on top of it","predicate":"has evidence coverage","object":"1 captured evidence page","text":"How we built Cloudflare's data platform and an AI agent on top of it has evidence coverage 1 captured evidence page."}]},"signal":{"id":"3ff9ebe9-4c55-4470-909c-fceecec21d07","url":"https://onlylabs.fyi/signals/3ff9ebe9-4c55-4470-909c-fceecec21d07","json_url":"https://onlylabs.fyi/signals/3ff9ebe9-4c55-4470-909c-fceecec21d07/signal.json","source_url":"https://blog.cloudflare.com/our-unified-data-platform/","title":"How we built Cloudflare's data platform and an AI agent on top of it","summary":"Cloudflare (Workers AI) published a writing signal. onlylabs watches public writing for research themes, product direction, and model-launch context.","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"cloudflare","name":"Cloudflare (Workers AI)","category":"neocloud"},"occurred_at":"2026-05-28T13:00:00+00:00","first_seen_at":"2026-06-05T22:32:14.118742+00:00","date_source":"rss.item_date","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://blog.cloudflare.com/our-unified-data-platform/"]},"facets":{},"traction":{"github_stars":null,"hn_points":3,"hn_comments":4,"hn_story_id":"48313598","hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"url":"https://blog.cloudflare.com/our-unified-data-platform/","final_url":"https://blog.cloudflare.com/our-unified-data-platform/","title":"How we built Cloudflare's data platform and an AI agent on top of it","http_status":200,"content_type":"text/html","capture_method":"plain","fetched_at":"2026-06-07T21:14:08.444279+00:00","bytes":317482,"raw_path":"0f6c77546e58fefc81cad98b09fa14f8f302bc8e7e43c742fd702ca345e4d083.html","content_hash":"1a337643d1a09c16b315cc5a475fb7ecf5c8c1f2df805101e3a4237d5e7cee3e","excerpt_chars":1200,"truncated":true,"excerpt":"How we built Cloudflare's data platform and an AI agent on top of it How we built Cloudflare's data platform and an AI agent on top of it 2026-05-28 Brian Brunner Dmitry Alexeenko Matt Moen 12 min read This post is also available in 日本語 and 한국어 . Cloudflare processes more than a billion events every second. Our network spans 330+ cities in 120+ countries. Behind every HTTP request, every Worker invocation, every R2 read operation, there is data, and a lot of it. For years, that data was not very easy to access. It lived in dozens of production databases, ClickHouse clusters, Kafka streams, Google Cloud buckets, BigQuery datasets, and a long tail of pipelines. To answer a simple question like \"How many domains that signed up today are in the Top 100 by traffic?\", an analyst at Cloudflare had to know which system to ask, what credentials to use, what query language to write, and whether the data they were looking at was sampled, fresh, or seven-days stale. As a result, it was difficult to glean informed insights from the data. To solve this problem, we built two in-house tools: Town Lake, Cloudflare's unified data analytics platform, and Skipper, an AI data agent that runs on..."},"evidence_pages":[{"url":"https://blog.cloudflare.com/our-unified-data-platform/","final_url":"https://blog.cloudflare.com/our-unified-data-platform/","title":"How we built Cloudflare's data platform and an AI agent on top of it","http_status":200,"content_type":"text/html","capture_method":"plain","fetched_at":"2026-06-07T21:14:08.444279+00:00","bytes":317482,"raw_path":"0f6c77546e58fefc81cad98b09fa14f8f302bc8e7e43c742fd702ca345e4d083.html","content_hash":"1a337643d1a09c16b315cc5a475fb7ecf5c8c1f2df805101e3a4237d5e7cee3e","excerpt_chars":1200,"truncated":true,"excerpt":"How we built Cloudflare's data platform and an AI agent on top of it How we built Cloudflare's data platform and an AI agent on top of it 2026-05-28 Brian Brunner Dmitry Alexeenko Matt Moen 12 min read This post is also available in 日本語 and 한국어 . Cloudflare processes more than a billion events every second. Our network spans 330+ cities in 120+ countries. Behind every HTTP request, every Worker invocation, every R2 read operation, there is data, and a lot of it. For years, that data was not very easy to access. It lived in dozens of production databases, ClickHouse clusters, Kafka streams, Google Cloud buckets, BigQuery datasets, and a long tail of pipelines. To answer a simple question like \"How many domains that signed up today are in the Top 100 by traffic?\", an analyst at Cloudflare had to know which system to ask, what credentials to use, what query language to write, and whether the data they were looking at was sampled, fresh, or seven-days stale. As a result, it was difficult to glean informed insights from the data. To solve this problem, we built two in-house tools: Town Lake, Cloudflare's unified data analytics platform, and Skipper, an AI data agent that runs on..."}],"related_signals":[{"id":"224fa7ff-e825-4f71-92de-ad4ed336e6e4","url":"https://onlylabs.fyi/signals/224fa7ff-e825-4f71-92de-ad4ed336e6e4","source_url":"https://blog.cloudflare.com/private-origins-dns-routing/","title":"Route public traffic to private applications with Cloudflare","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"cloudflare","name":"Cloudflare (Workers AI)","category":"neocloud"},"occurred_at":"2026-06-10T13:00:00+00:00","first_seen_at":"2026-06-11T07:01:30.73661+00:00","date_source":"rss.item_date"},{"id":"19c1aa86-cbcf-49c0-ba43-9bdb6b848150","url":"https://onlylabs.fyi/signals/19c1aa86-cbcf-49c0-ba43-9bdb6b848150","source_url":"https://blog.cloudflare.com/frontier-model-defense/","title":"Defend against frontier cyber models: Cloudflare's architecture as customer zero","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"cloudflare","name":"Cloudflare (Workers AI)","category":"neocloud"},"occurred_at":"2026-06-09T06:00:00+00:00","first_seen_at":"2026-06-10T07:01:36.764443+00:00","date_source":"rss.item_date"},{"id":"b7c25abb-905a-4512-be1c-728c37aec267","url":"https://onlylabs.fyi/signals/b7c25abb-905a-4512-be1c-728c37aec267","source_url":"https://blog.cloudflare.com/realtime-threat-intel-waf-rules/","title":"Turning Cloudflare’s threat indicators into real-time WAF rules","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"cloudflare","name":"Cloudflare (Workers AI)","category":"neocloud"},"occurred_at":"2026-06-08T13:00:00+00:00","first_seen_at":"2026-06-09T07:00:44.379079+00:00","date_source":"rss.item_date"},{"id":"0a3c44ce-32db-4ae9-b9a5-cdba5188203e","url":"https://onlylabs.fyi/signals/0a3c44ce-32db-4ae9-b9a5-cdba5188203e","source_url":"https://blog.cloudflare.com/ai-gateway-spend-limits/","title":"Your AI bill is out of control. Cloudflare can fix it now. ","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"cloudflare","name":"Cloudflare (Workers AI)","category":"neocloud"},"occurred_at":"2026-06-05T13:00:00+00:00","first_seen_at":"2026-06-05T22:32:14.118742+00:00","date_source":"rss.item_date"},{"id":"1eb2b6b6-5c21-47f0-a7fc-71b8badf109c","url":"https://onlylabs.fyi/signals/1eb2b6b6-5c21-47f0-a7fc-71b8badf109c","source_url":"https://blog.cloudflare.com/voidzero-joins-cloudflare/","title":"VoidZero is joining Cloudflare","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"cloudflare","name":"Cloudflare (Workers AI)","category":"neocloud"},"occurred_at":"2026-06-04T12:59:00+00:00","first_seen_at":"2026-06-05T22:32:14.118742+00:00","date_source":"rss.item_date"},{"id":"b2985d85-f194-41f3-a7f1-577c6aa0eedc","url":"https://onlylabs.fyi/signals/b2985d85-f194-41f3-a7f1-577c6aa0eedc","source_url":"https://blog.cloudflare.com/enforce-first-as-bgp/","title":"Enforcing the First AS in BGP AS_PATHs","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"cloudflare","name":"Cloudflare (Workers AI)","category":"neocloud"},"occurred_at":"2026-06-03T17:00:00+00:00","first_seen_at":"2026-06-05T22:32:14.118742+00:00","date_source":"rss.item_date"}]}