How I Built Source-Backed Expert-Video Search on Cloudflare

A developer built Base2026, a source-backed expert-video search tool on Cloudflare, using D1, R2, Queues, Workflows, and Workers AI for transcription. The platform offers deterministic retrieval with attributable findings and bounded excerpts, while maintaining a strict public/private split to ensure evidence integrity.

AI-assisted production note:AI helped with drafting and packaging. The architecture, live capabilities, boundaries, and dated numbers were checked against the Base2026 release evidence. Useful SEO and AI-search knowledge often lives inside short-form video. Discovering a clip is easy. Remembering who said what, comparing it with another practitioner, and giving a teammate a source they can inspect is not. I built Base2026 https://base2026.dev/ around a narrower question: What did practitioners actually say about this topic? A useful result should retain the creator, a bounded excerpt, its context, the Base2026 record, and the original source. If the corpus cannot support a responsible answer, “not enough evidence” is a valid result. I did not want another answer engine. I wanted an evidence path a person could inspect, challenge, and revisit. The indexed sample is not the whole industry, and Base2026 does not present it as consensus. That limitation is part of the product, not a footnote. The public request, search, and delivery path runs on Cloudflare: The cloud intake path is deliberately separate. D1 and R2 hold bounded private state and media, Queues and Workflows coordinate retries, and Workers AI supports transcription. Identities, validation, and receipts stop a retry from silently becoming a different public record. public discovery → private D1 / R2 intake and dedupe → queued capture and transcription → evidence validation and review state → policy-bound excerpt projection → public D1 FTS5 → Worker pages, search API and JSONL Public search does not need a live model call for every visitor query. A request reaches the Worker, the Worker reads the public D1 layer or serves a static asset, and the visitor can open a stable evidence page or the original source. Base2026 exposes reviewed public records, bounded evidence, and source links. It is not a mirror of TikTok and not a transcript dump. The public/private split is architectural, operational, and editorial at the same time. The public release excludes: People should be able to inspect the evidence and return to the creator, while private source material stays private. Correction and removal paths are public product features for the same reason. The product direction is deterministic retrieval. For a fixed question, filter set, corpus version, and ranking version, I want the result to be explainable and reproducible. That is a different goal from generating the smoothest possible paragraph. Evidence Brief V1 and V2 are live deterministic retrieval endpoints: attributable findings, bounded excerpts, original-source links, coverage, and ranking receipts. What I am not claiming is a free-form generative synthesis layer that invents conclusions beyond the public corpus. The current capabilities are D1 FTS5 search, stable public source pages, attribution, the read-only Evidence Brief API https://base2026.dev/api , public JSONL files, documented methodology, and correction or removal paths. The verified August 29 public readback recorded: The versioned static artifact contained 1,939 reviewed public insight cards. That was a different layer from the 83 projection cards in the August 29 live D1 snapshot. An independent review found that an earlier static file mixed those 1,939 reviewed rows with 524 non-public or needs review rows. The corrected release contained only the reviewed public set, and its builder rejects a non-public, review-held, or wrong-policy row before it can ship. The zero-full-transcript rule is as important as the larger numbers. The public layer can preserve claims, bounded excerpts, topics, time ranges, attribution, and original links without becoming an archive of every underlying source text. The public-safe code lives in the Base2026 GitHub repository https://github.com/offflinerpsy/base2026 . The August 29 dataset shipped through a reviewed pull request and a versioned release. Before deployment, the release suite checked generated pages, Worker behavior, TypeScript types, deterministic D1 import, Static Assets upload, forbidden paths, review holds, and secret patterns. Desktop and mobile browser QA then checked overflow, console errors, and broken requests. The live dataset page was read back for its canonical, indexability, heading, and Dataset structured data. Those checks answer unglamorous but essential questions: The public core is free to use and read-only. I do not describe the entire operation as cost-free: infrastructure, processing, review, and maintenance still consume resources. Cloudflare makes a compact edge architecture possible; release discipline is what makes that architecture credible. The next step is to keep improving deterministic retrieval and turn the Evidence Brief contract into a verified product experience only when its latency, attribution, and quality gates are real. Coverage and limits should remain visible. Original sources should remain one click away. “Not enough evidence” should remain possible. That is the larger lesson I am taking from building Base2026: infrastructure, data policy, and publishing discipline are not separate chores. Together, they shape the product a user can trust. If you work on SEO, GEO, AEO, or AI-search research, inspect the current public surface https://base2026.dev/workspace/ . I would value a concrete critique of the evidence boundary or its failure modes.