Blog

Historias, ideas y artículos técnicos del equipo de Evidoc.

· Founder

Oxford in Nature: The Friendlier You Make a Chatbot, the More It Lies

A new Oxford Internet Institute study published in Nature analyzed 400,000+ chatbot responses across five models. Warm, empathetic models made 10–30% more factual errors and were 40% more likely to agree with users' false beliefs. The fix isn't a colder bot — it's a grounded one.

ai-hallucination customer-support ai-risk research grounding verified-ai
· Founder

Sullivan & Cromwell Filed 40+ AI Hallucinations in Court. Self-Verifying AI Would Have Caught Every One.

A top-ranked lawyer at one of the world's most elite law firms submitted a court filing with over 40 fabricated citations generated by AI. The errors were caught by opposing counsel — not by the firm's own safeguards. Here's how self-verifying AI prevents this from ever happening.

ai-hallucination legal ai-risk case-study verified-ai
· Evidoc Team

Introducing the Evidoc API: Verifiable Document Intelligence for Your Product

Embed Evidoc's Knowledge-Graph reasoning engine into your own product, agent, or pipeline. Three retrieval routes, click-to-verify citations, secured behind a managed API gateway. Prepaid credits, pay as you go — start for $1.

api developers platform graphrag integrations
· Founder

Your Support Team Spends 20% of Their Day Searching for Answers. Here's How to Fix It.

Support engineers waste hours hunting through documentation. With 100K+ pages of docs, the answer exists — finding it is the bottleneck. Self-verifying AI with exact citations changes the equation.

technical-support knowledge-management documentation productivity ai-search
· Founder

Air Canada Got Sued for Their Chatbot's Wrong Answer. Here's How to Prevent It.

In 2024, a tribunal ruled Air Canada liable for misleading chatbot advice. With the EU AI Act enforcing compliance by August 2026 (fines up to €15M for transparency violations), every company with an AI chatbot needs a verification layer. Here's how self-verifying AI solves both liability and compliance.

chatbot-liability customer-support ai-risk case-study eu-ai-act compliance
· Evidoc Team

How Evidoc Finds Answers Across Documents: Knowledge Graphs and Mathematical Reasoning

A look inside Evidoc's retrieval engine — how Knowledge Graph algorithms find connections across documents that keyword search and vector similarity miss.

technology knowledge-graph deep-reasoning
· Founder

Why I Built Evidoc: The Missing Layer Between AI and Trust

Every AI chat tool can summarize your documents. None of them let you click a sentence and see it highlighted on the original page. That's the gap Evidoc fills.

founder-story product citations