Blog

Everyone’s obsessing over the same question right now: “How do we get more people in the business using AI?” Because on paper it’s brilliant. It can bash out first drafts, summarise a mountain of info, untangle code, and generally take the boring weight off people’s shoulders so they can do the higher-value stuff.

index is not “just an AI layer on top of your docs” If you’ve taken some time to look at what we do and thought, “Hang on… can’t we just add a copilot / RAG / search upgrade and call it done?”, you’re forgiven, because we've heard this a few times now - hence the blog post!

AI rarely fails because the model is “dumb”, it fails because the knowledge it’s pulling from is messy. If you’ve ever had an AI answer at work that sounded confident but made you think “hang on… is that actually true?”, you’ve hit the real issue: shaky inputs create shaky outputs. In this short video I explain why, in 2025/2026, enterprise AI is only as trustworthy as the knowledge base behind it, and why duplicates, contradictions and outdated docs quietly turn into errors,

Here’s the reality in 2025/2026: there isn’t one universal “where does AI gets its facts from?” because most frontier labs don’t fully disclose their training mixes anymore. But we can anchor this in what’s publicly documented and what regulators/researchers keep pointing at. You know what people get wrong about AI? They think it “looks things up” like a clever librarian. Most of the time it doesn’t. Most of the time it’s answering from whatever got baked into it during trai