Explainers
Why answers from your own content beat a general chatbot
A general chatbot answers from what it learned in training. A space answers from your documents and shows its sources. When each one fits.
Ask a general chatbot about your company's refund policy and it will give you a confident answer about refund policies in general. It has never seen yours. A space has, because you put it there.
Two ways an AI can answer
- A general chatbot answers from what it learned in training: a huge, fixed snapshot of public text. It knows a lot about the world and nothing about your files.
- A space first finds the passages in your content that match the question, then has the AI answer from those passages and cite them. This approach is called retrieval-augmented generation, or RAG.
Why that matters
- Specific answers. Your figures, your terms, your dates, not an average of the internet.
- Checkable answers. Every claim points to a numbered source, so you can confirm it in seconds.
- Honest gaps. If your content doesn't cover the question, the answer says so instead of guessing. Any general knowledge it adds is labelled.
- Always current. Add a new document and the next answer can use it. There's no waiting for a model update.
When a general chatbot is the better choice
For brainstorming, explaining a general concept, or writing from scratch, a general chatbot is fine. It doesn't need your files for that. Reach for a space when the answer has to come from specific material you have and others don't.
Getting the most from it
- Add the documents the answer should come from, and nothing it shouldn't.
- Ask direct questions in plain language.
- Open the citations for anything you'll act on.
We don't train models on your content. To answer, the relevant passages are sent to third-party AI providers. The privacy policy has the details.