I built a file format so AI answers cite an exact source sentence, or admit they don't know

1Key Takeaways

• RAG has a trust problem: a model answers fluently, cites nothing, and you can't tell fact from confident improvisation without manually checking the source docs.
• This gets worse, not better, with smaller models — they're more likely to fill gaps with something plausible, and less likely to hedge.
• I've been building AIPK , a package format that tries to close that gap — not by making the model smarter, but by making it provably grounded , sentence by sentence, or explicit about the fact that it….