Verbiage clarity edits for LLM chatbots use case

Co-authored-by: Arjun Hassard <arjunhassard@gmail.com>

Author: mzkrasner

docs/composedb/examples/taco-access-control.mdx

@@ -21,7 +21,7 @@ TACo’s encrypt/decrypt API – [taco-web](https://github.com/nucypher/taco-web
 
 - **IoT event streams:** Let data flow from sensors to legitimate recipients, without trusting an intermediary server to handle the routing and harvest sensitive (meta)data. For example, a medical professional can be issued a temporary access token if the output data from a patient's wearable device rises above a certain threshold.
 
-- **LLM chatbots:** Messages to and from a chatbot should be 100% private, not mined by a UX-providing intermediary. Harness Ceramic's web-scale transaction processing and TACo's per-message encryption granularity to provide a smooth and private experience for users of LLM interfaces.
+- **LLM chatbots:** Messages to and from a chatbot should be 100% private, not mined by a UX-providing intermediary. Harness Ceramic's web-scale transaction processing and TACo's per-message encryption/condition granularity to provide a smooth and safe experience for users of LLM interfaces.
 
 ## Example Application & Repo