Designing Multi-User Agents for Group Chats and Wearables
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
prompt injection — An attack that hides instructions in content an AI will read — a webpage, email, or document — tricking it into following the attacker instead of the user.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
Why it matters
If you're building agents that sit in a group chat, shared workspace or wearable, this lays out two failure modes single-user designs don't surface: context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → bloat across many speakers, and cross-agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → information leakage where two safe capabilities combine into a disclosure path. The proposed per-user adapter guard model is a concrete alternative to regex-based redaction that misses injected or implied context.
Key quotes
“a shared assistant is not just a large model which is shared between different people but it's almost a new social contract”
Sai Krishna
“The memory is what the agent becomes and it's becoming in real time it's evolving in real time.”
Sai Krishna
“we can't secure an agentic system like we secure a large language model”
