Sai Krishna Rallabandi argues that today's agents usually serve one person, while future assistants may participate in group chats and wearable conversations. Examples from an agent he calls Judith show why the same reply might belong in a private message rather than a shared thread, and why a group assistant must track changing context across participants.
Rallabandi describes prompt injectionPrompt injection occurs when untrusted content attempts to redirect an AI system's behaviour beyond the authority of that content. and the combination of seemingly safe tools as risks when an agent reads group messages, pages and files. He proposes checking potentially sensitive actions at the tool boundary, separating untrusted data from instructions, and supplementing deterministic rules with a learned classifier. The reported paper results and benchmark improvements are claims from the talk, not independently verified here.
He then turns to memoryAI agent memory is stored information that an agent can retrieve and use across steps, sessions, or changing contexts. and privacyData privacy governs how personal, confidential, or sensitive information is collected, used, shared, retained, and protected in AI systems.: extracting useful factsInformation extraction identifies selected facts and relationships in source material and converts them into a structured form. from conversations, reassessing relevance as plans change, and deciding what the agent should forget or retrieveRetrieval is the process of selecting relevant stored information and returning it to an AI system for the current task.. He proposes shared memory with user-specific adapters and a classifier to choose when and to whom the agent speaks. The talk presents these as design ideas; it does not demonstrate that learned adapters alone enforce access permissions.
Watch on YouTube




