Architecting Trust: Layered Context and Security for Production AI Agents
Schedule
Thu Apr 30 2026 at 05:30 pm to 08:00 pm
UTC-07:00Location
Asana | Vancouver, BC
About this Event
This talk will dissect the architectural and machine learning engineering challenges of building trustworthy, multi-actor AI Agents that operate on sensitive user data. We will use Asanaβs "AI Teammates" and "Smart Chat" as a case study to demonstrate how we manage to simultaneously expand the operational context of our agents while rigidly enforcing data access controls.
Central Thesis: The systemβs core design principle is that the AI Agent never operates with elevated permissions, a guarantee achieved by structurally limiting its visibility to the intersection of the triggering user's access and the agent's own memberships.
Key Themes for ML Engineers:
- Advanced RAG and State Management: We will detail the agent's context assembly process, which moves beyond simple RAG to include dynamic, self-accumulated "Memories", the triggering event's full object context (serialized as XML), and previous execution summaries for continuity.
- Defense-in-Depth Access Control: We will explore a critical, three-layered defense model for data security in a high-throughput search environment:
- The Search Actor Model: Assigning distinct, permission-limited actors (DomainUser vs. AiTeammateExecution) to different AI types.
- Query-Time Filtering: Injecting the accessFilter directly into OpenSearch queries to eliminate inaccessible objects at the index level.
- Post-Query Re-Validation: A database-level re-check on all result IDsβthe ultimate defense-in-depth guarantee against index staleness or misconfiguration, ensuring no unauthorized object IDs ever reach the LLM.
Attendees will leave with concrete, battle-tested patterns for building secure, context-aware AI applications that satisfy the highest bar for enterprise data governance.
Agenda
π: 05:30 PM
Welcome + Networking
π: 06:30 PM
Opening Remarks from Chai Ravula, Head of Engineering, AI
Host: Chai Ravula
π: 06:40 PM
Panel: Architecting Trust: Layered Context and Security for Production AI Agen
Host: Chai Ravula
π: 07:15 PM
More Networking, Food & Drinks
Where is it happening?
Asana, 601 West Hastings Street, Vancouver, CanadaEvent Location & Nearby Stays:
EUR 0.00



















