When Search Makes Decisions with AI
Enterprise RAG systems increasingly influence customer answers, policy interpretations, recommendations, and business actions. But a fluent, cited answer can still be unsafe if it relies on stale policy, unauthorized data, a superseded document, or an incomplete view of the truth.
This interactive session reframes RAG as an evidence-and-decision system. Participants examine a realistic stale-answer failure and redesign the retrieval path using source authority, freshness clocks, entitlement-aware access, lexical and semantic search, Graph RAG, structured data, citations, decision receipts, and safe refusal rules.
Most RAG talks focus on embeddings, chunking, vector databases, and prompts. Those are necessary—but not enough when AI influences real customers or business outcomes. The hard enterprise question is not “Did we retrieve something relevant?” It is:
“Was this evidence authorized, current, applicable, and strong enough for the AI to make this claim or recommendation?”
Without these controls, a system can look healthy—fast responses, good relevance, attractive citations—while exposing private data, applying an expired policy, or making promises the organization cannot defend.
Value for participants:
- Learn how to prevent stale, superseded, or unauthorized evidence from reaching AI context.
- Understand when to use BM25, semantic retrieval, Graph RAG, and structured system-of-record data together.
- Design a practical evidence graph that captures ownership, policy versions, scope, conflicts, and applicability.
- Separate the AI’s role in synthesizing evidence from policy’s role in allowing a decision.
- Build citations that can be checked, and decision receipts that explain why the AI was allowed to respond.
- Define when the system should answer, ask for clarification, defer, refuse, or escalate to a human.
- Take away reusable architecture artifacts: Source Authority Map, - Freshness Clocks, Admissibility Contract, Retrieval Ensemble Map, Citation and Decision Receipt, and Refusal/Stop-Authority Ladder.
About Rohit Bhardwaj
Rohit Bhardwaj is a Director of AI & Data Architecture at Salesforce, where he focuses on enterprise AI, agentic systems, cloud-native architecture, distributed systems, data platforms, security, and large-scale transformation.
Over his career, Rohit has designed and led complex enterprise platforms across AWS, Google Cloud, microservices, real-time data, API ecosystems, resilient distributed systems, and AI-enabled architectures. His work increasingly focuses on the challenges enterprises face as software evolves from deterministic services to AI-native and agentic systems—particularly around reliability, governance, evidence, security, observability, cost, and safe autonomy.
Rohit is the author of System Design with AI Interview Guide: Designing Scalable, Agentic, and Defensible Systems, published by Apress. The book presents a modern approach to system design covering scalability, distributed systems, AI architecture primitives, security, reliability, economics, agentic systems, and real-world architectures including e-commerce, ride sharing, payments, fraud detection, messaging, video streaming, file storage, and search. (Springer Link)
Book:
Amazon: https://a.co/d/09Zs1twa
Publisher / Springer Nature: https://link.springer.com/book/10.1007/979-8-8688-2782-2
O'Reilly: https://learning.oreilly.com/library/view/system-design-with/9798868827822/
Rohit is also an O’Reilly instructor and a frequent speaker at technology conferences including No Fluff Just Stuff, UberConf, GIDS, and other international events. His talks focus on practical architecture lessons from building and operating complex systems, including AI control planes, trusted agents, inference at scale, evidence-first RAG, AI security, distributed-system failure, and AI-era software architecture.
As a trusted advisor and architecture leader, Rohit works at the intersection of business strategy and deep technical architecture—helping teams translate complex business problems into scalable, resilient, secure, and economically sustainable systems.
Rohit holds an MBA in Corporate Entrepreneurship from Babson College and graduate-level education in Computer Science from Boston University and Harvard University.
Connect with Rohit:
LinkedIn: http://linkedin.com/in/rohit-bhardwaj-cloud
X / Twitter: @rbhardwaj1