From AI Demos to Defensible Decisions
AI agents rarely fail with a visible outage. They can return 200 responses while acting on stale evidence, retrying into duplicate side effects, using an unauthorized tool, or making a customer commitment the organization cannot later defend.
This hands-on session shows how to architect for that reality.
Rather than beginning with a model, prompt, or orchestration framework, participants start with the system’s promise: what is it allowed to attempt, what is it allowed to claim, and where does the platform stop trying and start owing?
Using a live AI-commerce scenario, we will design an agent that must answer a customer, evaluate a return, and potentially issue a refund. Then we will introduce realistic pressure: conflicting policy versions, stale inventory, ambiguous payment status, weak evidence, and a runaway tool-call loop.
Participants will use five practical artifacts from the companion lab: a Liability Boundary Map, Admissibility and Freshness Contract, Churn Budget, Stop Authority Ladder, and Decision Replay Card. The session closes by showing how the system can remain useful while safely deferring, freezing liability actions, or escalating to human review.
Attendees leave with a repeatable method for building AI systems that can act, stop, explain, and be trusted.
Learning outcomes:
- Identify the commitment boundary before designing components.
- Define evidence, authority, freshness, and policy required for AI action.
- Bound retries, fan-out, tool calls, latency, and cost.
- Design capability-scoped stop and re-enable controls.
- Create replayable proof for consequential AI decisions.
About Rohit Bhardwaj
Rohit Bhardwaj is Director of AI & Data Architecture at Salesforce, an O’Reilly instructor, and founder of AI Architect Circle. With 30 years of experience in software and enterprise architecture, he helps engineers, architects, and technology leaders make architecture decisions they can explain and defend.
His work brings together enterprise AI, agentic systems, data architecture, and distributed systems. He focuses on the decisions that determine whether a system remains reliable, secure, accountable, and economically sustainable when it encounters real-world demands.
Rohit’s talks and workshops explore practical questions: What happens when an AI agent acts on conflicting information? Can a failed payment be retried safely? Who can stop an autonomous action, and what evidence explains the decision afterward? His teaching connects these questions to architecture, customer trust, and business outcomes.
He is the author of System Design with AI Interview Guide: Designing Scalable, Agentic, and Defensible Systems, published by Apress. He also developed ARCHVIEW™, ROCS Loops™, and LLM-SHIELD™ to help teams structure architectural thinking and address the challenges of building trustworthy AI systems.
Through AI Architect Circle, Rohit extends this learning through live discussions, book walkthroughs, videos, and interactive architecture challenges. These challenges explore incidents such as payment timeouts and conflicting bookings, helping participants practice the judgment behind their design decisions.
Continue learning with Rohit
Join Rohit live on Saturdays at 9:00 a.m. Eastern
System Design with AI — Live with the Author is a free live podcast and Q&A series featuring practical system-design scenarios, AI architecture discussions, and questions from the community.
See the next session and register
Try an interactive architecture challenge
Put your design decisions under pressure and explore the consequences.
Explore the challenges
Explore AI Architect Circle
Find architecture lessons, videos, resources, and ways to continue learning.
Visit AIArchitectCircle.com
Read the book: Amazon · O’Reilly
Watch and connect: YouTube · Instagram: @aiarchitectcircle · LinkedIn · X / Twitter: @rbhardwaj1
More About Rohit »