AI System Design Under Pressure: Architecture Katas
Build the skills to make architectural decisions you can explain, test, and defend. This full-day, hands-on workshop brings together system design fundamentals and the challenges of enterprise AI, including scalability, data consistency, reliability, security, and cost.
Through an evolving enterprise case study and interactive design exercises, you’ll translate business requirements into architecture, compare alternatives, and evaluate trade-offs. You’ll define where AI can assist, what agents are authorized to do, and how systems should respond when dependencies fail or outcomes are uncertain.
You’ll tackle practical challenges from AI Architect Circle (https://www.aiarchitectcircle.com/challenges) to develop defensible AI solutions. These challenges put your decisions to the test: expose hidden assumptions, investigate failure scenarios, strengthen controls, and gather evidence to support your design.
Drawing on concepts from System Design with AI Interview Guide, the workshop culminates in a collaborative architecture review where you defend your decisions, respond to questions, and adapt to changing constraints.
You’ll leave with a practical design workbook, documented architectural decisions, and a repeatable approach to enterprise design reviews and system design interviews.
For: Software architects, technical leads, senior developers, and engineers designing enterprise AI systems.
What participants will learn
By the end of the workshop, participants will be able to:
- Frame a system design problem: Translate business goals, customer journeys, and operational constraints into requirements and measurable success criteria.
- Define architectural boundaries: Establish responsibilities, data ownership, interfaces, and the path from a request to a completed business outcome.
- Evaluate meaningful trade-offs: Compare alternatives across scale, consistency, latency, reliability, security, complexity, and cost.
- Bound AI authority: Distinguish recommendations from authorized actions and define permission checks, human escalation, and stopping conditions.
- Design for uncertain outcomes: Reason about retries, duplicate effects, recovery, reconciliation, and ownership of incomplete work.
- Support decisions with evidence: Connect architectural claims to calculations, scenario results, operational signals, and validation plans.
- Lead a constructive architecture review: Explain decisions clearly, respond to challenges, acknowledge uncertainty, and revise an approach when its assumptions change.
How participants will work
The workshop combines guided instruction, an evolving enterprise case study, interactive challenges, and peer review. Participants create and refine architectural artifacts throughout the day, using a shared problem to connect individual decisions to the behavior of the larger system.
The experience culminates in a collaborative design review. Participants present their architecture, discuss alternatives, explain failure and recovery behavior, and identify what still needs validation.
Connection to the book
The workshop draws on System Design with AI Interview Guide, applying its structured design approach and its treatment of distributed systems, AI architecture, trust, reliability, and economics.
The book provides a foundation for continued study, while the workshop gives participants direct practice applying those ideas to consequential design decisions.
What participants will take away
Participants will leave with:
- A completed design workbook containing requirements, diagrams, and key assumptions.
- Documented architectural decisions and trade-off comparisons.
- AI authority boundaries and failure-recovery scenarios.
- An evidence checklist and prioritized validation plan.
- A repeatable method for enterprise architecture reviews and system design interviews.
Who should attend
Software architects, enterprise architects, technical leads, senior developers, and engineers responsible for designing or reviewing AI-enabled systems.
Participants should be comfortable with APIs, databases, and basic distributed systems concepts. Prior experience building AI agents is helpful but optional.
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