The Commitment Engine: A Practical Control Plane for Enterprise AI
Enterprise AI is moving beyond answering questions. Agents now retrieve data, call tools, recommend actions, modify workflows, and influence customer outcomes.
That changes the architecture problem.
An enterprise AI system is not merely a workflow engine. It is a commitment engine: a system that must know what it is allowed to attempt, what it is allowed to claim, when it crosses a liability boundary, and how it can prove its decision later.
In this practical architecture session, Rohit Bhardwaj introduces a control-plane model for governing AI agents at scale. Participants will learn how to connect authority, policy, evidence, freshness, cost, human approval, and operational controls into one coherent design.
Using a realistic AI-commerce-agent scenario, the session follows an agent that wants to answer a customer, retrieve policy, inspect payment and inventory status, and issue a refund. Then reality changes: evidence becomes stale, policies conflict, a payment is ambiguous, retries rise, and the agent’s tool-call budget is nearly exhausted.
Rather than asking only, “Is the service up?”, we ask the more important question: Is the system still allowed to act?
Attendees will use practical artifacts from the System Design with AI Interview Guide companion lab: the Commitment Engine Answer Template, Liability Boundary Map, Admissibility Contract, Freshness Clocks Template, Churn Budget Template, ROCS Loop, Stop Authority Template, and Decision Replay Card.
The outcome is a repeatable method for designing enterprise AI systems that can act, defer, stop, explain, and earn trust.
Learning objectives
Participants will be able to:
- Identify the commitment boundary—the moment a system stops attempting and starts owing.
- Define the authority, policy, evidence, and freshness requirements needed before an agent may act.
- Apply churn budgets to bound retries, tool calls, fan-out, latency, and inference cost.
- Design a capability-scoped stop-authority ladder: Normal, Conservative, Defer, Freeze, Human Review, and Re-enable.
- Create a Decision Replay Card that proves why the system acted, what it knew, and what could reverse the outcome.
- Use ROCS—Reliability, Observability, Cost, and Sustainability—as one operating control loop rather than four disconnected dashboards.
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