From REST to Reasoning Agents: Designing APIs for the AI Era
APIs have powered modern applications for decades, but AI agents and LLMs are rewriting the rules. Traditional RESTful patterns aren’t enough when your consumers are autonomous systems that demand machine-readable contracts, contextual hints, and self-discovery. This talk explores how to design APIs that work seamlessly for humans and reasoning agents alike. You’ll learn practical techniques for contract-first design, metadata enrichment, hypermedia navigation, and avoiding pitfalls like “agent drift.” Future-ready APIs start here.
APIs are no longer just for apps and developers—they’re now serving reasoning agents, LLMs, and automation platforms. To prepare for this shift, API design must evolve. In this session, we’ll explore:
- Why REST needs an upgrade → traditional design patterns weren’t built for autonomous consumers.
- Contract-first design → how OpenAPI/Swagger extensions make APIs machine-readable and agent-friendly.
- Function-calling formats → structuring endpoints so LLMs can parse, chain, and execute them reliably.
- Metadata enrichment → annotating APIs with contextual hints to improve interpretability for agents.
- Hypermedia navigation → when patterns like HAL and HATEOAS help AI agents self-discover functionality.
- Agent drift pitfalls → why autonomous consumers misinterpret APIs and how to mitigate it.
- Practical patterns for tomorrow’s APIs → real-world strategies to serve both human developers and reasoning agents.
Audience: Backend developers, API designers, architects
Takeaways:
- Design APIs that are both human- and machine-friendly
- Apply contract-first principles for LLM discoverability
- Avoid common pitfalls like agent drift and misinterpretation
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 »