Anthropic's CCA Exam as a Field-Guide for Agentic Engineering
Frank Coyle
- When
- Thursday, July 211:10 AM – 11:30 AM · 20 min
- Where
- Track 8San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
Anthropic's CCA Exam: A Field-Guide for Agentic Engineering The Claude Certified Architect (CCA) exam distills what Anthropic has learned from working with the AI companies shipping agents to production — the patterns that work, the anti-patterns that quietly burn tokens and trust, and the architectural decisions that separate demos from systems you'd stake a quarter on. This talk treats the exam as a field guide for agentic engineering, whether or not you ever sit for it. We'll walk through the five competency domains the exam tests — Agentic Architecture, Tool Design and MCP Integration, Claude Code, Prompt Engineering, and Context Management — with particular emphasis on multi-agent orchestration, subagent delegation, tool schema design, and lifecycle hooks. We'll then work through the six real-world scenarios the exam uses to probe judgment, each organized around an anti-pattern: the seductive-but-wrong move that looks reasonable until it costs you a production incident. Attendees leave with a working mental model of the agentic surface area and a checklist of the failure modes that matter most when moving from prototype to production. Who should attend: engineers and architects building agentic systems with Claude or other frontier models, technical leads evaluating agent designs, and developers considering the CCA credential.
Speaker
Lecturer, UCALBerkeley / Founder AI/Edge, UCAL Berkeley
Frank Coyle (also known as drC) is a recently retired computer science professor who spent 32 years at Southern Methodist University, where he was repeatedly recognized as a standout teacher, before moving into part-time online teaching generative AI and large language models at Berkeley on. He is also a visiting professor at the University of Bologna, where he teaches generative AI in the graduate school of business. His path to AI runs through an unusual range of disciplines: psychology, neuroanatomy and physiology, and computer science. That cross-domain background shapes how he thinks about intelligent systems—drawing connections others miss, from neural architecture to software design patterns. His current work focuses on the practical engineering of agentic AI systems and the architectural gaps that cause them to fail. He argues that many agent failures are symptoms of a missing layer: formal ontologies acting as logical guardrails around probabilistic reasoning. He also teaches AI to district attorneys and formerly-incarcerated students. (150 words)
More in Agentic Engineering
- DeepSWE: expert code datasetsThursday, July 2 · 10:45 AM – 11:05 AM · Track 8
- MCPs, CLIs, and Skills: Choosing the Right Tooling Layer for Agentic DevelopmentThursday, July 2 · 11:10 AM – 11:30 AM · Main Stage
- Auth for Agents: Unblock Autonomous AI with auth.mdThursday, July 2 · 11:40 AM – 12:00 PM · Main Stage
- Guide, Verify, Solve: The Engineering Discipline Agentic Development DemandsThursday, July 2 · 11:40 AM – 12:00 PM · Track 8
- Benchmarking Coding Agents on New vs Legacy Code basesThursday, July 2 · 12:05 PM – 12:25 PM · Track 8
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.