Claude Architecture Bootcamp
Security, Evals, and Governance
Claude can now understand repositories, write code, call tools, retrieve enterprise knowledge, and complete multi-step workflows.
That creates enormous opportunity—but also new architecture, security, and governance risks.
This full-day workshop shows architects, developers, and technical leaders how to use Claude safely and effectively in real production environments.
You will begin with Claude Code and learn how to move beyond uncontrolled “vibe coding” into governed engineering workflows using CLAUDE.md, plan-first development, tests, pull requests, and CI/CD quality gates.
You will then expand into the complete Claude architecture landscape:
- Claude APIs and structured outputs
- Agent SDK and bounded agent workflows
- MCP tools and permission controls
- Production RAG and trusted evidence
- Prompt injection and data protection
- Evals, observability, cost, and latency
- Release governance and rollback
- Production-readiness decisions
This is not a feature tour.
This is a practical architecture bootcamp focused on one essential question:
How do we give Claude powerful capabilities without giving it uncontrolled authority?
Who Should Attend
This workshop is ideal for:
- Software and enterprise architects
- Senior developers and technical leads
- AI and platform engineers
- DevOps and DevSecOps professionals
- Engineering managers
- Teams adopting Claude Code, MCP, RAG, or AI agents
No deep machine-learning experience is required.
What You Will Learn
Participants will learn how to:
- Use Claude Code as a governed engineering assistant.
- Create effective CLAUDE.md repository guidance.
- Apply architecture, testing, security, and maintainability guardrails.
- Design safe Claude API and Agent SDK workflows.
- Build MCP tools with least privilege and approval gates.
- Design grounded RAG systems with trusted, current evidence.
- Protect against prompt injection, secrets leakage, and unsafe tool use.
- Evaluate correctness, groundedness, safety, latency, and cost.
- Trace prompts, sources, tool calls, decisions, and failures.
- Decide whether a Claude-powered system is truly ready for production.
Workshop Format
The workshop includes:
- Architecture demonstrations
- Hands-on design exercises
- Claude Code governance examples
- MCP tool-risk classification
- RAG and security simulations
- Evaluation scorecards
- Production-readiness scenarios
- A final architecture defense
Participants leave with a practical playbook for introducing Claude into engineering teams without losing architecture discipline.
Full-Day Agenda
Sessions
Claude Code: From Vibe Coding to Governed Engineering
Break
Claude APIs, Agent SDK, and MCP Tool Governance
Break
RAG, Security, Evals, and Observability
Break
Production Delivery and Architecture Defense
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 »