Speaker Topics - No Fluff Just Stuff

ChatGPT for Software Architects & Developers 2025 — Build Agentic, Secure AI

In 2025, ChatGPT is no longer just a chatbot—it’s an agent platform that integrates with your stack (via MCP, Realtime API, Azure Agent Service, Amazon Q Dev, Gemini Code Assist, Claude 3.5).
Software Architects and Developers who can harness this ecosystem will design faster, code safer, and ship smarter.

This workshop takes you from basic prompting to building a full-stack AI-powered agent with guardrails, observability, and enterprise-ready governance—all in one day.

Who Should Join?

  • Software Architects – to shape AI-augmented blueprints
  • Enterprise Architects – to design AI-ready platforms with governance
  • Technical Leads & Senior Developers – to scale code, reviews, and CI/CD with AI copilots
  • IT Managers & Engineering Leaders – to drive digital transformation with secure AI workflows
  • AI Enthusiasts – to future-proof your career with agentic systems skills

What You’ll Learn

  • Master prompt engineering that passes acceptance tests
  • Build agentic workflows using MCP tool servers and the Realtime API
  • Compare GPT-5, Claude 3.x, Gemini 2.x, Amazon Q Dev, Azure Agent Service for enterprise use
  • Implement RAG 2.0 with evals & structured outputs
  • Secure your systems with OWASP LLM Top 10 (2025) red-team/blue-team exercises
  • Integrate AI into CI/CD pipelines, IDEs, and architectural documentation
  • Optimize costs, observability, and governance for large-scale AI adoption

Outcomes
By end of day, you will leave with:

A working repo of an MCP-connected agent

A security checklist mapped to OWASP LLM Top 10

Hands-on experience with AI copilots across major vendors

Playbooks for cost, governance, and evaluation

Confidence to lead AI-first architecture initiatives in your org

Agenda

Module 1 — The New AI Landscape

  • GPT-4o/o3, Claude 3.5, Gemini 2.5, Amazon Q Dev, Azure Agent Service
  • Trade-offs in cost, latency, context, and governance

Module 2 — Agentic Architecture with ChatGPT

  • Hands-on: Build a ChatGPT agent using MCP + Realtime API
  • Connect to repos, tickets, APIs — simulate enterprise workflows

Module 3 — RAG 2.0 & Structured Outputs

  • Retrieval augmentation patterns for architecture tasks
  • Eval harnesses, JSON-strict outputs, regression gates

Module 4 — SDLC Integration with AI Copilots

  • Amazon Q Dev for code refactor
  • Gemini Code Assist “Agent Mode” for multi-file edits
  • Azure Agent Service for gated deploys

Module 5 — Security & Risk

  • Prompt-injection red team exercise
  • OWASP LLM Top 10 walkthrough
  • Guardrails for data and compliance

Module 6 — Observability & Governance

  • Cost controls, tracing, quotas, model routing
  • AI SLOs & governance dashboards

Capstone Lab (90 min)
Build a secure MCP-powered ChatGPT Agent that:

  • Reads a repo → files a ticket → generates a patch → passes evals → resists injection.
  • Optional: connect via Realtime API voice call (SIP) for a live hotline demo.

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 »