Staging environment

Claude Certified Architect: Safety as Architecture

Hosted by Carmelo Iaria, Niharika Srivastav, and Sanjay Saxena

Wed, Oct 14, 2026

4:00 PM UTC (30 minutes)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Become an Agentic Architect
Carmelo Iaria
View syllabus

What you'll learn

Fail-close tools by blast radius

Match HITL and permissions to stakes. Prompt injection, write access, and compliance are design inputs.

Design the path, not a pile of agents

Pick a pattern — workflow, agentic, or augmented LLM — and decompose it so a teammate could implement it.

Put risk in the architecture, not a slide

Hazard, control, owner. GDPR, HIPAA, FedRAMP constrain the path — they are not a values appendix.

Why this topic matters

Forrester: the enterprise architect is now the human in the loop responsible for what agentic AI delivers. Labs cannot sell that. Models cannot own it. Capital is chasing people who put guardrails, HITL, and compliance on the path — not on a values slide after the demo. In 30 minutes you will fail-close the system so the organization can actually trust it. Lesson 4 of 5.

You'll learn from

Carmelo Iaria

Agentic Architect, Pearson SME, Startup Founder, 30 years of global experience

I help teams move from AI pilots to governed, production-grade agentic systems — through live programs and hands-on advisory.

Three decades across Europe, the US, and Brazil taught me one lesson: AI value is won in execution — clear scope, reliable multi-agent workflows, and governance that survives production.

I teach that discipline on Maven (Become an Agentic Architect, live workshops, Lightning Lessons, resources) through my AI-Assisted Multi Agent Development (AAMAD) Framework. I also work as a Fractional Chief AI Officer with teams that need embedded judgment, not generic advice — plus O’Reilly live sessions and Pearson certification-aligned programs.

Niharika Srivastav

AIGP, Certified AI Governance Practitioner

Niharika has spent 25+ years closing the gap between AI innovation and compliance approval. Former roles at Deloitte, Bank of America, Charles Schwab, and Blue Shield of California gave her deep enterprise experience. Now as Managing Director of Drishtee Foundation, she empowers 200,000+ rural women entrepreneurs with AI and digital tools.

She holds a Stanford Executive Leadership Program certificate, MBA from Delhi School of Economics, and engineering degree from Delhi College of Engineering. Her expertise spans portfolio delivery, AI implementation, cybersecurity, and compliance across highly regulated industries.

Niharika translates AI complexity into language legal teams understand and approve.

Sanjay Saxena

Chief AI Officer, Ex-Harvard, Deloitte, KPMG

Sanjay has spent 25 years in the room where AI projects get approved or killed. At Deloitte, KPMG, CVS Health, and Kaiser Permanente, he witnessed brilliant ideas die because teams couldn't speak the language of legal and compliance. That's why he created this course.

As Founder of Elevate AI, he helps businesses scale AI responsibly. He holds CISSP and PMP certifications, he did Executive MBA from Harvard Business School, and earned his engineering degree in India. His 25+ years span AI implementation, security, and enterprise architecture across highly regulated environments.

Sanjay breaks down complex concepts into frameworks students use immediately. He also hosts technology radio shows, believing that if you can't explain something simply, you don't understand it well enough.

See all products from Carmelo

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.