Agentic AI Execution

Are you walking straight into the AI system design interview trap? Tanishq Singh joins Leena on the Agentic AI Execution Podcast to reveal how to scale RAG architectures and ace your tech interviews.Discover how to move past surface-level buzzwords and think in individual system components like chunking strategies, vector databases, and indexing algorithms. Whether you are a technical program manager (TPM) or an engineer, this episode breaks down how to balance cost, latency, time-to-first-token, and practical problem-solving to build reliable, production-ready AI systems.

**Timestamps:***

**00:00** – Introduction & Guest Welcome

* **02:22** – Why AI System Design Matters

* **04:05** – Thinking in Components & Scaling

* **13:50** – Key Interview Terms for PMs & TPMs

* **17:15** – Final Takeaways & Steering AI Tools🔗

RESOURCES & LINKS:

• Connect with Tanishq: https://www.linkedin.com/in/tanishq25/

• Connect with Leena: https://www.linkedin.com/in/leenaagarwal/

Sign up to cohort: https://aiengg.dev/

#llmsecurity #AI #InterviewReady #AgenticAIExecution

Are your AI agents ready for production, or are they about to go rogue?

In this episode, Leena sits down with Angie Jones, VP of the Agentic AI Foundation, at AGNTCon to discuss the massive shift happening in Agentic AI. They dive deep into real-world production challenges, including why token maxing is out, how guardrails and evals keep systems secure, and what standards like MCP (Model Context Protocol) and A2A mean for multi-agent workflows. Plus, they explore how software engineering is evolving from "vibe coding" into rigorous systems thinking.

⏱️ Timestamps & Key Topics:

00:00 — Introduction: Welcome to AGNTCon & MCPCon with Angie Jones

01:10 — AGNTCon Scale: Highlights from the 4,200+ attendee event and MCP/A2A maintainer homecoming

02:20 — Enterprise Shift: Moving from learning agents to governance, security, and cross-department sharing

03:40 — Guardrails & Observability: Addressing wrong answers and using Agent Gateway & Router

04:50 — Permission Chaos: Examining news stories of agents tweaking permissions and opening gates

05:55 — Model Assumptions & Risks: Goal-driven models versus human morals, judgment, and safety risks

07:00 — Proactive Testing: Using Hugging Face's OpenEnv playground to simulate scenarios

08:00 — The Power of Evals: Best practices for testing non-deterministic systems without letting models write their own evals

09:45 — The Death of Token Maxing: The financial wake-up call and the pivot back to efficient engineering principles

11:15 — Vibe Coding vs. Systems Thinking: How software engineering is evolving and why systems thinking is critical

13:00 — Solving Multi-Agent Chaos: Moving away from "YOLO" loops toward Agent-to-Agent (A2A) communication protocols

14:15 — Monday Morning Advice: What engineers should start building and thinking about next

15:00 — What's Next: Angie's upcoming agent course (MCP & A2A) and the MCP Dev Summit in Nairobi

🔗 RESOURCES & LINKS:

• Connect with Angie : https://www.linkedin.com/in/angiejones/

• Connect with Leena: https://www.linkedin.com/in/leenaagarwal/

#AgenticAI #AGNTCON #MCPCON

In Episode 34 of the Agentic AI Execution Podcast, host Leena Agarwal is joined by Jason P. Yoong (co-founder of Level Up and former Amazon leader) to explore how professionals can navigate market anxiety, AI wash, and the modern job search.Stop sending blind cold applications. Instead, Jason breaks down the tactical mindset shifts required to build real career leverage, become "email forwardable," and use AI as a strategic thought partner rather than a shortcut.

⏱️ Timestamps & Key Topics:

00:01 — Introduction: Navigating career uncertainty and change in the AI era

00:47 — Defining success, life tenets, and balancing parenthood as a "100x dad"

03:08 — Time management, energy management, and being fully present while building05:56 — How to use AI tools (like Claude/Codex) as a rigorous thought partner for first drafts and deep work

08:36 — Real productivity gains vs. corporate chaos: What CXOs and AI-native founders are getting right

12:21 — Stop Applying Cold: Why proof of results is table stakes and how to become "email forwardable"

16:45 — The relationship-building playbook: How Jason built a deep professional partnership with Ethan Evans through high-standards networking

24:21 — The book recommendation strategy and how to genuinely connect with leaders

27:44 — A 5-year outlook on AI, education, human connection, and the rise of anti-AI business playbooks (live sports and community)

🔗 Connect

• Connect with Jason P. Yoong: https://www.linkedin.com/in/jasonyoong/

• Connect with Leena Agarwal: https://www.linkedin.com/in/leenaagarwal/

#AgenticAI #CareerAdvice #TechLeadership #JobSearch #Networking

In this episode, Ankit—former engineer, award-winning AI researcher, and DevRel leader at Rime— break down the harsh realities of scaling Agentic AI We cover why AI models excel inside constraints but struggle with enterprise edge cases, how developers should position themselves in the age of LLMs, and why transparently admitting your product’s weaknesses builds ultimate customer trust

---

🎯 KEY TOPICS COVERED

:00:00 - Introduction & Ankit's Career Journey

00:36 - From Full-Stack Developer to AI Researcher to DevRel04:55 - How Budding Developers Can Thrive in the Agentic AI Era

05:55 - Will AI Ever Replace Human DevRel?

08:20 - Combating "AI Slop" & Creating Genuine High-Quality Content

09:28 - Behind the Scenes: Lessons from a Financial AI Hackathon

11:12 - The Gap Between AI Demos vs. Real Production Systems

15:13 - First 90 Days: How B2B AI Startups Can Scale Product-Market Fit

18:43 - Why B2B Founders Must Embrace Product Weaknesses to Build Trust

In this episode, Ankit—former engineer, award-winning AI researcher, and DevRel leader at Rime— break down the harsh realities of scaling Agentic AI We cover why AI models excel inside constraints but struggle with enterprise edge cases, how developers should position themselves in the age of LLMs, and why transparently admitting your product’s weaknesses builds ultimate customer trust

---

🎯 KEY TOPICS COVERED:

00:00 - Introduction & Ankit's Career Journey

00:36 - From Full-Stack Developer to AI Researcher to DevRel

04:55 - How Budding Developers Can Thrive in the Agentic AI Era

05:55 - Will AI Ever Replace Human DevRel?

08:20 - Combating "AI Slop" & Creating Genuine High-Quality Content 09:28 - Behind the Scenes: Lessons from a Financial AI Hackathon

11:12 - The Gap Between AI Demos vs. Real Production Systems

15:13 - First 90 Days: How B2B AI Startups Can Scale Product-Market Fit

18:43 - Why B2B Founders Must Embrace Product Weaknesses to Build Trust

In Episode 32 of the Agentic AI Execution Podcast, Mitesh breaks down what actually happens when AI touches real money. From connecting Claude to Robinhood's MCP server and building decision journals to beat the S&P 500, to the massive battles in agentic commerce, merchant risk profiles, and session-level fraud—we cover what is breaking and what needs to be solved

📌 TIMESTAMPS

00:00 - Introduction & Mitesh’s Background

00:25 - Building an Autonomous Trading Agent with Robinhood MCP

01:30 - Setting Up Guardrails, Mandates & Stock Selection Rules

02:45 - The Breakthrough: Prompting AI to Keep a "Decision Journal"

04:00 - Daily Monitoring vs. Weekly Rebalancing Agents

04:30 - Beating the S&P 500 & The Real Risks of Agentic Trading

06:15 - Why Enterprises Are Cautious About AI Guardrails

07:45 - The Evolution of Agentic Commerce & Browser Checkouts

09:30 - Merchant Risk Profiles & Session-Level Fraud Scores

11:15 - How Agentic Traffic Will Change E-Commerce Funnels & KPIs

13:30 - Key Skills for PMs: Mastering AI Evals & End-to-End Tracing

15:45 - The Future of Tech Roles: Problem-Solving Over Job Titles

---------------------------------------------------

💡 KEY TAKEAWAYS:

• Decision Journals for AI: Forcing LLMs to document their reasoning prevents context loss and random flip-flopping across sessions.

• Sandbox First: Never expose your primary trading account to autonomous agents—use dedicated sub-accounts or MCP sandboxes.

• Agentic Commerce Shift: Browsers are enabling AI agents to shop directly on merchant websites without waiting for custom API integrations.

• Crucial PM Skills: Understanding agent tracing, evaluation metrics, and session-level risk controls is vital for building production-ready AI.

🔗 RESOURCES & LINKS:

• Connect with Mitesh Shah: https://www.linkedin.com/in/mitesh-shah-19673039/

• Connect with Leena Agarwal: https://www.linkedin.com/in/leenaagarwal/

#AgenticAI #AI #FinTech #ArtificialIntelligence #Claude #ProductManagement #AITrading #Robinhood #TechPodcast

In Episode 31 of the show, Leena sits down with Christina, a London-based purpose and career coach, TEDx speaker, and host of the *Eudaimonia Life Show*.With the massive surge of AI and automation, it’s easy to feel lost in the short-term rush. In this powerful conversation, Christina dives deep into what it truly means to find your purpose at a soul level, blending ancient Greek and Japanese philosophies to help us navigate modern career pressures.*Timestamps:*

* **00:00** - Introduction: Meet Christina (Purpose & Career Coach and TEDx Speaker)

* **00:36** - Redefining Purpose: Why the Corporate Ideal of Purpose is Flawed

* **03:40** - Peer Pressure vs. Soul-Level Purpose: How to Make Aligned Choices

* **05:35** - The "Mid-Sprint" Trap: Escaping Short-Term Urgency and Shiny Penny Syndrome

* **09:47** - Activating Hope and Optimism Through Discipline and Integrity

* **12:00** - A Decision-Making Framework: Choosing Who You Need to Be

* **14:26** - Accountability as an Act of Love and Constructive Feedback

* **17:15** - Knowing When to Walk Away: Preserving Your Mental Peace

* **19:07** - What is Eudaimonia? Ancient Philosophy on Human Flourishing

* **26:06** - AI vs. Human Authenticity: Why AI Can Never Replace Being Witnessed

* **29:56** - Mentorship & Connection: Why Wisdom Requires Heart, Not Just Data

* **33:04** - Final Key Takeaways and Where to Find Christina

🔗 RESOURCES & LINKS:

* Connect with Christina on LinkedIn: https://www.linkedin.com/in/christinagaridi/

* Connect with Leena on LinkedIn: https://www.linkedin.com/in/leenaagarwal

In this episode of Agentic AI Execution, host Leena Agarwal sits down with tech leader Shylaja (ex-Anthropic, Airbnb, Amazon, Meta, Netflix) to explore how artificial intelligence and agentic workflows are reshaping Technical Program Management (TPM) and software development life cycles.

**Timestamps:***

**00:00** - Introduction & Shylaja’s Background across Meta, Airbnb, and Amazon

* **00:48** - The TPM Spectrum: 0-to-1 Products vs. 1-to-N Scaling

* **02:18** - How the Agentic AI Wave is Transforming TPM Workflows

* **03:45** - Automating Work vs. Refining Critical Judgment Calls

* **05:15** - Setting Up Agents, MCP Connectors, and Model Selection

* **06:12** - Defining "Done" & Forcing Functions for Production Readiness

* **07:05** - Human-in-the-Loop: Prototypes, Security, and Edge Cases

* **08:15** - Managing Risk, Speed Trade-offs, and Evolving SDLC

* **09:30** - Practical Steps to Start Using AI Assistants Today

* **10:40** - Advice for Organizations Adopting Agentic AI

* **11:30** - Mindset for the Future: Embracing Career Inflection Points

🔗 RESOURCES & LINKS:

* Connect with Shylaja on LinkedIn: https://www.linkedin.com/in/shylajar/

* Connect with Leena on LinkedIn: https://www.linkedin.com/in/leenaagarwal/

Welcome to episode 29 of the Agentic AI Execution podcast! In this episode, Leena sits down with Akshay, a Google Developer Expert (GDE) for Android, Developer Advocate, and founder of the Android Engineers Community in India.

Akshay shares his journey of building with Agentic AI, starting with a unique digital Ganesh Pandal powered by voice AI and GPT Live 1. The conversation dives deep into the realities of developer relations (DevRel), how to effectively use Gemini inside Android Studio, and the critical differences between a flashy AI demo and a resilient model that survives real-world production edge cases.

**Key Topics Covered:**

* **00:00** – Introduction and exploring the real gap between a flashy AI demo and one that survives production.

* **01:01** – Demo: Building a digital Ganesh Pandal with voice AI so anyone can join the festival virtually.

* **03:15** – The path to becoming a GDE and the importance of advocating for developers.

* **08:00** – Leveraging Gemini AI in Android Studio for faster coding and documentation.

* **10:30** – Protecting developer trust and providing quick-start AI templates via Agora

.* **12:50** – Real-world lessons: What to do when your live tech demo breaks.

* **22:14** – Navigating latency, background noise, and creating natural human-like voice agents

.

* **24:45** – Demos vs. Production: Why handling edge cases like low lighting and choppy video matters.

* **27:10** – The massive untapped opportunity for Voice AI in children's toys across India.

🔗 RESOURCES & LINKS:

* Connect with Akshay on LinkedIn: https://www.linkedin.com/in/anandwana001/

* Connect with Leena on LinkedIn: https://www.linkedin.com/in/leenaagarwal/

In Episode 28 of Agentic AI Execution, host Leena Agarwal sits down with James (Senior PM, former Staff TPM, and author of The TPM Craft newsletter) to unpack how agentic workflows are reshaping technical leadership roles across startups, mid-sized companies, and large enterprises.James breaks down why human relationships matter more than ever, where trust still breaks down in agentic code generation (security, compliance, quality), and the exact skills TPMs must double down on to stay indispensable. Plus, he shares real-world projects he built using AI—including a short-form content blocker and a virtual bank app for kids!

⏱️ CHAPTERS / TIMESTAMPS:

• 0:00 – Intro: Setting the Stage for the Agentic AI Era

• 0:45 – Roles, Trust, & The Secret Sauce for Using AI Well

• 21:13 – Scarce Skills TPMs Need as Execution Gets Cheaper

• 35:41 – Closing Thoughts

🔗 RESOURCES & LINKS:

• Subscribe to James’s Newsletter (The TPM Craft): https://thetpmcraft.substack.com/

• Connect with James on LinkedIn:   / jamzdayhuff  

• Connect with Leena on LinkedIn:   / leenaagarwal