DiscoverAgentic AI Execution
Agentic AI Execution
Claim Ownership

Agentic AI Execution

Author: Leena Agarwal

Subscribed: 4Played: 27
Share

Description

The podcast for TPMs, product managers, and builders shipping real AI systems. No hype, no frameworks — just honest conversations about what it actually takes to move from model to production.
Topics include agentic AI, AI program execution, stakeholder alignment, technical roadmaps, and building trust in AI-driven orgs. Hosted by Leena Agarwal, 18-year TPM veteran from Amazon and Meta.
New episodes every week. Built for tech leaders who ship.
37 Episodes
Reverse
In Episode 37 of the Agentic AI Execution Podcast, AI Technical Program Manager (TPM) Praveen with nearly two decades of experience spanning development, data architecture, and ML programs at tech giants like Amazon and Meta, Praveen shares how he solved a major job-hunting frustration by building his own custom, open-source AI interview prepper tool. Discover how to stop relying on generic online advice and instead build a personalized AI agent grounded in your actual resume, story bank, and target company hiring loops!TIMESTAMPS:*00:00* Introduction & Praveen’s Tech Journey (Amazon & Meta)*02:30* Why Traditional Interview Prep Fails & Building the AI Prepper*06:15* Live Demo: How the AI Interview Prepper Works (Resume Grounding & Company Loops) *12:00* Tackling Hard TPM Questions: Pushbacks, Negotiations & Frameworks *16:45* Inside Amazon’s Alexa Plus Rollout: Moving from Rule-Based to Conversational AI*22:30* Managing Probabilistic AI Programs vs. Traditional Predictable Roadmaps *27:15* Core KPIs & Metrics: Latency, Task Completion, and Hallucination Rates*32:00* Handling Failures, Context Switching, and Demo Corner Cases*37:15* The Evolution of the TPM Role & What Hiring Managers Look For*42:00* Overhyped vs. Underrated in AI (Autonomous Agents vs. Rigorous Evaluations)Connect & Resources:- Praveen: https://www.linkedin.com/in/praveenpatri/- Leena: https://www.linkedin.com/in/leenaagarwal/- Praveen's blog: https://praveenpatri.medium.com/what-if-ai-could-personalize-your-interview-prep-165e38791b89#AITPM #AIInterviewPrep #TechInterviews #OpenAI #Google #Amazon #AIExecution
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 era00:47 — 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 work08:36 — Real productivity gains vs. corporate chaos: What CXOs and AI-native founders are getting right12:21 — 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 networking24:21 — The book recommendation strategy and how to genuinely connect with leaders27:44 — 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 Fit18:43 - Why B2B Founders Must Embrace Product Weaknesses to Build Trust
loading
Comments