Skip to content
Aakash GuptaAakash Gupta

AI Agents for PMs in 69 Minutes — Masterclass with IBM VP

Armand Ruiz, VP of AI Platform at IBM, reveals why most enterprise AI implementations fail and what Fortune 500 companies are actually building that works. He breaks down the difference between chatbots and agents, the 4-step framework powering real AI systems, and why RAG dominates 90% of enterprise use cases. ---- Transcript: https://www.news.aakashg.com/p/armand-ruiz-podcast ---- ⏰ Timestamps: 00:00 Intro 02:39 What Makes AI Agents Special 04:40 The Four Steps of AI Agents 07:14 AI Agent Development Frameworks 12:59 RAG Explained 16:55 Ads 18:46 Common RAG Mistakes 26:48 Managing Multiple AI Agents 31:39 Ads 33:57 How AI Changes Product Management 37:43 Problem Investigation vs Feature Factory 41:22 Roadmap to Build AI Agents 43:30 Can Open Source AI Win? 51:39 IBM's AI Strategy 59:32 Career Journey: Intern to VP 1:02:36 Building 200K LinkedIn Followers 1:08:18 Outro ---- 🏆 Thanks to our sponsors: 1. Kameleoon: Prompt-based experimentation platform - kameleoon.com/prompt 2. AI Evals Course for PMs & Engineers: Get $800 off https://maven.com/parlance-labs/evals?promoCode=ag-product-growth 3. Vanta: Security and compliance for fast-moving teams - https://www.vanta.com/lp/demo-1k 4. Amplitude: Mobile user engagement analytics - https://amplitude.com/digital-maturity-model 5. Product Faculty: Product Strategy Certificate for Leaders (Get $550 off) https://maven.com/product-faculty/ai-product-management-certification?promoCode=AAKASH25 ---- Key Takeaways: 1. AI Agents vs Chatbots: Chatbots respond to queries while agents execute complete workflows. The difference between getting suggestions and getting finished work. 2. Four-Step Agent Framework: Every agent needs Thinking (reasoning), Planning (task breakdown), Action (system execution), and Reflection (learning from outcomes). 3. RAG Dominates Enterprise: 90% of enterprise AI uses RAG to connect LLMs to proprietary data. Success requires 95%+ accuracy through sophisticated evaluation. 4. Vision RAG Unlocks Value: Most business data lives in charts and tables that traditional text-only RAG completely misses. 5. Framework Selection Matters: Use coding frameworks (LangGraph, CrewAI) for complex systems. Use no-code tools (Lindy, n8n) for rapid prototyping. 6. PM Ratios Transform: Traditional 1:6-10 PM-to-developer ratios become 1:2-30 when agents handle research and documentation. 7. Prototypes Beat PRDs: Show working systems instead of 20-page documents teams misinterpret. AI enables functional demos. 8. Open Source Wins: Despite closed-source capabilities, enterprises choose open source for licensing control and infrastructure flexibility. 9. Technical Literacy Essential: Understanding agents, RAG, and frameworks becomes baseline knowledge for everyone, not just developers. 10. Implementation Reality: Enterprise RAG needs heavy data engineering. Teams underestimate accuracy requirements and engineering complexity. ---- 👨‍💻 Where to find Armand: LinkedIn: linkedin.com/in/armandruiz IBM AI Platform: ibm.com/ai ---- 👨‍💻 Where to find Aakash: Twitter: twitter.com/aakashg0 LinkedIn: linkedin.com/in/aagupta/ #AIAgents #EnterpriseAI #RAGSystems #ProductManagement ---- 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 185K listeners. Hosted by Aakash Gupta, who spent 16 years in PM, rising to VP of product, this 2x/week show covers product and growth topics in depth. 🔔 Subscribe and turn on notifications to master AI agent implementation!

Aakash GuptahostArmand Ruizguest
Sep 4, 20251h 9mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

AI agents, RAG, open source, and the PM shift explained

  1. AI agents are positioned as the next leap beyond chatbots because they combine reasoning with planning, tool-taking actions, and reflection to automate end-to-end work.
  2. Building agents increasingly splits into two tracks: code-first frameworks (e.g., LangGraph, CrewAI, LlamaIndex, AutoGen) for control and low/no-code builders (e.g., Lindy, n8n, LangFlow, Flowise) for accessibility.
  3. RAG remains a dominant enterprise technique for injecting fresh, company-specific context into LLM workflows, but reliability requires serious data engineering and evaluation at multiple steps—not just checking the final answer.
  4. Managing “10–20 agents per employee” introduces a new orchestration skill: humans become accountable reviewers of agent outputs, with governance, cost controls, and safe experimentation as key enterprise constraints.
  5. AI changes product management by compressing the PM lifecycle (research → prioritization → PRD → prototype → monitoring) and enabling broader PM coverage, while still requiring customer-first problem investigation to avoid feature-factory behavior.

IDEAS WORTH REMEMBERING

5 ideas

Agents matter because they close the loop from “answering” to “doing.”

Ruiz frames agents as the “wall of automation”: not just generating text, but decomposing tasks, executing actions in real systems (email/CRM/Workday), and improving through reflection over time.

The simplest useful mental model for agents is Think → Plan → Act → Reflect.

Thinking leverages LLM reasoning; planning breaks work into subtasks; action is enabled by tool access/protocols (he cites MCP); reflection uses feedback/history to iteratively improve future runs.

Pick your agent tooling based on required control, not hype.

Low/no-code builders accelerate experimentation for non-technical users, while code frameworks (LangGraph/CrewAI/etc.) remain necessary for complex, production-grade agentic systems needing deeper flexibility.

RAG is primarily for fresh context, not “making the model smarter.”

He distinguishes RAG (connecting to databases/knowledge bases for up-to-date info) from fine-tuning (better for behavior/style/specialization, not continuously changing enterprise knowledge).

Most RAG failures are evaluation and data-engineering failures, not “LLM failures.”

Enterprises can’t tolerate “70% accuracy,” so vanilla templates break; teams need systematic eval practices and better pipelines (embeddings, chunking, retrieval, filtering, ranking) to reach business-acceptable reliability.

WORDS WORTH SAVING

5 quotes

Agents… deliver the wall of automation that is gonna unlock everyone… to generate way more output.

— Armand Ruiz

Four simple steps. The first one is thinking… planning… action… reflection.

— Armand Ruiz

70% accuracy is not acceptable.

— Armand Ruiz

Evals in agentic workflows should be almost… at every single step if you're really serious about developing something… a critical system.

— Armand Ruiz

If you didn’t write the most beautiful detailed PRD, still a lot of information is lost in translation… nothing speaks better than just a working prototype.

— Armand Ruiz

Definition of AI agents vs chatbotsFour-step agent loop: think, plan, act, reflectAgent development: coding frameworks vs low/no-code toolsRAG vs fine-tuning and enterprise context injectionVision RAG for PDFs, charts, tables, multimodal extractionRAG accuracy, data engineering, and evals throughout workflowsMulti-agent orchestration and human-in-the-loop accountabilityHow AI reshapes PM ratios, workflows, and prototyping cultureOpen source AI in enterprise: deploy-anywhere controlIBM strategy: hybrid deployment, Granite models, governanceAI regulation and enterprise compliance inventoryAI talent wars as capital allocationCareer acceleration: prototypes, customer obsession, networkingLinkedIn growth systems and diminishing AI-content advantage

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome