In this special episode of the ODSC AI+ Podcast, host Sheamus McGovern dives into the real-world impact of GPT-5—from routing and hallucination issues to cost savings and open-weight models.

Joining him are two expert guests:
- Ivan Lee: Founder and CEO of Datasaur, who helps enterprises build private LLM stacks and has deep experience evaluating model upgrades.
-Nir Gazit: Co-founder and CEO of Traceloop, and co-creator of the OpenTelemetry Generative AI SIG, who brings insight into model routing, evaluation strategies, and observability tooling.
Together, they unpack what GPT-5 actually changed—and what teams should do next.

Key Topics Covered:
-Why GPT-5’s biggest shift is routing, not reasoning
-What casual vs. power users gained (or lost) with the rollout
-Hallucination benchmarks vs. real-world results
-Evaluation strategies using open-source tools like Phoenix and LangChain
-OpenAI’s OSS model release and its enterprise implications
-Why developers worry about black-box routing and the lack of traceability
-How to migrate safely: pinning snapshots, running evals, shadow testing
-Whether GPT-5 gets us closer to AGI, or just better infrastructure
-What to expect from agent workflows, tool selection, and model specialization

Memorable Outtakes:
- Ivan Lee: “GPT-5 is an upgrade for 98% of users—but for the power users, the loss of model choice felt like control was taken away.”
- Nir Gazit: “Of course, every new model crushes it on benchmarks—they’re optimizing for the benchmarks. That doesn’t mean it works for your use case.”
- Ivan Lee: “OpenAI’s OSS release might be the bigger story than GPT-5. Suddenly, enterprises are back at the table.”

References & Resources:
Guests
- Ivan Lee – CEO of Datasaur
Website: https://www.datasaur.ai
LinkedIn: https://www.linkedin.com/in/iylee/
- Nir Gazit – CEO of Traceloop
Website: https://www.traceloop.com
Blog: https://www.traceloop.com/blog
LinkedIn: https://www.linkedin.com/in/nirga/

Resources Mentioned
- OpenAI GPT-5  https://openai.com/gpt-5
- OpenTelemetry Project: https://opentelemetry.io
- Traceloop OpenLLMetry: https://www.traceloop.com/openllmetry
- Phoenix (Arize AI open-source evals): https://github.com/Arize-ai/phoenix
- LangChain Evals: https://python.langchain.com/api_reference/langchain/evaluation.html
- GPT-OSS Open Weight Models by OpenAI: https://platform.openai.com/docs/models/gpt-oss
- Claude + Model Context Protocol (Anthropic): https://docs.anthropic.com/en/docs/tool-use
- ARC-AGI Leaderboard: https://arcprize.org/leaderboard

Sponsored by:
🔥 ODSC AI West 2025 – The Leading AI Training Conference
Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket.
Learn more: https://odsc.ai 


GPT-5 Unboxed: What Changed, What Broke, and What’s Next with Ivan Lee and Nir Gazit

In this episode of the ODSC Ai X Podcast, host Alex Landa speaks with Georgios N. Yannakakis, Professor at the Institute of Digital Games, University of Malta, co-founder of Modl.ai and Human Feedback AI, and Editor-in-Chief of IEEE Transactions on Games. A leading researcher in AI and games, Georgios shares insights from two decades of work at the intersection of artificial intelligence, player experience, and creative design. The discussion spans his seminal paper Choose Your Weapons: Survival Strategies for Depressed AI Academics, the value of human feedback in AI development, and the transformative role of AI in game research and design.

Key Topics Covered:
Georgios’s background in AI and game research, including co-founding Modl.ai and Human Feedback AI
The challenges facing AI academics today, including scaling maximalism and the need for smaller, human-centered models
Insights from the satirical yet practical paper Choose Your Weapons: Survival Strategies for Depressed AI Academics
The underrated importance of human data and human-in-the-loop approaches for AI alignment
Applications of AI in gaming, from procedural content generation to adaptive player modeling
How reinforcement learning and emotional modeling can create personalized, player-centric game experiences
The shift from building superhuman AI agents toward co-creative systems that assist game designers
Strategies like “try things that shouldn’t work” and how disruptive, risky research can lead to breakthroughs
Current projects in affective computing, user modeling, and generative AI for co-creation in games

Memorable Outtakes:
“As recently as 10 years ago, if you had a decent desktop computer and an internet connection, you had everything you needed to compete with the best researchers. Well, guess what? It’s not the case anymore.” – Georgios N. Yannakakis
“Humans are the next frontier of AI. We need human-centered models to build safer, explainable, and more trustworthy AI.” – Georgios N. Yannakakis
“The best use of generative AI in games is as a creative partner—an assistant in the design process—not as a fully autonomous game designer.” – Georgios N. Yannakakis

References & Resources:
Georgios Yannakakis University of Malta profile: https://www.um.edu.mt/profile/georgiosyannakakis
Georgios’ LinkedIn: https://www.linkedin.com/in/georgios-n-yannakakis-67a5b05
Modl.ai: https://modl.ai/
Human Feedback AI: https://humanfeedback.ai/
IEEE Transactions on Games: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7782673
Book Artificial Intelligence and Games: http://gameaibook.org/
Paper: Choose Your Weapons: Survival Strategies for Depressed AI Academics: https://ieeexplore.ieee.org/document/10458714
Paper: Pixels and Sound of Emotion: General Purpose Representations of Arousal in Games (IEEE Transactions on Affective Computing): https://arxiv.org/abs/2101.10706
Paper: BehAVE: Behaviour Alignment of Video Game Encodings: https://arxiv.org/html/2402.01335v3
Podcast with his colleague, Julian Togelius - From Turing’s Chess to Neural Game Engines: AI in Video Games Today: https://youtu.be/f_z2PpR3GaU

Sponsored by:
ODSC AI West 2025 – The Leading AI Training Conference
Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket.
Learn more: https://odsc.ai

Gaming Research in AI and the Need for Human-Centered Design with Georgios Yannakakis

In this episode of the ODSC Ai X Podcast, host Sheamus McGovern speaks with Sandi Besen, AI Engineer and Ecosystem Lead at IBM Research, about designing rule-based, production-ready AI agents using IBM’s open-source BeeAI framework. Sandi shares her journey from the performing arts to AI engineering, unpacks the challenges of agent reliability and trust, and explores how frameworks like BeeAI are solving real-world issues through enforceable rules, observability, and open standards. This episode dives deep into multi-agent systems, communication protocols, and what it really takes to deploy AI agents safely and effectively in enterprise environments.

Key Topics Covered:
Sandi’s background and current role at IBM Research
What inspired the creation of the BeeAI framework and platform
The concept of "agent chaos" and how BeeAI brings structure and reliability
Comparison of popular agent frameworks: LangChain, LangGraph, CrewAI
Introduction to emerging agent communication protocols (MCP and A2A)
Enforcing hardcoded rules (conditional requirements) in agents
Building agent behavior guardrails and preventing rogue actions
Importance of observability, memory, and tracing in agent frameworks
Using OpenTelemetry for tracing agent decision-making
Challenges in agent safety, validation, and trust for enterprise use
How BeeAI makes deploying an agent with a UI fast and easy (in under an hour)
When to build from scratch vs. using a framework like BeeAI 
Common mistakes startups make when adopting cutting-edge AI tech
Trends in context engineering and long-term memory
The future of consulting in the age of AI

Memorable Outtakes:
“Agent chaos is real. We needed a way to bring structure, enforce rules, and make agents safe for production.”
“Conditional requirements let you hardcode business logic into your agents — not just suggest behavior, but enforce it.”

References & Resources:
Sandi Besen – AI Engineer & Ecosystem Lead at IBM Research: https://research.ibm.com/people/sandi-besen
Website: https://sandibesen.com/
LinkedIn: https://www.linkedin.com/in/sandibesen/
BeeAI: https://www.ibm.com/think/news/beeai-open-source-multiagent
BeeAI GitHub Repository: https://github.com/i-am-bee/beeai-framework
Agent Communication Protocol (ACP) Course (DeepLearning.AI): https://www.deeplearning.ai/short-courses/acp-agent-communication-protocol/
OpenTelemetry:  https://opentelemetry.io/
Google’s P2 Payment Protocol (for AI agents): https://ap2-protocol.org/
AP2 GitHub: https://github.com/google-agentic-commerce/AP2
OpenAI Agent Commerce Protocol: https://developers.openai.com/commerce/

Sponsored by:
🔥 ODSC AI West 2025 – The Leading AI Training Conference
Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket.
Learn more: https://odsc.ai


AI Agents That Follow the Rules: Sandi Besen

In this episode of the ODSC Ai X Podcast, we speak with Noah Giansiracusa, a professor of mathematics at Bentley University and the author of Robin Hood Math (MIT Press, 2024). Noah makes the case that you don’t need to be a math genius to use numbers to challenge power, spot manipulation, and think more clearly in today’s data-saturated world. From social media algorithms to misleading rankings and risk perception, Noah explains how math is a tool for empowerment—not just abstraction.
Key Topics Covered:
Why “being pretty good at math” is enough for most real-world reasoning
The real-world implications of expected value and decision theory
How college and law school rankings are gamed—and what’s wrong with the metrics
How social media platforms like Facebook use engagement formulas to shape behavior
The problem with overestimating rare events 
Why being “numerically literate” is now a form of civic engagement
The role of anecdotes vs. data in shaping perception and risk
Memorable Outtakes:
“What I wanted to do with this book was show people that you don’t have to be 
“When we talk about risk, the things we fear the most are often not the things that are most likely to happen—and that’s a statistical insight.”
References & Resources:
Robin Hood Math by Noah Giansiracusa    https://www.noahgian.com/books
Noah Giansiracusa’s website  https://www.noahgian.com
Noah Giansiracusa’s academic page: https://faculty.bentley.edu/profile/ngiansiracusa
Mentioned research on COMPAS algorithm and algorithmic bias: https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
College ranking methodology critique   https://en.wikipedia.org/wiki/Criticism_of_college_and_university_rankings_in_North_America
Sponsored by:
 🔥 ODSC AI West 2025 – The Leading AI Training Conference
 Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
 Use the code podcast for 10% off any ticket.
 Learn more: https://odsc.ai



Robin Hood Math: Taking the Algorithms Back with Noah Giansiracusa

In this episode, we speak with Kyle Corbitt, co-founder and CEO of OpenPip, recently acquired by CoreWeave, to explore the evolving role of reinforcement learning in building smarter, more reliable AI agents. Kyle shares the journey of OpenPipe from supervised fine-tuning to developing ART (Agent Reinforcement Trainer), their open-source RL toolkit designed to train AI agents that can think, adapt, and perform with greater autonomy. The discussion spans technical insights, practical applications, startup lessons from YC’s Startup School, and the future of agent-based AI systems.

Key Topics Covered:
Why reinforcement learning is gaining attention in modern Agent development
The transition from supervised fine-tuning (SFT) to reinforcement learning (RL)
Practical differences between RL and SFT, including weight movement and model reliability
OpenPipe’s approach with ART: supporting multi-turn agent training and tool use
How ART differs from OpenAI’s RFT implementation
The importance of consistent agent behavior in production and how RL helps
Avoiding reward hacking and the role of Ruler, OpenPipe’s LLM-based judging system
Cost-efficiency strategies in RL training using serverless infrastructure
OpenPipe’s long-term vision for self-improving agents
Advice for AI startup founders on building in a rapidly evolving ecosystem

Memorable Outtakes:
On why reinforcement learning matters now:
"What RL does… is it actually lets you solve the reliability problem. You can make your smaller model significantly more reliable—even more performant in your domain—through RL." 
On OpenAI's RFT vs. OpenPipe’s ART:
"What you're missing [with OpenAI's RFT API] is the ability to define custom tools and multi-turn agent behavior. With ART, you own the code, define the tools, and have full control of the reward signal."  

Guest information, Mentioned Tools and Projects:
Kyle Corbitt: https://www.linkedin.com/in/kcorbitt/
OpenPipe: https://openpipe.ai 
OpenPipe GitHub: https://github.com/OpenPipe/OpenPipe
ART (Agent Reinforcement Trainer): https://github.com/OpenPipe/ART
Ruler: LLM-based evaluation tool for training agents (part of the ART package): https://openpipe.ai/blog/ruler
DeepSeek R1: https://api-docs.deepseek.com/
OpenAI RFT: https://platform.openai.com/docs/guides/reinforcement-fine-tuning
SkyPilot: scale AI workloads  https://github.com/skypilot-org/skypilot

Notable Blog Posts:
Ruler (LLM-as-a-Judge): https://www.openpipe.ai/blog/ruler
Reward Hacking Post: https://www.openpipe.ai/blog/reward-hacking
Serverless RL Backend: https://www.openpipe.ai/blog/serverless-rl
ART Trainer: A New RL Trainer for Agents: https://openpipe.ai/blog/art-trainer-a-new-rl-trainer-for-agents

Sponsored by:
🔥 ODSC AI West 2025 – The Leading AI Training Conference
Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket.
Learn more: https://odsc.ai


Training Agents with Reinforcement Learning: Kyle Corbitt

In this special episode of the ODSC AI Podcast, host Sheamus McGovern, Founder of ODSC, shares a curated selection of short, focused Minisodes recorded live at ODSC AI West 2025. Across three days of hands-on sessions, keynotes, and workshops, these conversations capture the voices of eight experts driving the next wave of enterprise and applied AI, from responsible governance and trust engineering to coding with AI, open models, and the automation of discovery itself.
Guests include: Cal Al-Dhubaib, Ivan Lee, Sinan Ozdemir, Chip Huyen, Jepson Taylor, Helen O’Sullivan, Andrew Radin, and Steven Pousty — spanning startups, academia, and industry innovation.
Key Topics Covered:
▪️ Trust Engineering and AI Governance
▪️ Labeling Agents and Human-in-the-Loop Systems
▪️ Benchmarking and Real-World Performance Gaps
▪️ AI Engineering and the Future of Coding
▪️ Algorithmic Invention and Superhuman Code
▪️ Enterprise AI Infrastructure and Cost Optimization
▪️ AI Entrepreneurship and Measuring ROI
▪️ Computer Vision, Data Quality, and AI Sovereignty


Memorable Outtakes:
▪️ Cal Al-Dhubaib: “Trust is the currency of enterprise AI — you earn it over time, and one bad incident can spend it all.”
▪️ Ivan Lee: “Supervised learning is back. It never really left — we’ve just made it faster and smarter with labeling agents.”️
▪️Chip Huyen: “Saying prompt engineering is dead is like saying communication is dead.”


References & Resources:
▪️ Cal Al-Dhubaib – ⁠https://www.linkedin.com/in/dhubaib/⁠
▪️ Ivan Lee – Datasaur:⁠ ⁠https://www.linkedin.com/in/iylee/
▪️ Sinan Ozdemir – Crucible AI:⁠https://www.linkedin.com/in/sinan-ozdemir/⁠
▪️ Chip Huyen – The AI Engineer (O’Reilly Media):https://www.linkedin.com/in/chiphuyen/
▪️ Jepson Taylor – VEOX Inc.:⁠ ⁠⁠https://www.linkedin.com/in/jepsontaylor/⁠
▪️ Helen O’Sullivan – Dell Technologies:⁠ ⁠⁠https://www.linkedin.com/in/helen-o-sullivan-0596b1150/⁠
▪️ Andrew Radin – StartX:⁠ ⁠https://www.linkedin.com/in/andrewradin/
▪️ Steven Pousty – Red Hat:⁠ ⁠https://www.linkedin.com/in/thesteve0/
Sponsored by:
🔥 ODSC AI East 2026 – The Leading AI Training Conference
Join us in Boston from April 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket. Learn more:⁠ https://odsc.ai/east⁠

ODSC West Minisodes: Trust, Agents, and the Next Wave of Applied AI

In this episode of the ODSC Ai X Podcast, host Sheamus McGovern speaks with Dr. Denis Garagić, CTO at Palladyne AI, about how intelligent systems are moving beyond the screen and into the physical world.
They explore the rise of embodied and physical AI, how it’s transforming robotics and manufacturing, and why autonomous drone swarms represent a powerful shift in real-time, decentralized decision-making. Denis also shares why hybrid models often outperform LLMs in production environments, and what’s needed to safely deploy these systems in industry and defense.
Key Topics Covered
How Denis Garagić’s work connects robotics, AI software, and autonomy.
What Embodied AI and Physical AI mean, and how they differ from traditional automation.
Why embedded, adaptive systems are replacing rigid, pre‑programmed robots in manufacturing.
The role of data, edge compute, and multi‐modal perception in enabling real‑world autonomy.
Internal limitations of large language models (LLMs) in industrial and physical systems, and why hybrid autonomy is often preferable.
How true drone swarms work: decentralized decision‑making, edge planning, and self‑organising UAV fleets.
Use cases in industrial manufacturing (automotive, aerospace, defense, construction) and in public‑safety/drone swarms.
The operational, organisational, and safety challenges of deploying embodied/physical AI in production: workforce readiness, verification & validation, regulatory considerations.
The future of embodied & physical AI: world‑models, runtime memory, sim‑to‑real transfer, and where the industry is headed next.
Memorable Outtakes
“Embodied AI is about learning through actions. You perceive, adapt, and reason while interacting with the physical world—just like we do as humans.”
“Drone swarms shouldn’t act like fleets. They should act like hives—decentralised, self‑organising, and communicating with only what’s necessary.”
“LLMs don’t scale well in industrial environments. Data is proprietary, compute is constrained, and the models need to be reliable — not just impressive.”

References & Resources
Dr. Denis Garagić’s bio (Palladyne AI): https://www.palladyneai.com/about-palladyne-ai/dr-denis-garagic/
Palladyne AI homepage: https://www.palladyneai.com
Blog: Autonomous Swarming Takes Flight: The Next Era of UAV Operations: https://www.palladyneai.com/blog/autonomous-swarming-takes-flight-the-next-era-of-uav-operations
Press release: Palladyne AI Achieves Key Milestone with First Small Drone Autonomous Tracking Flight:  https://www.tmcnet.com/usubmit/2024/12/23/10124356.htm TMCnet
News article: Palladyne AI and Draganfly partner for advanced UAV swarm autonomy: https://www.dronexl.co/2025/10/21/draganfly-ai-palladyne-autonomous-drone-swarms/ DroneXL.co
News article: Palladyne AI secures US Patent for advanced swarming and autonomy technology: https://www.asdnews.com/news/defense/2025/11/03/palladyne-ai-secures-us-patent-advanced-swarming-autonomy-technology ASD News


Sponsored by:
🔥 ODSC AI East 2026 – The Leading AI Training Conference
Join us in Boston from April 28th–30th for expert‑led sessions on Agentic AI, AI Engineering, Data Science, Machine Learning, LLMOps, and AI‑driven automation.
Learn more: https://odsc.ai/east


🧠 Agentic AI Summit – Learn to Build and Deploy Autonomous AI Systems
Happening online this January, the Agentic AI Summit is your chance to dive into hands‑on workshops and expert sessions on AI agents, workflows, and real‑world automation.
 Use the code podcast for 10% off any ticket for either event
Learn more: https://summit.ai



From Embodied and Physical AI to Autonomous Drone Swarms with Dr. Denis Garagic

In this episode, host Sheamus McGovern is joined by Lake Dai (Founder, Sancus Ventures; AI Professor, Carnegie Mellon University) to unpack how venture capital invests in AI startups, what founders need to know, and how individuals with less capital can still participate meaningfully. Together they explore the shifting AI ecosystem—from model‑builders to tool‑builders—what VCs look for in teams, and how energy and infrastructure will soon become critical bottlenecks. Lake also shares her startup idea rooted in gamified simulation for workforce retraining and life‑skills development.

Key Topics Covered:
- What VCs are really looking for: signals, spending patterns from major foundation model firms, and how that drives investment strategy.
- The transition from “one or two foundation models” to a diverse array of open‑source tools and the implications for startup builders.
- Why choosing the right tools is one thing—but choosing where you drive them (i.e., product‑market fit + customer value) is the competitive advantage.
- How energy inefficiencies and infrastructure constraints (compute, cooling, power) are emerging as AI bottlenecks and investment opportunities.
- How solo founders or small teams can still add value to startups (e.g., as advisors/operators) and what boundaries and commitments matter.
- The importance of building your early team—whether co‑founders or advisors—with the same care you would in selecting a partner for life.
- Lake’s personal startup idea: a gamified simulation environment to train people in different roles and life skills, making learning fun and highly personal.
- Advice for younger listeners and first‑time investors: ways to plug into the startup ecosystem even without large capital.
- Practical questions that founders should ask a fund: What is the operating platform? What resources, networks, and buyer access does the fund provide?

Memorable Outtakes:
- Lake Dai: “I’m looking at it as if OpenAI, xAI, and Anthropic, who raise so much money, and where do they spend it? That’s where I invest.”
- Lake Dai: “You are the one that decides which direction you are going… at the end of the day, AI is a tool … you have to do something meaningful with it — find your product‑market fit and be the preferred provider of your customer.”
- Sheamus McGovern: “What Lake just described isn’t just a technical footnote — it’s a massive strategic pivot for the AI ecosystem: the next frontier isn’t just bigger models, it’s how we power and deploy them.”

References & Resources:
- Lake Dai (Sancus Ventures): https://www.sancus.vc/team/lake-dai
- LinkedIn: https://www.linkedin.com/in/lakedai/
- Stanford University AI Index Report (for data‑center energy trends): https://aiindex.stanford.edu

This episode was sponsored by:
 🔥 ODSC AI East 2026 – The Leading AI Training Conference
Join us in Boston from April 28th–30th for expert‑led sessions on Agentic AI, AI Engineering, Data Science, Machine Learning, LLMOps, and AI‑driven automation.
Learn more: https://odsc.ai/east

🧠 Agentic AI Summit – Learn to Build and Deploy Autonomous AI Systems
Happening online this January, the Agentic AI Summit is your chance to dive into hands‑on workshops and expert sessions on AI agents, workflows, and real‑world automation.
Use the code podcast for 10% off any ticket for either event
Learn more: https://summit.ai



The VC Playbook: AI Deals, Founders & Joining the Game with Lake Dai

In this episode, guest host Cal Al-Dhubab sits down with Reid Blackman, Founder & CEO of Virtue and author of Ethical Machines. Reid is one of the most widely recognized voices in applied AI ethics and risk management. His work has supported organizations such as Amazon, Etsy, Kraft Heinz, Merck, Nationwide, and U.S. Bank. He has spoken at the FBI, NASA, the World Economic Forum, and the International Atomic Energy Agency, and contributes frequently to Harvard Business Review.
The conversation explores Reid’s journey from philosophy professor to AI ethics leader, why traditional “principles and pillars” approaches no longer work, and how organizations can instead adopt an “ethical nightmares” framework to manage AI risks—especially as generative and agentic AI introduce new points of failure and new paths to familiar harms.

Key Topics Covered
- Reid’s transition from academic philosophy to AI ethics consulting
- Why AI ethics requires outcome-oriented frameworks, not high-level value statements
- The limits of traditional responsible AI playbooks in the era of agentic and multi-agent systems
- The core idea of ethical nightmares and why they motivate action better than “values.”
- How AI systems create new ways for old failures to happen—especially bias, privacy leaks, and hallucinations
- Why generative AI dramatically reduces predictability and increases monitoring requirements
- The explosion of risk surface area with agentic AI and tool-using systems
- The importance of real-time monitoring, observability, and human-in-the-loop oversight
- How to run Reid’s Ethical Nightmare Challenge using three simple questions
- Why responsible AI programs must start at the project, team, or department level—not with slow enterprise policies
- The need for ongoing user training beyond one-time AI literacy modules
- Philosophical and societal concerns Reid is watching closely, including digital duplicates, therapy bots, and human–AI emotional relationships

Memorable Outtakes
1. Reid Blackman: "Nightmares are clear, concrete, vivid, and outcome-specific. If you know what a bad outcome looks like, you can immediately ask what strategies you need to avoid it."
2. Reid Blackman: "Agentic AI doesn’t create new nightmares — it creates new ways to realize the ones we already know, and at lightning speed and scale."
3. Cal Al-Dhubab: "The biggest failure cases you see in the news aren’t intentional—they’re unintended consequences people never anticipated."
References & Resources
Guest
Reid Blackman — Founder & CEO, Virtue Website: ⁠https://virtueconsultants.com⁠ Personal site:⁠ https://www.reidblackman.com⁠ Substack:⁠ https://reidblackman.substack.com⁠, ⁠https://virtueconsultants.com⁠), (⁠https://www.reidblackman.com⁠).
Guest host Cal Al-Dhubab LinkedIn: ⁠https://www.linkedin.com/in/dhubaib/⁠ 

Referenced Organizations & Examples
NASA —⁠ https://www.nasa.gov⁠
World Economic Forum —⁠ https://www.weforum.org⁠
International Atomic Energy Agency —⁠ https://www.iaea.org⁠
Harvard Business Review — ⁠https://hbr.org⁠ 

Articles / Concepts Discussed
Responsible AI Checklist (HBR article referenced) — ⁠https://hbr.org⁠
Ethical Nightmare Challenge (outlined by Reid) — described during the interview
Digital Duplicates & Deepfakes — general discussion topic

Sponsored by:
ODSC AI East 2026 – The Leading AI Training Conference. Join us in Boston from April 28th–30th for expert-led sessions on Agentic AI, AI Engineering, Data Science, Machine Learning, LLMOps, and AI-driven automation. Learn more:⁠ https://odsc.ai/east⁠
Agentic AI Summit – Learn to Build and Deploy Autonomous AI SystemsHappening online this January, the Agentic AI Summit is your chance to dive into hands-on workshops and expert sessions on AI agents, workflows, and real-world automation. Use the code podcast for 10% off any ticket for either eventLearn more:⁠ https://summit.ai⁠

Ethical Nightmares, Agentic AI, and Building Real Responsible AI Programs with Reid Blackman

In this episode of ODSC’s Ai X Podcast, host Alex Landa, Head of Content at ODSC, speaks with Dr. Denise Gosnell, an award-winning computer scientist, startup advisor, and global authority in graph technologies. Dr. Gosnell is the former Chief Data Officer at DataStax, holds multiple patents (including one from AWS for an enterprise-scale AI engine), and earned her PhD in Computer Science from the University of Tennessee. She is also the author of Tech Confidential and The Practitioner’s Guide to Graph Data.
This conversation explores the evolution of graph systems, why explainability still matters in modern AI, lessons learned from deploying massive systems under pressure, and how teams can adopt a context-first mindset to build AI that survives contact with the real world.

Key Topics Covered:
Early lessons from her PhD work and why explainability remains foundational in AI systems
The role of learning styles and vocabulary empathy in AI adoption
How engineering teams can avoid silos and build products by meeting customers where they are
What “embrace the chaos” really means, and how it helps teams ship real AI systems
Why context—not model size—is the true differentiator for enterprise AI
The four essential graph patterns: neighborhoods, trees, paths, and recommendations
Why paths are the most underused graph pattern and the ROI organizations miss when avoiding them
How organizations know they’re ready—or absolutely not ready—for a unified graph layer
The biggest misconceptions founders and CTOs have about AI adoption today
How intuition, empathy, and cross-functional collaboration influence high-performance technical teams
Advice for practitioners trying to prioritize, pivot, and build AI systems that deliver ROI

Memorable Outtakes:
“Explainability matters… executives aren’t very excited about probabilistic black boxes in production.”
“The most important thing that I have done—and that I know—is the fact that I really don’t know anything. Nobody knows everything.”
“Hiring one brilliant 10x engineer is not going to get you where you want to go. What matters is teamwork and a place where failures aren’t punished.”

References & Resources:
Guest Links:
Dr. Denise Gosnell – Website & Writing: https://denisegosnell.ai
LinkedIn: https://www.linkedin.com/in/denisekgosnell/
Instagram: https://instagram.com/denisegosnell.ai
Substack: https://substack.com/@denisegosnell
OpenDataScience Blog Series: https://opendatascience.com/from-graphs-to-generative-ai-building-context-that-pays-part-1/
Books by Denise Gosnell:
Tech Confidential – Published September 2025
The Practitioner’s Guide to Graph Data (O’Reilly)
Links to both: https://www.amazon.com/stores/Denise-Gosnell/author/B087DSH8SB

Sponsored by:
ODSC AI East 2026 – The Leading AI Training Conference
Join us in Boston from April 28th–30th for expert-led sessions on Agentic AI, AI Engineering, Data Science, Machine Learning, LLMOps, and AI-driven automation.
Learn more: https://odsc.ai/east

Agentic AI Summit – Learn to Build and Deploy Autonomous AI Systems
Happening online this January, the Agentic AI Summit is your chance to dive into hands-on workshops and expert sessions on AI agents, workflows, and real-world automation.
Use the code podcast for 10% off any ticket for either event.
Learn more: https://summit.ai


Context, Graphs, and Embracing Mistakes in AI with Denise Gosnell

In this episode, Sterling Chin, Senior Developer Advocate at Postman, discusses what it really takes to build agentic workflows that work in production, especially when those agents need to interact with real systems through APIs. Sterling breaks down how MCP fits into the picture, why “APIs aren’t going anywhere,” and what teams should change about their specs, error handling, examples, and documentation so agents can reliably use them. 

Key Topics Covered:
Sterling’s background and how his work at Postman
Why “APIs aren’t going anywhere”
Why agents are only as good as the APIs/data they can access
Making APIs “agent-ready”
Debugging and evaluation tactics
Orchestration patterns and reliability
MCP in practice
GraphQL for agentic systems
Claude Skills + MCP as a workflow pattern

Memorable Outtakes:
“APIs aren’t going away”
Claude Skills… plus MCP are really, really powerful.”

References & Resources:
LinkedIn: https://www.linkedin.com/in/sterlingchin/
Website: https://www.sterlingchin.com/
Postman Agent Mode: https://www.postman.com/product/agent-mode/
Official MCP registry: https://registry.modelcontextprotocol.io/
MCP Inspector (Model Context Protocol docs): https://modelcontextprotocol.io/docs/tools/inspector Model Context Protocol
Anthropic Claude Skills (Docs): https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview Claude
Anthropic Skills (GitHub): https://github.com/anthropics/skills
Postman Flows: https://www.postman.com/product/flows/
Postman Community AMA with Sterling Chin: https://community.postman.com/t/ama-with-sterling-chin-senior-developer-advocate-at-postman/84978

Sponsored by:
🔥 ODSC AI East 2026 – The Leading AI Training Conference
Join us in Boston from April 28th–30th for expert-led sessions on Agentic AI, AI Engineering, Data Science, Machine Learning, LLMOps, and AI-driven automation.
Learn more: https://odsc.ai/east
🧠 Agentic AI Summit – Learn to Build and Deploy Autonomous AI Systems
Happening online this January, the Agentic AI Summit is your chance to dive into hands-on workshops and expert sessions on AI agents, workflows, and real-world automation.
Use the code podcast for 10% off any ticket for either event
Learn more: https://summit.ai


Agent-Ready APIs with Sterling Chin

With Ai X Podcast, Open Data Science Conference (ODSC) brings its vast experience in building community and its knowledge of the data science and AI fields to the podcast platform. The interests and challenges of the data science community are wide ranging. To reflect this Ai X Podcast will offer a similarly wide range of content, from one-on-one interviews with leading experts, to career talks, to educational interviews, to profiles of AI Startup Founders. Join us every two weeks to discover what’s going on in the data science community.

Find more ODSC lightning interviews, webinars, live trainings, certifications, bootcamps here - https://aiplus.training/  
Don't miss out on this exciting opportunity to expand your knowledge and stay ahead of the curve.

GPT-5 Unboxed: What Changed, What Broke, and What’s Next with Ivan Lee and Nir Gazit

ODSC's Ai X Podcast