AI Agent Observability: OpenClaw, ClawMetry and Observability | Vivek Chand (Booking.com)

How do you monitor AI agents in production? 

In this episode, Vivek Chand, tech leader at Booking.com and founder of ClawMetry breaks down AI agent observability, evaluation loops, and his open-source tool ClawMetry tracking agent behaviour in real time. Clawmetry is an open-source tool with already 30,000 plus downloads after just a week. 

Vivek shares his engineering journey from startups to leading customer support AI at Booking.com, what it actually takes to ship AI systems that deliver ROI, and why observability is the missing layer for agentic AI workflows.

We cover OpenClaw for coding agents, how ClawMetry visualizes agent actions, subagent spawning, file access, and token usage, plus the roadmap for remote monitoring, mobile apps, and security alerts.

🔑 Topics covered:
AI agent observability explained
Building production AI systems at Booking.com
Evaluation loops for prediction quality
OpenClaw use cases for coding agents
Clawmetry Telemetry: open-source agent monitoring
Advice for junior AI engineers in 2026

00:00 Welcome and Guest Intro
00:59 Vivek Career Journey
03:03 Building AI at Booking
04:26 Scaling Systems and Eval Loops
06:19 Advice for Junior Engineers
07:48 Why Agent Observability Matters
11:30 OpenClaw Use Cases for Coding
13:21 Productivity Gains with Agents
14:43 What Telemetry Does
18:03 How Telemetry Was Built
19:53 Roadmap Managed and Security
22:24 Future of Agents and Monitoring

To download and try Clawmetry, you can use the following link: https://clawmetry.com/

There is also a cloud version available with a 7-day free trial here: https://clawmetry.com/cloud

Clawmetry Mac app:  https://clawmetry.com/mac

Would you clone your likeness and personality with AI?

Chris is joined by Katherine Ivanova, co-founder of Pantio, a company dedicated to creating digital personalities, a product that has the potential to change how humanity communicates. 

They discuss the product, which involves deep voice cloning to capture and preserve a person's unique personality and voice. They discuss the ethical and security considerations of this technology, its applications in preserving legacies, and potential use cases for individuals with terminal illnesses. 

Tune in as they delve into the philosophical aspects and future visions of immortalising human experiences through digital avatars.

00:00 Introduction To The Podcast
00:42 Meet Kate: Co-Founder of Panio
02:16 Understanding Digital Twins and Deep Voice Cloning
04:11 The Vision Behind Panio
05:33 Addressing Ethical and Security Concerns
06:48 Personal Stories and Use Cases
10:57 Future Plans and Technological Advancements
16:06 Customer Engagement and Feedback
33:20 Final Thoughts and Closing Remarks

https://pantio.io/

We're joined by Artem Elmuratov, Head of Life Sciences at Nebius and former Founder. 

In this episode, we discuss with Artem genetics and its future with AI. Specifically discussing the impact of CRISPR-GPT on biotechnology. We explore its potential applications in genetic engineering, disease prevention, and personalised medicine. The discussion highlights the scientific breakthroughs enabling precise genetic modifications and considers the societal implications of such advancements.

Join us as we explore: 

00:00 Introduction: AI and Scientists
00:20 Welcome to Rhe NeuralPod
00:37 Artem's Unique Journey in Biotech
01:04 The Intersection of Genetics and AI
03:55 Career Overview and Early Ventures
04:54 Confidential Computing and Current Role
05:40 Lessons Learned and Advice for Researchers
08:16 Current State of Genetics and AI
10:05 Challenges in the Industry
12:03 AI's Role in Drug Discovery
18:02 CRISPR and Gene Editing
27:24 Future of Gene Editing and Ethics
31:56 Fun Predictions and Sci-Fi Inspirations
41:05 Closing Thoughts and Contact Information

CRISPR GPT: https://nebius.com/customer-stories/crispr-gpt-stanford

We're joined by Keith Dear, CEO and co-founder of Cassi, an AI super strategy engine. Keith is a former intelligence officer, an advisor at Number 10 and a former leader at Fujitsu Research. 

We discussed his vision for Cassie, the concept of 'everything is prediction,' and how AI will shape organisational strategies and decision-making processes. We also explore the potential impact of AGI on job markets, the national economy, and global politics, touching on Keith's recent visit to China and his work with the UN on AI security and ethics. 

00:00 Introduction and Initial Thoughts
00:22 Welcome to the Neuro Pod
00:41 Keith's Career Journey
01:16 Cassie: The Super Strategy Engine
02:17 The Importance of Clear Objectives
03:26 AI and Crowdsourcing in Decision Making
04:58 Keith's Background and Education
06:57 The Genesis of Cassie
10:42 Concerns About AI and the Future
14:29 Visiting China: Insights and Observations
18:39 Leadership Principles and Military Experience
24:36 Transitioning from Corporate to Startup
26:44 Predictions on AGI and Superintelligence
34:17 Choosing AI Over Human Advice
34:45 AI's Limitations and Human Judgment
35:23 Trusting AI vs. Human Judgment
36:33 Self-Driving Cars and Ethical Dilemmas
37:57 AI's Impact on Jobs and Economy
40:34 International Security and AI
48:03 Cassie: Everything is Prediction
50:50 Cassie in Action: Real-World Applications
56:46 The Future of AI and Organizational Design
01:03:00 Closing Thoughts and Future Aspirations

Keith's blog on why everything is prediction: https://cassiai.substack.com/p/everything-is-prediction
Website: https://cassi-ai.com/

Future of AI in E-commerce and Ad Tech 

Join us for a discussion with Staff AI Researcher and Project Leader from Criteo, Alberto Lumbreras. We chatted about how Agentic AI will transform the AdTech and e-commerce experience. 

Alberto shares his unique career journey from telecommunications engineering to AI and machine learning, exploring his involvement in social network analysis and PhD studies. The conversation goes into the evolving landscape of AI in e-commerce, with a specific focus on shopping assistants and agent interfaces. Alberto also discusses the challenges in developing AI systems for commerce, the impact on the ad tech industry, and future predictions. Learn about his views on the importance of unique data, the advent of smaller, more efficient AI models, and how AI will become more autonomous and integrated into daily life.

00:00 Introduction and Welcome
01:02 Alberto's Career Journey
03:06 AI and Social Movements
03:53 Joining Criteo and Current Work
04:52 The Future of Shopping with AI Agents
08:25 Impact on Ad Tech Industry
10:48 Challenges and Opportunities in E-commerce
21:06 Data as a Competitive Moat
26:21 Challenges in Retail Catalogs for AI
27:15 Dynamic Data in Travel Industry
28:19 Importance of Comprehensive Data for AI
28:41 User Willingness to Share Data
29:07 Research, Engineering, and Talent Crossover
30:00 Essential Skills for ML Researchers
31:45 Impact of AI Tools on Engineering
32:46 Advice for Working with AI
38:19 Future Trends in AI Development
44:49 Research Directions and Influential Papers
48:18 Books That Shape AI Thinking
51:41 Conclusion and Farewell

Link to the first solo publication mentioned in the podcast: https://arxiv.org/pdf/2510.04871

We welcome Michal Klos, former Tech Lead from ByteDance and ShareChat focusing on machine learning and recommendations. Michal recently joined Lex AI as Co-Founder, a tech start-up in Germany solving challenges in Legal Monitoring with AI, recently partnering with Deloitte.

 The conversation delves into the architecture and innovative solutions offered by Lex AI. Mical shares his views on integrating AI to streamline workflows while maintaining accuracy and efficiency. 

The episode also explores the importance of feedback in finding product-market fit, building 0-1 and navigates through the challenges and future trends in the legal tech space.

00:43 Michal's Career Journey
03:49 Working at ByteDance
06:48 Challenges at ShareChat
09:46 Founding Lex AI
10:20 Machine Learning Fundamentals
15:39 The Value of an MBA
20:01 Transitioning to Startups
24:01 Building Lex AI
32:19 Technical Insights of Lex AI
42:24 Overview of Legal Problems
43:30 Product Market Fit Challenges
45:53 Feedback and Adaptation
52:03 AI in Legal Tech
55:00 Startup Culture and Engineering
01:00:44 Future of AI in Legal Tech
01:04:45 Productivity Tools for Founders
01:15:37 AI Trends and Predictions
01:22:50 Conclusion and Final Thoughts

Learn more about Lex AI's partnership with Deloitte and how they are creating positive change here: https://www.lexai.co/post/deloitte-partnership-with-ai-startup-lex-ai-underscores-role-of-ai-in-legal-and-compliance

Exploring the Future of Longevity: Breakthroughs, Ethical Dilemmas, and Viva City

In this episode of the NeuralPod, Chris and Alexey discuss recent developments in the field of longevity, with an emphasis on breakneck innovations and ethical concerns. Our guest, Alexey, shares insights on his co-founded project, Viva City—a new initiative aiming to accelerate progress in longevity through special economic zones. They discuss the concept of 'sack of organs', the potential and controversy around gene-edited and animal-grown organs, and recent advances in longevity research. The podcast also sheds light on the importance of mega-projects for longevity, akin to the International Space Station or Apollo programs, and the need for substantial investments to make significant breakthroughs. Learn about the AI agents vs. aging hackathon aimed at attracting more talent to the longevity space and explore future possibilities of significantly extending human lifespan through technology.

00:00 Welcome Back to the Neural Pod
00:28 Longevity in the Mainstream
01:14 Recent Breakthroughs in Longevity
03:14 The Concept of 'Sack of Organs'
07:04 Ethical Dilemmas in Organ Replacement
09:50 AI and Organ Transplantation
14:31 Introducing Viva City: The Longevity City
16:16 The Vision Behind Viva City
24:59 Challenges and Negotiations for Viva City
29:56 Building Viva City: The Role of Universities and Smart People
30:23 Governance and Initial Experiments in Viva City
32:06 Challenges and Legal Considerations for Longevity Therapies
38:47 Global Perspectives on Longevity Research
47:27 AI and Longevity: The Hackathon Initiative
54:40 The Future of Longevity and AI
58:11 Conclusion and Final Thoughts

Join Chris as he sits down with Danijela Horak, former Head of AI of the BBC. Danijela holds a mathematics PhD and she is a machine learning expert. 

We explore her unconventional career path leading to the BBC. Danijela discusses common themes in machine learning, the importance of scientific thinking, and the role of AI in media and journalism.

Their conversation covers the increasing relevance of LLMs, deepfake detection, and initiatives for responsible AI. Learn about cutting-edge projects at the BBC, the challenges of balancing innovation with trust, and Danijela's leadership philosophy in a highly complex, interdisciplinary environment.

00:00 Introduction and Welcome
00:50 Danijela's Career Journey
03:36 Common Themes in Machine Learning
04:08 The Importance of Fundamentals in AI
08:20 Challenges in Programming and Engineering
16:35 AI Innovation at BBC
21:26 DeepFakes and Detection
30:42 Governance and Responsible AI
36:32 Leadership and Culture
44:44 Future Trends and Personal Use of AI
51:13 Conclusion and Farewell

Thanks for sharing your insights, Danijela!

Join us, as Chris interviews Pavan Vemuri, the Director of Product Engineering at SDVerse. Pavan shares his remarkable journey from working with Cognizant in India to leading AI and ML operations at major automotive companies like Ford and Stellantis. 

They discuss a range of topics, including the application of generative AI in the automotive sector, overcoming technical and organizational challenges, and building efficient ML infrastructure. Pavan also delves into his effective strategies for onboarding teams and scaling AI use across large organizations. They conclude with thoughts on future trends in AI and the rise of AI agents. 

Here's what we covered 👇

00:00 Introduction and Career Background
05:36 Move to Advanced Engineering at Ford
10:22 Implementing Data Quality Inference Engine
15:45 Role in Advanced Product Group
19:56 Centralized vs. Decentralized ML Platform
23:36 Entry into Generative AI
27:12 Overcoming Technical Hurdles
32:44 Improving Onboarding Process
38:59 Collaboration and Adoption
46:23 GenAI in Automotive
52:14 AI Productivity Tools and Techniques
56:21 Future AI Trends and Predictions
59:42 Building Trusted Teams and Culture

Thanks, Pavan, for sharing!

Exploring Agentic Systems and Infrastructure with Schaun Wheeler, Chief Scientist at Aampe. 

In this in-depth discussion with Schaun, we discuss his unique career path, from cognitive anthropology to leading roles in civil service and ad tech. Sean offers insights into the development of agentic systems for optimizing user experience and the challenges within. Here's what we covered 👇

✓ Schaun's career journey: From cognitive anthropology to data science
✓ The role of anthropology in data science and decision-making
✓ Common themes and challenges in machine learning projects
✓ Developing agentic infrastructure for consumer apps
✓ Key technical challenges in startup environments
✓ Building agentic systems at Aampe
✓ Aampe's Unique Approach to User Engagement
✓ The Role of LLMs in Engineering
✓ Agent Decision-Making Processes
✓ Navigating a fully remote global team culture
✓ Future advancements in agentic systems and AI
✓ The importance of understanding evidence and decision-making processes in AI
✓ Future of AI and Agents

Tune in for real-world AI insights and cutting-edge developments in agentic systems. 

Thanks, Schaun for sharing!