We chat through Grok 4 and Vending Bench, Chrome with Nano, Comet from Perplexity, A2A and the ADK kit and more from the AI, Agent engineering world.

Chapters

00:00 Introduction

00:34 Grok 4, Vending Bench

06:25 Vending Bench Benchmarking

09:43 Replit brings the Vibes to Microsoft

18:05 Browser wars, Nano in Chrome and Comet launch

29:00 Understanding A2A Protocol and Agent Development Kit

31:34 Agents as Problem Solvers vs Tools

37:29 Agent Card Specifications and Metadata

42:27 Robustness and Reliability of A2A Protocol

51:06 Practical Applications and Code Demonstration

57:47 Understanding Agent Communication and Debugging

01:06:42 Agent Cards and Composability in Development

01:13:20 Demonstrating the A2A Web Application

01:15:17 Exploring JavaScript Agents and Orchestrator Functionality

01:20:41 Connecting Agents for Travel Planning

01:23:12 Clarifying User Interactions in Travel Booking

01:26:25 Introducing the Build Vault and RAG Agents

01:27:12 Video Agent Demonstration and Challenges

01:36:59 Future Integrations and Closing Thoughts

In this episode of The Build, Tom Spencer and Cameron Rohn break down some of the biggest developments in AI infrastructure, medical reasoning, and agent deployment.

🏥 Highlights:

• Microsoft’s Agentic Medical AI paper and how LangGraph + Claude replicated the architecture

• Claude’s new MCP desktop apps — AI agents as drag-and-drop tools

• A mysterious new OpenAI model on OpenRouter with a 1M token context window • Cloudflare’s LLM paywall and “House of Mirrors” tech to trap AI crawlers • HIPAA-compliant retrieval with OpenEvidence

• Local model deployments with Gemma 3n and hybrid edge computing

• How startups are balancing inference cost vs. data infra as AI matures👀 Resources

Mentioned:

• Microsoft’s blog: https://microsoft.ai/new/the-path-to-medical-superintelligence/

• Cypher Alpha model on OpenRouter: https://openrouter.ai/openrouter/cypher-alpha:free

• OpenEvidence: https://www.openevidence.com/

• State of AI 2025 (ICONIQ): https://www.iconiqcapital.com/growth/reports/2025-state-of-ai

• LangGraph repo: https://github.com/langchain-ai/langgraph

• MedAgent demo code: https://github.com/The-Build-Podcast/mediagent

🔧 Code + Demos:→ GitHub: https://github.com/The-Build-Podcast

→ LangGraph + Claude demo walkthrough→ LangSmith traces and architecture diagrams

Chapters

00:00 Introduction and Overview

02:40 Microsoft Medical Agent Diagnosis

04:07 Claude AI and Desktop Applications

06:49 OpenAI and Competitive Landscape

09:23 State of AI Report Insights

17:58 Data Storage and Processing Costs

20:52 Cloudflare Innovations and AI Crawlers

30:29 The Explosion of AI Models

31:54 Exploring Multimodal Models

34:40 The Rise of Local AI Models

35:13 Innovations in On-Device AI

39:22 The Future of AI in Healthcare

45:53 AI in Medical Diagnostics

53:32 Limitations and Future Directions

58:11 Evaluations and Methodologies in AI

59:44 LangGraph and Langsmith Integration

01:01:05 Building a Medical Diagnostic Agent

01:04:59 Chain of Debate in Medical Diagnostics

01:08:22 Iterative Development and Debugging

01:12:55 Customizing Agent Architectures

01:18:55 Performance and Reasoning in AI Models

01:25:14 Future of AI in Medical ApplicationsShow

Links

https://openrouter.ai/openrouter/cypher-alpha:free

https://www.openevidence.com/

https://www.iconiqcapital.com/growth/reports/2025-state-of-ai

https://microsoft.ai/new/the-path-to-medical-superintelligence/

https://epoch.ai/data/large-scale-ai-models

https://www.linkedin.com/posts/tomasztunguz_remember-when-you-took-a-family-photo-ghibli-styled-activity-7343312053211734016-TcVU

https://lancedb.com/

https://theory.ventures/

https://www.cloudflare.com/en-au/press-releases/2025/cloudflare-just-changed-how-ai-crawlers-scrape-the-internet-at-large/

https://github.com/The-Build-Podcast

https://microsoft.ai/new/the-path-to-medical-superintelligence/

https://arxiv.org/abs/2506.22405 https://github.com/The-Build-Podcast/mediagent

Explore the future of AI agent architectures with Tom Spencer and Cameron Rohn. This deep-dive covers the power of multi-agent systems, from swarm intelligence to advanced agent collaboration, and how to build them using cutting-edge tools like LangChain, LangGraph, and the Model Context Protocol (MCP). Learn about the intersection of AI and cybersecurity, context management in LLMs, and the agentic workflows shaping the next wave of software development.🎙️ Hosts:• Tom Spencer: https://tomspencer.co• Cameron Rohn: https://cameronrohn.comCHAPTERS00:00 Intro: The Rise of AI Agents & Overview01:26 What are the latest developments in Model Context Protocol (MCP)?03:38 What were the key AI takeaways from Vercel Demo Day?06:14 How is AI creating a new frontier for SEO and AEO?11:32 How is content optimization evolving with AI?15:49 What is Vercel's role in modern AI application development?18:33 Which emerging tools and technologies are defining the space?22:44 What are the most effective agent communication protocols?26:43 How do AI and cybersecurity intersect in agentic solutions?34:52 How do current video models perform for content generation?37:39 What is the evolution of content production models?39:21 How can prompting techniques be refined for better AI results?41:22 What is the current state of text generation in video models?42:39 Where is OpenAI focusing its efforts for future video models?43:03 Diving into Agent Architectures44:52 Contrasting Perspectives on Agent Structures49:44 Navigating Errors in Multi-Agent Systems52:25 Understanding Swarm Architectures56:43 Complexity in Agent Interactions01:02:49 Introduction to MCP Tools and Agent Swarm01:04:09 Applications and Composability of Agents01:07:08 Marketplace of Agents and Microservices01:08:41 Context Degradation and Output Management01:10:38 Multimodal Agent Execution and Creative Work01:14:48 Deep Research with Langchain and Agent Architecture01:26:42 Multi-Agent Workflows and Practical Applications01:28:15 Understanding LLM Queries and Reports01:30:24 Context Engineering: Insights and Developments01:34:24 Evaluating AI Outputs and Traces01:38:36 Applications of AI in Real Estate and Research01:49:10 Building Effective AI Agents and Strategies🔗 Resources & Links Mentioned:

• LangChain Blog on Multi-Agent Systems: https://blog.langchain.com/how-and-wh...• Cognition AI on Agent Architectures: https://cognition.ai/blog/dont-build-...• LangChain Open Deep Research Repo: https://github.com/langchain-ai/open_...• OpenAI Cybersecurity Agents Demo: https://github.com/openai/openai-cs-a...• LangGraph MCP Server Concepts: https://langchain-ai.github.io/langgr...• Cameron Rohn's MCP Server Demo: https://github.com/Cam10001110101/mcp...📌 Topics Covered:• Multi-Agent Systems & Swarm Intelligence• AI Agent Architecture & Collaboration• LangChain, LangGraph, and MCP Tools• Agentic Workflows & Context Management• AI in Cybersecurity & Threat Detection• AI for SEO (AEO) & Content Optimization• Deep Research Agents & Multimodal Execution• AI Applications in Real Estate🔔 Subscribe to The Build Podcast for more deep dives into the world of AI and software development! Like this video if you found it valuable and let us know your biggest takeaway in the comments below.#AIAgents #LangChain #TheBuildPodcast

Links from the show

Cameron Rohn and Tom Spencer explore the latest in AI—from voice assistants and generative tools to no-code platforms and agentic systems. They unpack challenges in AI memory, Claude 4 and the growing role of AI in creative workflows.

Chapters

00:00 Introduction to Voice AI and Creative Tools

02:55 Deep Dive into Creative Tooling and Updates

05:46 Exploring Vercel and Figma's New Features

08:41 Gumloop and the Future of No-Code Solutions

11:30 Linear Agents and Their Impact on Development

14:23 Agentic Systems and Long-Running Workflows

17:18 The Importance of Benchmarks in AI

20:22 Impact of AI on Professional Services

23:12 Claude 4: Features and Economic Impact

26:01 System Prompts and Their Role in AI Behavior

35:33 Building Memory Engines in AI

37:44 The Art of Directing AI Responses

41:34 Understanding System Prompts and Tool Calls

45:18 The Impact of Package Choices on AI Outputs

49:02 Navigating Memory in AI Systems

58:29 The Future of Personalized AI Experiences

01:07:49 Exploring Memory in AI and Human Cognition

01:12:05 The Evolution of Generative AI Tools

01:15:06 Understanding Diffusion Models and Their Impact

01:20:24 The Future of Video Generation and AI

01:25:18 The Intersection of AI and Creative Expression

01:41:46 Exploring Interactive Animation with Remotion

01:44:27 Advancements in Interactive Environments

01:48:22 The Future of Creative Control in Video Production

01:53:47 Emerging Technologies: Neural Radiance Fields

01:57:48 The Metaverse and Its Implications for Creativity

02:01:11 The Evolution of Marketing and Technology Careers

https://www.anthropic.com/research/tracing-thoughts-language-model

https://www.tbench.ai/

https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

System Prompt Leaks - https://github.com/elder-plinius/CL4R1T4S/tree/main

https://www.youtube.com/watch?v=ugvHCXCOmm4

Triplex.com

https://x.com/noahmacca/status/1927014156152058075 https://platform.openai.com/docs/guides/evals  

https://x.com/ns123abc/status/1927491593181004212  

https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#interleaved-thinking

https://every.to/chain-of-thought/vibe-check-claude-4-sonnet  

https://x.com/simonw/status/1926636807875158060  https://huggingface.co/datasets/Anthropic/model-written-evals 

https://github.com/anthropics/evals  

https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf  

https://huggingface.co/datasets/Anthropic/hh-rlhf 

https://huggingface.co/Anthropic 

https://www.tbench.ai/about

https://assets.anthropic.com/m/2e23255f1e84ca97/original/Economic_Tasks_AI_Paper.pdf

https://huggingface.co/datasets/Anthropic/EconomicIndex

https://app.ltx.studio/motion-workspace

https://www.florafauna.ai/

Fal.ai

https://www.youtube.com/watch?v=UwvlPkAFx1Q

https://remotion.dev/

https://github.com/pmndrs/react-three-fiber

https://triplex.dev/

https://docs.nerf.studio/

https://deepmind.google/models/veo/

https://github.com/Vchitect/VBench

gumloop.com

linear.com

Join hosts Cameron Rohn and Tom Spencer for the inaugural episode of their weekly AI deep dive!

Chapter Links

00:00 Intro

00:35 LangChain Interrupt Conference Recap

03:00 Ambient Agents in High-Risk Use Cases

04:45 LangChain Product Updates: LangGraph & LangSmith

06:00 LangGraph Platform and Prebuilt Agent Marketplace

07:45 LangChain's MCP Integration and Cloud Desktop Demo

09:00 Keynote Themes: Evals and Agent Simplicity

10:45 Open Evals and "LLM as a Judge" Concepts

12:00 Agent Inbox and Email Task Manager Demo

13:45 Human-in-the-Loop UX and LangGraph Publishing

15:00 Agent Engineer as a New Role

16:30 Architectural Standards and LangGraph Adoption

18:00 Interesting Talks: Docet ETL and Data Challenges

21:00 Greg Kamradt, Arch Prize, and Context Engineering

23:15 Devon's Deep Wiki and Contextual Agents

25:00 Google’s Gemini 2.5 Pro and Diffusion LLMs

27:30 Google Labs: VEO V3, Flow, and Creative Tools

29:30 SynthID, Agent UX, and Agent Mode OS Concepts

31:00 Microsoft’s Ecosystem: Teams, MCP, and Identity

33:15 MCP Native to Windows & Local Development

35:00 Daytona, Cloudflare Sandboxes, and Remote Agents

38:00 Cloud Execution Environments and Security

40:00 One-Time Use Software and Just-In-Time Apps

42:00 LangGraph Prebuilts and Computer Use Agents

44:00 AI Containers, Sharing Memory & Swarm Architectures

47:00 Outlook on Supervisor Models vs Workflow Models

49:00 Wrap-Up and Final Thoughts on the Agent Ecosystem

Overview

They kick things off by unpacking the flood of insights from the recent LangChain 'Interrupt' Conference in San Francisco. Discover how agents are being trusted in high-stakes scenarios like finance, and why 'Agent Engineering' might be the next big role.

They cover LangChain's latest product launches, including LangGraph Platform and Agent Inbox, and its surprising lead over OpenAI in SDK downloads. Major announcements from Google and Microsoft's strategy, focusing on its ecosystem, AI Foundry, and building MCP (Multi-Agent Collaboration Protocol) natively into Windows and Teams.

Finally, the duo gets hands-on, discussing and demoing remote AI sandboxes. They explore tools like Daytona, Cloudflare's upcoming containers, E2B, and Scrapybara, showing how these environments enable complex, secure, and even disposable AI applications. Plus, catch their live reaction as Anthropic appears to launch Claude 4 during the recording!

Key Discussion Points:

• LangChain Conference Recap: Key themes (Simplicity, Agents, Evals), new products (LangGraph Platform, Agent Inbox, Pre-builts), MCP integration, and the Agent Engineer role.
• Google AI Updates: Scale, Gemini 2.5 Pro, Diffusion LLMs, Veo, AI Labs, Agent Mode, and Synth ID.
• Microsoft AI Strategy: Open source push, MCP in Windows, Teams integration, and the power of their identity ecosystem.
• OpenAI News: Acquisition of Jony Ive's IO startup.
• AI Tools & Demos: DocETL, Deep Wiki, NL Web, and a live demo of AI agents in Daytona remote sandboxes.
• The Future: Agent-to-Agent (A2A) communication challenges, the impact of remote execution environments, and the announcement of Claude 4.

Mentioned Links & Resources:

• LangChain: https://www.langchain.com/
• LangGraph: https://github.com/langchain-ai/langgraph
• Agent Inbox: https://github.com/langchain-ai/agent-inbox
• DocETL: https://github.com/ShreyaGanesh/DocETL
• Deep Wiki (Devin): https://github.com/devin-ai/deep-wiki
• NL Web (Microsoft): https://github.com/microsoft/NL2Web
• Google AI Labs: https://labs.google/
• Daytona: https://daytona.io/
• E2B: https://e2b.dev/
• Scrapybara: (Link Needed)
• Claude (Anthropic): https://www.anthropic.com/claude

Follow Cameron & Thomas:

Cameron Rohn:

https://cameronrohn.com/

LinkedIn

GitHub

X

YouTube

Thomas Spencer:

tomspencer.co

https://linkedin.com/in/tomspencerdigital

https://github.com/spencerthomas

https://x.com/surfcodetom

https://www.youtube.com/@tomspencer1286