AI Summit and CAT-MIP Initiative Cameron spoke at an AI summit hosted by N-able, a company formerly part of SolarWinds. His talk focused on the infrastructure gaps that Managed Services Providers (MSPs) face when handling AI. Consortium for AI Terminology (CAT-MIP): https://cat-mip.org/N-able (Host Company): https://www.n-able.com/AI Market and Stock News Google's stock is performing exceptionally well, and Gemini reportedly has 600-650 million daily active users. A new deal between Microsoft and OpenAI restructures OpenAI into a public benefit corporation, with Microsoft holding a 27% stake. As part of this, OpenAI pre-committed to purchasing $250 billion in cloud compute from Azure.Gemini User Statistics (Note: Research indicates 35M daily users and 450M monthly users): https://vertu.com/lifestyle/gemini-vs-chatgpt-user-numbers-comparison-features-2025-trends/The MCP Server Deployment Challenge Tom's project involves building an MCP (Model Context Protocol) server for massive.com, the new name for market data provider Polygon. Massive (formerly Polygon): https://massive.com/MCP Central Project Cameron's new project, mcpcentral.io, aims to solve this deployment problem. It builds the necessary infrastructure for the agent layer, making agent deployment and management easy for technical users and MSPs. The platform is designed for multi-tenancy, allowing MSPs to run services for clients without deep DevOps expertise.MCP Central Server Example: https://skywork.ai/skypage/en/ai-engineer-langchain-hub/1981168855956770816LangChain Agent Builder Demo A demo of LangChain's new Agent Builder, currently in private beta, shows how it creates agents from natural language. The tool includes pre-built triggers for services like Gmail, Slack, and Linear. An example email assistant agent successfully analyzed an inbox, categorized emails, and created a draft reply directly in a Gmail drafts folder.LangChain Agent Builder Documentation: https://docs.langchain.com/langsmith/agent-builderClaude Skills Explained and Demoed Anthropic's "Claude Skills" feature has been available for about a month. Skills are defined in skill.md files that provide instructions and can reference scripts, which then run in a secure, sandboxed cloud container. This method saves context and allows for repeatable, complex workflows. A demo of the "MCP builder" skill shows it successfully scaffolding a new, production-ready MCP server for the Massive/Polygon options trading API.Explanation of Claude Skills: https://simonwillison.net/2025/Oct/16/claude-skills/Getting Started with Claude Skills: https://neon.com/blog/getting-started-with-claude-skillsChapters00:00:00 Introduction & Weekly AI News00:01:33 Minimax M2 Model Analysis00:13:15 DGX Hardware Update00:14:19 AI Summit & Managed Services Providers (MSPs)00:16:24 CATMIP: A Terminology Standard for AI in IT00:20:53 Big Tech News: Google, Gemini, and Market Growth00:30:25 Demo: Options Trading MCP Server (Polygon/Massive)00:35:21 The Problem: How to Host and Share MCP Servers00:37:47 MCP Central00:44:20 ChatGPT Connectors & Developer Mode00:49:48 Grok Code Fast Model Update00:50:47 LangChain V1 Updates & LangSmith00:52:13 Demo: LangChain Agent Builder00:57:43 Demo: Email Assistant (Agent Builder)01:12:12 Agent Builder: Multi-Tenancy & Security01:13:43 LangSmith: Annotation, Datasets & Experiments01:18:54 Demo: LangSmith Agent Insights01:23:56 Introduction to Claude Skills01:25:12 Demo: Algorithmic Art Skill01:30:38 Claude Skills GitHub Repo01:33:25 Demo: Canvas Design Skill (Podcast Poster)01:37:41 Claude Plugin Marketplace01:40:00 Claude Skill Creator & MCP Builder01:45:26 Demo: Using the MCP Builder Skill01:50:43 Integrating LangSmith with Claude Code01:55:38 Quick Tip: Remote DGX Access with Cloudflare Tunnels01:56:15 Final Demo: Options Trading MCP Server Build Complete01:58:01 Wrap-up
Takeaways1- Tom discusses his recent trip to Texas and the importance of brisket.2 - Cameron shares his experience with the DGX and running DeepSeek OCR.3 - Tom highlights the funding announcement for LangChain and its implications.4 - Cameron expresses excitement about the new features in Google Gemini.5 - Tom discusses the performance of different AI trading algorithms.6 - Cameron shares insights on the OCR performance comparison between DeepSeek and Tesseract.7 - Tom explains the significance of the DGX in running large models.8 - Cameron discusses the potential for continuous fine-tuning in AI models.9 - Tom shares his thoughts on OpenAI's new browser and its market impact. 10 -Cameron and Tom explore new AI tools and their applications.
Takeaways1- Tom discusses his recent trip to Texas and the importance of brisket.2 - Cameron shares his experience with the DGX and running DeepSeek OCR.3 - Tom highlights the funding announcement for LangChain and its implications.4 - Cameron expresses excitement about the new features in Google Gemini.5 - Tom discusses the performance of different AI trading algorithms.6 - Cameron shares insights on the OCR performance comparison between DeepSeek and Tesseract.7 - Tom explains the significance of the DGX in running large models.8 - Cameron discusses the potential for continuous fine-tuning in AI models.9 - Tom shares his thoughts on OpenAI's new browser and its market impact. 10 -Cameron and Tom explore new AI tools and their applications.DescriptionSummary
In this conversation, Cameron and Tom discuss various developments in the AI landscape, including funding announcements, new tools like Google Gemini, and the performance of AI models in tasks such as OCR and crypto trading. They share personal updates, insights on the DGX system, and explore the implications of recent innovations in AI technology. The discussion also includes hands-on demos of new applications and a look into the future of AI workflows and automation.
Sound Bites
Key Points
Why “computer use” agents matter for real form-filling and CRUD tasks
Live look at Gemini 2.5 Computer Use, Browserbase/Playwright, and WebVoyager-style tasks
Operator vs Claude/Gemini computer use: accuracy, speed, and safety guardrails (CAPTCHAs, consent, impersonation)
Where computer use fits vs MCP tools, local OS access, and classic scraping
Veo 3.1 API update: reference images and start/end frames for consistent video
Claude Code Plugins & community marketplaces (sub-agents, tools, slash commands)
GitHub “Spec Kit” and spec-driven workflows for coding at scale
Cerebras inference speed vs quality tradeoffs; why speed sometimes beats depth
Local rigs and training: DGX Spark use cases and limits
Karpathy’s NanoChat: small-scale train-your-own chat model and cost envelope
“Agent Universe” demo: NAICS-led industry mapping → value flows → agent blueprints
Architecture questions: vertical vs horizontal agents, data layer, tool connectors (HubSpot, Procore, Google Workspace)
A focused walkthrough of today’s agentic stack in practice. The episode tests Gemini 2.5 “computer use” for real browser tasks, compares it with Operator and Claude, and breaks down safety guardrails and why screenshot-loop agents remain slow. It covers where computer use fits alongside MCP and OS tools, then shifts to Veo 3.1’s new API features for reference-guided video. On the coding side, it explores Claude Code Plugins and community marketplaces, plus GitHub’s Spec Kit for spec-driven development on large codebases. The discussion touches Cerebras for ultra-fast inference, DGX Spark for local experiments, and Karpathy’s NanoChat for training compact chat models. It closes with the “Agent Universe” demo: mapping industries via NAICS, generating value-flow diagrams, and turning stages into deployable agent roles, with open questions on architecture, tools, and handoff into real systems.
09:51 Exploring Claude's Capabilities and User Experience19:28 Real-Time Code Generation: Claude Imagine Demo41:02 The Evolution of User Interfaces for AI Agents48:29 Challenges in Research and Data Analysis with AI58:22 Sora 2 and Luma.labs Live demo - Ray Reasoning Video Model01:04:21 Copyright Challenges in AI Content Creation01:12:59 Interactive Video Creation and User Control01:23:45 Building an AI-First Strategy and The GDPEVal Data Set01:37:38 Real-World Applications of AI01:51:42 Navigating AI's Impact on Employment
In this episode, Tom Spencer and Cameron Rohn discuss various updates in the tech world, including the challenges of AI podcasting, the implications of H1B visa changes, and the competitive landscape of AI models from Alibaba. They also delve into the limitations of Figma in web design and explore Cloudflare's new Vibe SDK. Cameron Rohn and Tom Spencer delve into the capabilities of Cloudflare's Vibe SDK and its integration with various AI tools. They discuss the potential of creating scalable applications using Cloudflare Workers, the ease of deploying custom apps, and the importance of integrating design tools like Figma into the development process. The conversation also touches on the features of Cloudflare's AI Gateway, including data loss prevention and real-time agent kits, as well as the advancements in voice cloning technology with 11 Labs for podcasting.Chapters00:00 Introduction and Overview of Topics03:02 Visa Policies and Talent Acquisition05:26 China's K-Visa and Global Talent Competition07:56 Alibaba's New AI Models and Innovations10:55 Deep Dive into Alibaba's Omni Model13:24 Comparative Analysis of AI Models16:09 Future of AI and Global Competition33:19 Exploring Alibaba's Innovations in AI Video Generation35:32 Diving into Figma and the Rise of NanoBanana42:35 Challenges with Figma's AI Integration and Design Workflow52:45 Utilizing MCP Servers for Enhanced Design Collaboration01:00:15 Transitioning to Cloudflare's Vibe SDK and Backend Infrastructure01:01:28 Exploring Cloudflare's Ecosystem01:07:41 Understanding Durable Objects and Stateful Applications01:13:52 Integrating AI Models and Customization01:20:19 Cloudflare AI Gateway and Observability01:25:32 Guard Rails and Data Loss Prevention in AI01:26:03 Innovations in Data Loss Prevention and Real-Time Evaluation01:28:26 Exploring Real-Time Agent Kits and Cloudflare's Infrastructure01:32:09 Voice Cloning and Podcasting with 11 Labs01:39:16 Creating Interactive AI Agents for Business Applications01:45:58 Future of AI in Communication and Collaboration
00:00 Introduction and Personal Updates
04:33 Transformative Use of ChatGPT in Family Projects
07:20 Discussion on AI Economic Index Reports
17:46 The Rise of ChatGPT: Analyzing Growth Metrics
22:03 Exploring User Interaction: Conversations with AI
27:45 Market Position: ChatGPT vs. Competitors
36:35 The Future of Development: Integration and Collaboration
42:14 DeepMind's Innovations: Exploring New Frontiers
43:32 The Virtual Agent Economy
49:21 Google's AP2 Protocol and Agentic Commerce
01:02:40 Exploring World Models and Spatial AI
01:11:32 Exploring AI and Hardware Leapfrogging
01:16:03 Robotics and the Built Environment
01:20:13 Advancements in Robotics and AI Models
01:25:23 The Future of Home Robotics
01:30:36 Privacy Concerns with Autonomous Robots
01:36:20 Creative Applications of AI in Music Production
01:41:46 Creative AI in Music Production
01:49:57 Challenges in Music Production and AI Integration
01:56:17 Exploring AI's Potential in Music Composition
02:09:19 The Future of AI in Music and Sound Design
Also the best ai generated takeaways from this episode is:
Chapters
00:00 Welcome Back and Project Updates
03:30 Insights from the All-In Summit
06:21 Claude's Performance Issues and Alternatives
09:38 Exploring New Tools and Interfaces
12:38 Innovations in AI and Image Generation
15:34 The Future of Content Creation and AI
18:32 AI's Impact on Music Production
21:22 Reflections on AI in Creative Industries
24:35 Concluding Thoughts from the All-In Summit
34:03 Exploring Individuality and Ambition
35:32 Technological Innovations in Warfare
37:33 Cultural Nuances in AI Development
38:46 Emerging AI Technologies and Their Applications
40:39 AI Models and Future Predictions
45:45 OpenAI's Strategic Moves and Market Positioning
53:29 OpenAI's Acquisitions and Future Directions
56:38 Oracle's Role in AI Development
01:01:22 The Future of AI in Creative Production
Lots of demos, deep discussions and ai injections. Check the vault for the show notes, links and more at buildaipod.com
Chapters00:00 Introduction and Personal Updates00:46 Diving Deeper into GPT-5 Features and User Reactions01:48 Comparing GPT-5 with Previous Models04:08 User Feedback and Market Reactions06:37 Final Thoughts on GPT-5 and Future Directions10:57 Navigating Coding Agents and Abstraction Layers13:40 The Evolution of GPT Models and Their Applications18:07 Inference Compute and the Future of AI Investment19:57 Exploring Grok Desktop and Its Features27:25 Interoperability and Customization in AI Tools35:22 Introducing the Vault: A Centralized Resource for AI Applications42:02 Exploring Deep Agents and UI45:28 Running Deep Agents Locally47:19 Enhancing User Experience with UI Components50:13 Integrating Claude Code with Deep Agents56:37 Transitioning to Social Media Agents57:43 Complexity of Social Media Agent Architecture01:04:10 Monitoring and Managing Social Media Agents01:09:25 Streamlining Content Generation Processes01:12:54 Optimizing Code Repositories for AI Agents01:13:58 Navigating Corporate Culture Shifts01:16:49 Exploring Options Trading with AI01:22:47 Integrating AI with Financial Data01:28:42 Full Loop Development in AI Projectssign up to the vault to get all the details about the show - buildaipod.com
We recorded August 7th, right before ChatGPT launched.
We dove into GPT open source, OpenCode, Ollama Turbo, and deep agent setups.
I wanted to see LangChain’s open suite and test agent environments.
OpenCode stood out for its flexibility — multiple model providers, easy local setup, works with Ollama Turbo for $20/month.
LM Studio runs similarly.
I’m considering a high-spec NVIDIA rig and DGX Spark for local inference.
GPT-OSS is cheap, fast, and excellent for coding and tool-calling, but weaker on general knowledge.
Running it locally means more setup work but more control.
Hybrid local-plus-cloud routing feels inevitable.
We demoed OpenAgent Platform — fast, multi-provider agents without writing code.
Then explored LangChain SWE — an open-source, multi-threaded coding agent with planner/programmer loops, GitHub integration, Daytona sandboxes, and detailed token-cost tracking.
We looked at Vercel’s v0 API for quick generative UI, and the potential to run it privately for internal teams.
I closed with Google’s upcoming AI-mode ads and Societies.io — a virtual audience simulation tool for testing and optimizing content before publishing.
Chapters
00:00 Introduction to ChatGPT Launch and Demos
01:40 Exploring Open Code and LangChain
04:37 Local Inference and Olamma Integration
07:25 Cloud Acceleration with Turbo Service
10:11 Open Source Model Benchmarks and Feedback
Notes to come.
Part one of two, for this week's show. Updates , links and notes coming soon.
Check out buildaipod.com and the Vault for all the details.
In this episode, we dive into the latest AI news, covering new open-source models like Qwen3 Coder and OpenAI's new agent.
We discuss a major AI breakthrough at the Math Olympiad, where models achieved gold medal scores, and unpack recent AI executive orders from the Trump administration. In our demo segment, we show how to use JSON for ad vanced AI video generation. We also introduce "The Build Vault," our new project for creating a searchable knowledge base from our podcast content using tools like LangGraph and Neo4j.
Chapters
Insights
Keywords
Tom and Cam explore recent AI advancements, with particular focus on the Kimi model, its capabilities, and developer implications. They address SaaS industry challenges, including rising customer acquisition costs and the trend toward consumption-based pricing models. The conversation highlights developers' growing influence in AI technology development and the critical role of customer retention in SaaS business success. They also discuss enterprise AI adoption, RAG (Retrieval-Augmented Generation) applications, and effective data vectorization techniques. Additional topics include Cognition's acquisition of Windsurf, the continuing importance of ETL processes, and how local models can improve data processing efficiency. Throughout their discussion, they emphasize the value of layered data management approaches and how traditional methods remain relevant alongside emerging technologies.
Chapters
00:00 Introduction and Technical Setup03:56 Exploring the Kimmy Model15:46 Developer-Centric AI Models23:25 Rapid Development in AI Tools25:00 Exploring Kimmy's Capabilities29:21 SaaS Industry Challenges and Changes33:23 Customer Acquisition Cost Insights38:13 The Future of SaaS in an AI-Driven World42:47 RAG and Vectorization in AI Development59:18 Understanding UMAP and Clustering in Data Representation01:02:14 Building a Mobile Inspection Tool for Real Estate01:05:23 Transforming Natural Language into Structured Data01:09:46 The Importance of ETL Processes in AI01:14:50 Defining Effective ETL Pipelines01:20:23 Exploring RAG and Its Applications01:28:39 The Role of Vector Stores in Data Management
Links
https://github.com/lmcinnes/umap
https://pair-code.github.io/understanding-umap/
https://www.pinecone.io/learn/vector-database/
LLM vectorization - https://bbycroft.net/llm
UMAP - Vizualisation of embeddings, Nomic Atlas Vizualisation - https://atlas.nomic.ai/data/andrewgao22/hacker-news/map
https://projector.tensorflow.org/
Example Superlinked Demo -https://hotel-search-recipe.superlinked.io/
https://docs.unsloth.ai/basics/kimi-k2-how-to-run-locally
https://developers.googleblog.com/en/gemini-embedding-available-gemini-api/
https://moonshotai.github.io/Kimi-K2/
https://platform.moonshot.ai/docs/introduction#text-generation-model
https://docs.superlinked.com/getting-started/why-superlinked
Keywords
AI, Kimi2 Model, SaaS, Technology, Coding, Developer Tools, Machine Learning, Open Source, API, Performance, SaaS, AI adoption, cloud computing, RAG, vectorization, ETL, Cognition, Windsurf, local models, data processing
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
NAICS Analysis - A16Z - https://a16z.com/vsaas-vertical-saas-ai-opens-new-markets/
Codes - https://www.census.gov/naics/
ONet - Tasks - http://onetonline.org/link/summary/11-2022.00
https://arxiv.org/html/2503.04761v1
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://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
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://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.youtube.com/watch?v=UwvlPkAFx1Q
https://github.com/pmndrs/react-three-fiber
https://deepmind.google/models/veo/
https://github.com/Vchitect/VBench
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:
Mentioned Links & Resources:
Follow Cameron & Thomas:
Cameron Rohn:
Thomas Spencer:
tomspencer.co
https://linkedin.com/in/tomspencerdigital
https://github.com/spencerthomas
https://x.com/surfcodetom
https://www.youtube.com/@tomspencer1286