Tool Use - AI Conversations

Check out www.ToolUsePodcast.comAre AI web browsers falling short of the hype? Enter Rover, a revolutionary open-source AI agent that unlocks full autonomous workflows directly on your website with just a single script tag. In this episode, Arjun and Bhavani from rtrvr return to dive deep into how Rover uses a unique DOM-only approach to navigate, click, and type with subsecond latency. This innovative method completely bypasses slow screenshot-based models and outdated playwright or puppeteer scripts. We discuss the engineering secrets behind building smart DOM trees, why they crushed web benchmarks, and how Rover provides a powerful alternative to Google's Web MCP by keeping users engaged on your site instead of handing traffic over to external AI tools. Plus, learn how you can trigger complex agentic workflows via simple URL queries and why open-sourcing this technology is a massive win for the developer community.Rover links:https://x.com/rtrvrairover.rtrvr.aiGithub: https://github.com/rtrvr-ai/roverRover Deep dive: https://www.rtrvr.ai/blog/10-billion-proof-point-every-website-needs-ai-agentBenchmark: https://www.rtrvr.ai/blog/web-bench-resultsConnect withushttps://x.com/ToolUsePodcasthttps://x.com/MikeBirdTechhttps://x.com/rtrvrai00:00:00 - Intro00:03:05 - The DOM-Only Approach vs Screenshots for AI Agents00:06:00 - Parsing HTML vs Markdown for Reliable LLM Data00:11:47 - Handling Modals, iFrames, and Canvas Elements00:15:32 - Implementing AI Guardrails and Extracting User Intent Data00:28:04 - Rover vs Google Web MCP for Website Automation00:31:25 - Triggering Autonomous AI Workflows via URL QueriesSubscribe for more insights on AI tools, productivity, and web automation.Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXTool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXIn 2026, building an AI product is easier than ever, but getting traction and finding customers is the real challenge. In episode 82 of Tool Use, we sit down with Mano Tsiris, a serial exited founder and head of growth at Optimal AI, to break down the ultimate go-to-market strategy for technical founders and builders. Discover how to validate your startup ideas and talk to users before writing a single line of code. Mano shares his proven marketing playbook, including how to build in public on LinkedIn, repurpose content using AI tools like Gemini and Claude Code, and leverage IRL events to grow your network. Whether you are bootstrapping a side project or trying to get your first hundred users, this conversation is packed with actionable advice on distribution, audience building, and standing out in a crowded market.Mano Tsiris on LinkedIn: https://www.linkedin.com/in/emanueltsirisOptimal AI: https://getoptimal.aiConnect with ushttps://x.com/ToolUsePodcasthttps://x.com/MikeBirdTech00:00:00 - Intro 00:03:53 - Mindset Shift: From AI Builder to SaaS Seller 00:09:21 - Building in Public & Thought Leadership Strategies 00:11:21 - Repurposing Content & SEO with AI Tools 00:22:12 - A/B Testing & Finding Viral Hooks with Gemini 00:26:56 - Startup Ideation: How to Validate SaaS Ideas Before Building 00:37:02 - The Ultimate AI Marketing Tech Stack for FoundersSubscribe for more insights on AI tools, productivity, and startup growth.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXAre you looking to optimize your AI applications with the best open source Large Language Models? This week, we explore open source AI, rapid model switching, and local self-hosting with Nathan Break, a Machine Learning Engineer at Mozilla AI and the creator of Any-LLM. Any-LLM is an open-source Python SDK that allows developers to seamlessly talk to any LLM provider through a single, unified interface.Nathan demonstrates how developers can instantly swap between cloud-hosted AI providers and local models like Llamafile by changing just a single line of code. We dive into the growing capabilities of smaller, cost-effective models, how to reduce your API expenses, and the security benefits of running local AI on your own hardware. Nathan also introduces the Any-LLM Platform, a secure vault for managing API keys that tracks your token usage and enforces budget limits without ever accessing your prompt data. Finally, we check out Porch Songs, Nathan's open-source application that leverages LLMs to rewrite the lyrics of popular songs while maintaining their original rhyme schemes and chord charts.Check out the projects mentioned in this episode:Any-LLM GitHub: https://github.com/mozilla-ai/any-llmAny-LLM Platform: https://any-llm.aiMozilla AI Blog Post: https://blog.mozilla.ai/introducing-any-llm-a-unified-api-to-access-any-llm-providerPorch Songs GitHub: https://github.com/njbrake/porchsongsConnect with ushttps://x.com/ToolUsePodcasthttps://x.com/MikeBirdTech00:00:00 - Intro 00:01:25 - What is Any-LLM? Unified API for Open Source AI 00:05:32 - Benefits of Rapid Model Switching & Open Weight Models 00:11:06 - Any-LLM Python SDK Demo: Mistral Image Recognition 00:19:51 - Best Local AI Models: Llamafile, LM Studio & Local LLMs 00:24:38 - Any-LLM Platform Vault & Porch Songs App Demo 00:34:45 - AI Coding Agents, Claude Code & LLM EvaluationsSubscribe for more insights on AI tools, productivity, and open source development.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXAre you putting your business at risk by relying on big AI companies? In this episode of the Tool Use podcast, we dive deep into Sovereign AI with Max McCrea, founder of Greyhaven. We explore how businesses can maintain control of their private data while still benefiting from AI. Max breaks down the importance of self-hosting and building architectures that abstract away the model provider so you can easily swap them out. We also discuss practical AI architecture decisions, the dangers of un-sandboxed AI agents, and how to set up software-defined sandbox environments to reduce the attack surface. Whether you are curious about running open source models or replacing proprietary tools, this episode provides a guide to taking back control of your systems.Guest Links:https://greyhaven.cohttps://maxmccrea.comhttps://github.com/GreyhavenHQConnect with ushttps://x.com/ToolUsePodcasthttps://x.com/MikeBirdTech00:00:00 - Intro00:12:17 - AI Context Management & Personal Data Indexing00:20:40 - Open Source Replacements vs Proprietary SaaS Tools00:29:14 - Corporate AI Data Harvesting & Vendor Lock-in00:49:18 - LLM Orchestration & AI System Architecture00:53:24 - Best Open Source AI Models for Self-HostingSubscribe for more insights on AI tools, productivity, and data sovereignty.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXVector databases can be an important component for building reliable AI agents and scalable semantic search applications. In this episode, Arjun Patel from Pinecone breaks down how to optimize your RAG pipeline, choose the right embedding models (sparse vs. dense), and implement effective chunking strategies for better data retrieval. We also explore the new Pinecone plugin for Claude Code, demonstrating how to build a recommendation system and chat with your documents using Pinecone Assistant without writing complex code.https://www.pinecone.io/ https://www.linkedin.com/in/arjunkirtipatel/Connect with us  https://x.com/ToolUsePodcast https://x.com/MikeBirdTech 00:00:00 - Intro 00:01:11 - What Vector Databases Unlock 00:04:40 - Optimal Chunking Strategies for RAG 00:09:07 - How Embedding Models Work 00:17:25 - Improving Search with Re-ranking 00:26:52 - SQL vs Vector Database Architecture 00:35:48 - Claude Code & Pinecone Assistant DemoSubscribe for more insights on AI tools, productivity, and vector databases.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXUnlock the power of AI fine-tuning for image and video models with Greg Schoeninger, CEO of Oxen.ai. In this episode, we explore how to move beyond simple prompt engineering to training custom open-source models for as little as $1. Discover the technical strategies for building high-quality datasets, the trade-offs between LoRAs and full fine-tunes, and how to achieve consistent characters and styles in generative video.We dive into real-world examples, including how to generate massive product catalogs for a fraction of the cost of enterprise APIs and the story behind the viral "Isometric NYC" project built with Claude Code. Greg breaks down the entire AI lifecycle—from data curation and labeling with Vision Language Models (VLMs) like Qwen and Gemini to deploying efficient, specialized models that outperform general-purpose giants. Whether you are looking to optimize GPU costs, automate video workflows, or build your own AI tools, this conversation provides the blueprint for scaling your AI capabilities.Links from the episode: Oxen AI: https://www.oxen.ai/ Fine Tuning Fridays: https://luma.com/oxen Isometric NYC Project: https://cannoneyed.com/projects/isometric-nycConnect with us  https://x.com/ToolUsePodcast https://x.com/MikeBirdTech  https://x.com/gregschoeninger00:00:00 - Intro 00:01:47 - When to Switch from Prompt Engineering to Fine-Tuning 00:11:05 - How to Build a Dataset for AI Fine-Tuning 00:21:52 - LoRA vs. Full Fine-Tuning Explained 00:27:53 - Case Study: Fine-Tuned Qwen 3 VL vs. Google Gemini 00:36:33 - Case Study: Isometric NYC with Claude CodeSubscribe for more insights on AI tools, productivity, and fine-tuning.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXUnlock the ability to build AI tools without coding experience as Justin Borge joins Tool Use to demonstrate how he built Helios, a personal management system, using only LLMs like Gemini and Claude. Justin breaks down his transition from marketer to growth engineer, sharing his exact workflows for using JSON documentation to give AI a perfect memory of his business and goals. He reveals his unique "bullying" strategy for debugging code using persona-based prompts and explains how he created a human-in-the-loop system to safely edit local files without hallucinations. This conversation covers everything from writing your first Python script to mastering meta-prompting for maximum productivity.https://www.linkedin.com/in/justinborge/ https://justinborge.comConnect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech00:00:00 - Intro 00:03:49 - Top AI Tools & JSON Workflows 00:10:06 - Transitioning from Marketing to Engineering 00:12:23 - How to Debug Code Without Coding Knowledge 00:13:56 - Persona Prompting & "Bullying" LLMs 00:18:09 - Live Demo: Helios AI Management System 00:31:29 - How to Start Building AI Tools TodaySubscribe for more insights on AI tools, productivity, and growth engineering.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXDiscover the power of the Ralph Wiggum Loop with Ryan Carson as we explore the future of AI coding agents, autonomous workflows, and building one-person companies. In this episode, we break down how to implement Jeff Huntley’s simplified bash script loop using tools like Claude Code and Amp to ship features faster than ever. Ryan shares his tactical advice on creating high-quality PRDs, defining clear acceptance criteria for agent browser testing, and moving beyond human-in-the-loop development. We also dive into advanced AI engineering strategies, including self-healing systems, MCP servers like Sentry and Fizzy, and how to use LLMs to automate business operations through CRON job insights and email marketing drips. Whether you are an AI engineer or a founder, learn how to stop writing syntax and start orchestrating a fleet of agents to amplify your delivery speed and creative joy.Follow Ryan's Work: Untangle: https://www.untangle-us.com/ Ralph Loop Repo: https://github.com/snarktank/ralph Ryan on X: https://x.com/ryancarsonConnect with ushttps://x.com/ToolUsePodcasthttps://x.com/MikeBirdTechhttps://x.com/ryancarson00:00:00 - Intro 00:01:17 - How the Ralph Wiggum Loop Works 00:02:46 - Fresh Context Windows vs. Context Rot 00:12:15 - Deterministic Harnessing and Agent Hooks 00:17:59 - Agent Browser Testing & Acceptance Criteria 00:28:13 - Automating Business and Marketing Loops00:39:09 - PR Review Bots and AI Engineering WorkflowsSubscribe for more insights on AI tools, productivity, and orchestration.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXClaude Code is evolving from a terminal-based developer tool into the Everything Agent that manages your entire life. In this episode, Eric Buess returns to show us how he built a hands-free, voice-controlled AI system that handles everything from school emails and calendar scheduling to monitoring family text messages. We dive deep into advanced Claude Code strategies, including how to use the hook system to intercept model prompts and the Ralph Wickham loop to enable truly autonomous task completion. Eric explains why he moved away from static claude.md files in favor of programmatic hooks that steer the model with surgical precision. We also explore the power of adversarial sub-agents that fact-check AI claims and the Titus wake word system that lets him command his terminal from a car or Meta Ray-Ban glasses. Whether you are a developer looking to maximize the Anthropic Agent SDK or a productivity enthusiast wanting to reclaim your time, this masterclass in agentic workflows will change how you think about AI automation.Keep up with Eric: https://ericbuess.aiConnect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech https://x.com/EricBuess00:00:00 - Intro 00:02:20 - The Claude Code Hook System & Vertical Stack 00:03:08 - Why Agentic Hooks Matter for Automation 00:11:58 - Replacing claude.md with JSON Rules & Hooks 00:16:43 - Multi-Agent Workflows & Adversarial Validation 00:29:58 - Autonomous Task Loops & Self-Referential Injection 00:41:00 - Hands-Free AI: Voice-Controlled Claude CodeSubscribe for more insights on AI tools, productivity, and Agentic Workflows.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXSukh Saini, an exited founder and the creator of Engyne, joins Tool Use to break down the essential strategies for AI product distribution and personal branding. With a track record of 38 products, Sukh shares how he transitioned from a self-proclaimed horrible employee to a successful entrepreneur by mastering the business loop of building, selling, and scaling. This episode covers the vital shift from managing multiple low-revenue apps to focusing on exponential growth through high-conviction projects like Retail, which he sold after finding a unique distribution edge within the Stripe marketplace.Learn why building in public is a massive advantage for establishing trust and why marketplaces like Canva, Stripe, and the ChatGPT store are the next big frontiers for indie developers. Sukh also details his practical framework for validating demand through industry research and hypothesis-driven customer calls, ensuring you solve high-value problems before writing a single line of code. Whether you are interested in B2B SaaS, AI app stores, or building a thought leadership brand on LinkedIn, this conversation provides a tactical playbook for any builder looking to win in the AI era.Engyne: https://engyne.ai/ Sukh's LinkedIn: https://www.linkedin.com/in/sssaini/Connect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech https://x.com/thisissukh_00:00:00 - Intro 00:01:21 - How to build a winning product loop 00:04:26 - Mastering product distribution and the Stripe marketplace 00:08:12 - Why building a collection of small apps is a mistake 00:14:56 - Validating SaaS demand before writing code 00:21:56 - Tactical framework for finding customer pain points 00:27:59 - The competitive advantage of building in public 00:42:27 - Unlocking distribution through the ChatGPT app storeSubscribe for more insights on AI tools, productivity, and entrepreneurship.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXMaster your AI career in 2026 with this comprehensive guide on how to get a job in AI as a developer or non-technical professional. Mike Bird, AI and Engineering Lead at BoxOne Ventures, breaks down his personal journey from software developer to AI leader and shares insider secrets on the modern hiring process. Learn why traditional resumes are failing in the age of AI screeners and why you should embrace building in public, networking at AI Tinkerers events, and creating obnoxious resumes to stand out from thousands of bot-driven applications. Whether you are looking to become an AI engineer, a specialized AI consultant, or the AI champion at your current company, this episode provides actionable strategies on leveraging tools like Claude Code, Cursor, and more to proof-of-concept your way into the fastest-growing industry in human history. We dive deep into the technical skills required for 2026, including managing fleets of AI agents and mastering security audits, while also addressing career pivots for those in their 40s or 50s.Connect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech00:00:00 - Intro00:01:02 - Career Pivot Strategy: From Dev to AI Lead00:03:35 - Beat AI Screeners: The Case for the "Obnoxious" Resume00:10:43 - 2026 AI Engineer Interview: Technical Screens & Vibe Checks00:16:08 - AI Consulting vs Productizing: Knowledge Arbitrage Tips00:20:08 - Build in Public: How to Increase Your AI Luck Surface Area00:25:30 - Non-Technical Strategy: Becoming an AI Champion00:30:32 - Realistically how long it takes to transition into AI00:36:26 - Is it too late to learn AI if you are 40+ or 50+?Subscribe for more insights on AI tools, productivity, and entrepreneurship.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXIn this 2025 year-end wrap-up, we dive deep into the massive shifts in the AI landscape, from the surprise release of GPT-5.2 to the rise of open source models like DeepSeek. Mike Bird and Richardson Dackam reflect on a year defined by accelerating iteration cycles, the growing energy bottleneck for data centers, and the emergence of reasoning models that have changed how we approach complex tasks. We also look ahead to 2026, predicting the evolution of browser agents, the integration of AI in physical robotics, and why the next frontier of artificial general intelligence might actually be found in biological simulation. Whether you are interested in fine-tuning open models, the future of AI-generated content, or how programmable payments through crypto will enable the agentic future, this episode covers the essential trends every AI builder needs to know.Check out Richardson's workhttps://www.nshipyard.com/Connect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech https://x.com/RichardsonDx00:00:00 - Intro00:00:26 - Frontier Model Race: Gemini 3 vs GPT-5.200:07:27 - Open Source AI and the DeepSeek Market Shock00:12:06 - The Future of AI Interfacing: Voice & Multimodality00:30:39 - Browser Agents and Agentic Tools for 202600:41:58 - Physical AI: The Humanoid Robot Revolution00:48:20 - The Next Frontier: Why Biology is the Bottleneck for AGISubscribe for more insights on AI tools, productivity, and automation.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXDiscover how to master your executive function and reclaim your schedule with AI. In Episode 71 of Tool Use, Sam Julien (Director of Developer Relations and Experience at Writer) joins Mike Bird to explore how AI acts as the ultimate equalizer for productivity and mental clarity. We dive deep into practical strategies for reducing the time tax of administrative drudgery, using AI voice-to-text for brain dumping, and leveraging models as rubber duck brainstorming partners. Whether you are navigating new parenthood, managing a fast-paced career, or looking to avoid burnout, this conversation covers the micro-skills that lead to massive quality-of-life improvements. From using local Whisper models for privacy to the role of AI in creative work, learn how to stop the brain rot and start using technology to find your flow.Learn more about Sam Julien: http://www.samjulien.com/https://www.linkedin.com/in/samjulien/Connect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech https://x.com/samjulien00:00:00 - Intro 00:01:21 - Validating AI Engineering: Moving from Hype to Reality 00:02:14 - Mastering Executive Function with AI Voice Dictation 00:06:53 - AI as a Brainstorming Partner and Rubber Duck 00:15:36 - Solving the ROI Challenge: Context Engineering vs. Drudgery 00:18:43 - Leveraging AI to Prevent Burnout and Admin Fatigue 00:26:14 - Navigating AI Monoculture and Preserving Human ConnectionSubscribe for more insights on AI tools, productivity, and executive function.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXDiscover the future of front-end development with Cluso, an AI-powered web inspector and browser designed for "vibe coding." In this episode, Jason Kneen returns to demonstrate how to build bespoke AI tools that go beyond simple transcription. We dive deep into implementing voice control with context-aware agents, mastering the Model Context Protocol (MCP) for tool integration, and building fast orchestration layers to route requests between local models and cloud agents like Claude and Gemini. Whether you are interested in Electron app development, context splicing, or multi-view mobile testing, this conversation covers how top builders are creating their own workflows.Cluso: https://cluso.app/Connect with ushttps://x.com/ToolUsePodcasthttps://x.com/MikeBirdTechhttps://x.com/jasonkneen00:00:00 - Intro00:07:54 - Building Voice Control for AI Agents00:15:20 - Leveraging MCP for Better Tooling00:19:42 - Fast Orchestration & Model Routing00:25:06 - Multi-Model Agent Architecture00:31:13 - Cluso Demo & WorkflowSubscribe for more insights on AI tools, productivity, and modern software development.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXDiscover how non-technical founders are building valid MVPs using vibe coding and Cursor, and why you need to move beyond simple AI wrappers. We sit down with Mike Leslie, CEO of Revela, to discuss the critical strategies for de-risking your business from big AI labs like OpenAI and Anthropic. Learn when to transition to in-house open-source models, how to fine-tune small language models (SLMs) for specific use cases, and the best methods for structured data collection to build a defensible IP moat.https://revela.io/ https://www.linkedin.com/in/mike-leslie-8b48a9141/Connect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech https://x.com/MikeLeslieML00:00:00 - Intro 00:04:14 - Advice for Non-Technical Founders: The "Vibe Coding" Revolution 00:13:07 - Hiring Strategy: Agency vs. In-House Tech Team 00:15:22 - Why You Must Move AI In-House: Small Language Models (SLMs) & Control 00:21:20 - How to Build a Data Moat: Structured Collection & Fine-Tuning 00:29:28 - The Trap of Thin Wrappers: The Cursor vs. Anthropic Cautionary TaleSubscribe for more insights on AI tools, productivity, and AI engineering.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXBuilding AI agents is the current trend, but are you doing it correctly? Sam Bhagwat, founder of Mastra, joins Tool Use to breakdown the principles of building reliable AI agents. We discuss why you should use a TypeScript agent framework like Mastra, how to engineer production-grade prompts, and the best patterns for tool calling. Sam explains advanced concepts like observational memory, dynamic agents, and the "lethal trifecta" of security risks. Whether you are building coding agents or enterprise workflows, this episode covers the essential primitives for success.Mastra: https://mastra.ai/ Get the Book: https://mastra.ai/bookConnect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech https://x.com/calcsam00:00:00 - Intro 00:01:19 - When to use an AI Agent Framework 00:06:05 - Principles for designing Agent Tools 00:11:01 - Human-in-the-loop Architectures 00:17:19 - Working Memory vs Long-term Memory 00:32:03 - The "Lethal Trifecta" of Security RisksSubscribe for more insights on AI tools, productivity, and AI Agents.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXTurn your Obsidian vault into a fully automated operating system using Claude Code and AI agents. In this episode of Tool Use, physicist and AI explorer Artem Zhutov reveals how to leverage coding agents for non-coding workflows to optimize your productivity.Discover how to build a dynamic "second brain" that acts as a personal coach, automates daily planning, and streamlines job searches—all while keeping your data local. Artem breaks down his unique setup where Claude Code interacts directly with his Obsidian files, running Python scripts and custom slash commands to create reliable, affordable, and powerful automations. From "just-in-time" context loading to instant voice note transcription with WhisperFlow, this conversation covers the cutting edge of personal knowledge management (PKM) and local AI assistance.Artem:Website: https://artemxtech.github.io/ YouTube: https://www.youtube.com/@ArtemXTech Connect with us https://x.com/ToolUsePodcasthttps://x.com/MikeBirdTechhttps://x.com/ArtemXTech00:00:00 - Intro 00:05:25 - How to Identify & Plan AI Workflows 00:11:36 - Building a "Second Brain" Morning Routine 00:17:48 - Automating Job Searches with Claude Code 00:22:03 - Managing Context with Claude.md Helper Files 00:31:55 - Making AI Agents Reliable with Deterministic Scripts 00:43:27 - How to Start Building Coding Agent WorkflowsSubscribe for more insights on AI tools, productivity, and automation.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXAI Agents, RAG hype, and the "Impossible Triangle" of LLM Infrastructure take center stage in this deep dive with Swyx (Shawn Wang). As the co-founder of AI Engineer and a team member at Cognition, Swyx breaks down why vertical agents are the golden opportunity for developers right now. We explore the decline of standalone vector databases, the rise of MCP vs. Computer Use, and why your prompts shouldn't live in your codebase. Whether you are building AI tools or trying to scale them, this conversation covers the essential shift from "vibe coding" to serious engineering using AI Gateways and proper evaluations.Swyx's Website: https://www.swyx.io/ Read the Impossible Triangle of LLM Infra: https://www.swyx.io/impossible-triangle Latent Space: https://www.latent.space/Connect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech https://x.com/swyx00:00:00 - Intro 00:04:03 - Why Agentic Browsers Haven't Stuck Yet 00:05:33 - Voice vs Slack: The God Interface 00:11:24 - Why MCP Won & The Reality of Integrations 00:18:27 - The Vector Database Hype Cycle 00:20:37 - Why You Should Build Vertical AI Agents 00:30:03 - Stop Putting Prompts in Your CodebaseSubscribe for more insights on AI tools, productivity, and agentic workflows.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXExplore AI risk mitigation, prompt injection dangers, and AI safety in this deep dive with AI engineering consultant Kyle Clark. We discuss the critical role of human-in-the-loop systems, safe AI implementation strategies for businesses, and the hidden dangers of AI web browsers and context rot. Kyle shares expert insights on leveraging AI tools like Claude Code, managing subagents, the pitfalls of MCP servers, and the build vs. buy debate for AI models. Learn how to use AI safely in your personal life and what companies must do to prepare for an AI transformation, including data governance and permissions management.Keep up with Kyle Clark https://www.linkedin.com/in/kyle-clark-tech/Simon Willison's "The Lethal Trifecta" https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/Connect with us https://x.com/ToolUsePodcast https://x.com/MikeBirdTech00:00:00 - Intro00:00:49 - The New Plane of AI Risk & Prompt Injection00:10:30 - How Businesses Can Implement AI Safely00:13:21 - Human in the Loop & Claude Code00:17:18 - Using Subagents as a Mitigation00:31:03 - The Build vs. Buy Debate for AI Models00:36:06 - What is Context Rot (And Why It Matters)Subscribe for more insights on AI tools, productivity, and AI safety.Tool Use is a weekly conversation with the top AI experts.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXMaster n8n workflow automation in this complete guide. If you're tired of manual tasks, n8n (an open-source Zapier alternative) might be the solution. Richardson Dackam, founder and AI builder, joins Mike to explore how developers can save time using n8n. We dive into powerful use cases like email management, social media automation, and prototyping. Learn how to integrate AI models (OpenAI, Anthropic, Gemini), run custom code scripts, use webhooks, connect to databases, and implement human-in-the-loop validation. Richardson also shares common pitfalls, observability strategies, and the difference between self-hosting and the cloud.Learn more from Richardson: https://richdackam.comhttps://www.nshipyard.comConnect with us https://x.com/ToolUsePodcasthttps://x.com/MikeBirdTechhttps://x.com/RichardsonDx00:00:00 - Intro 00:00:32 - What is n8n? (Open-Source Automation) 00:02:23 - Common n8n Use Cases (Email, Social Media) 00:03:36 - Automating Email: AI Tone & Human in the Loop 00:07:02 - Observability, Logging, and Error Handling 00:22:00 - Using Custom Code & JavaScript Nodes 00:29:50 - n8n Cloud vs. Self-Hosting (Features & Security) 00:37:01 - How to Get Started with n8n (Beginner's Roadmap)Subscribe for more insights on AI tools, productivity, and automation.Tool Use is a weekly conversation with the top AI experts.