Tool Use - AI Conversations

Check out www.ToolUsePodcast.comHermes Agent has emerged as the open source AI agent that people are choosing. In this episode, we go beyond the hype to understand why. Through conversations with a co-founder of Nous Research, AI engineering veterans, and non-technical builders, we explore what Hermes can actually do today, where it falls short, and why the choice of which agent you use matters more than you think. From self-improving skills and three-layer memory to video dubbing workflows and CAD hardware sourcing. These are real people getting real value from an agent they own. But the deeper story is about what happens when your AI infrastructure is closed vs open. The decisions you make today about which tools you use are shaping the future of AI for everyone. Open source must win, and this episode explains why.Follow the amazing guestsKaran - Co-founder & Head of Behavior, Nous Research: https://x.com/karan4dWolfram Ravenwolf - AI Evangelist and Creator Wolfbench: https://x.com/WolframRvnwlfRobert Desmond — Founder & CEO, Farm Friend: https://x.com/twodogseedsEvan Roach — Product Developer: https://x.com/evvaaannnnKat Winter - https://x.com/katspigeonConnect with ushttps://x.com/ToolUsePodcasthttps://x.com/MikeBirdTech00:00:00 - Intro 00:01:52 - Ambient Agents00:05:12 - Why everyone is switching to Hermes Agent 00:17:53 - Real-World AI Agent Use Cases & Automations 00:29:59 - Why Open Source Must WinSubscribe for more insights on AI tools, productivity, and the open source AI movement.Join the Tool Use Discord: https://discord.gg/PnEGyXpjaXTool Use is a weekly conversation with the top AI experts.

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 This innovative method completely bypasses slow screenshot-based models and outdated playwright or puppeteer scripts.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.