Tool Use - AI Conversations

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.