Join the Tool Use Discord: https://discord.gg/PnEGyXpjaX

Discover 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 us

https://x.com/ToolUsePodcast

https://x.com/MikeBirdTech

https://x.com/jasonkneen

00:00:00 - Intro

00:07:54 - Building Voice Control for AI Agents

00:15:20 - Leveraging MCP for Better Tooling

00:19:42 - Fast Orchestration & Model Routing

00:25:06 - Multi-Model Agent Architecture

00:31:13 - Cluso Demo & Workflow

Subscribe for more insights on AI tools, productivity, and modern software development.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaX

Discover 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/MikeLeslieML

00:00:00 - 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 Tale

Subscribe for more insights on AI tools, productivity, and AI engineering.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaX

Building 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/book

Connect with us

https://x.com/ToolUsePodcast

https://x.com/MikeBirdTech

https://x.com/calcsam

00:00:00 - 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 Risks

Subscribe 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/PnEGyXpjaX

Turn 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/ToolUsePodcast

https://x.com/MikeBirdTech

https://x.com/ArtemXTech

00:00:00 - 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 Workflows

Subscribe 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/PnEGyXpjaX

AI 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/swyx

00:00:00 - 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 Codebase

Subscribe 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/PnEGyXpjaX

Explore 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/MikeBirdTech

00:00:00 - Intro

00:00:49 - The New Plane of AI Risk & Prompt Injection

00:10:30 - How Businesses Can Implement AI Safely

00:13:21 - Human in the Loop & Claude Code

00:17:18 - Using Subagents as a Mitigation

00:31:03 - The Build vs. Buy Debate for AI Models

00:36:06 - 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/PnEGyXpjaX

Master 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.com

https://www.nshipyard.com

Connect with us

https://x.com/ToolUsePodcast

https://x.com/MikeBirdTech

https://x.com/RichardsonDx

00:00:00 - 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.

Join the Tool Use Discord: https://discord.gg/PnEGyXpjaX

Is your RAG (Retrieval-Augmented Generation) pipeline optimized, or is it even necessary? We all know context is king for LLMs, but large context windows might not be the answer. On Episode 63 of Tool Use, we deep dive into RAG with Apurva Misra, founder of Sentick. We explore the entire RAG workflow, from creating and optimizing embeddings to choosing the right vector DB (like Postgres with PG Vector). Apurva explains the critical role of re-rankers , the power of hybrid search (combining semantic and keyword search) , and when to consider agentic RAG. We also cover the essential steps for taking your RAG system to production, including data quality, feedback loops , and safety guardrails.

Connect with Apurva Misra:

LinkedIn: https://www.linkedin.com/in/misraapurva/

Consulting: https://www.sentick.com/

Website: https://apurvamisra.com/

Connect with us

https://x.com/ToolUsePodcast

https://x.com/MikeBirdTech

00:00:00 - Intro

00:01:18 - What is RAG (Retrieval-Augmented Generation)?

00:03:41 - Is RAG Dead? Large Context Windows vs. RAG

00:06:40 - The RAG Workflow: Embeddings, Chunking & Vector DBs

00:28:00 - Do You Need a Re-Ranker?

00:41:24 - Production RAG: Safety, Guardrails & Efficiency

Subscribe for more insights on AI tools, productivity, and RAG.

Tool Use is a weekly conversation with the top AI experts, brought to you by ToolHive.