Tool Use - AI Conversations

They explain a single script-tag agent that types, clicks, and runs autonomous workflows directly in the browser. They contrast a DOM-only approach with screenshot-based agents, highlighting subsecond actions and performance wins. They describe building semantic DOM trees, handling iframes and canvas limits, and triggering complex workflows via URL queries. They announce the client SDK is open source for developers to try.

Mano Tsiris, serial exited founder and head of growth at Optimal AI, shares practical playbooks for building and marketing AI products. He discusses validating ideas before coding. He explains building in public on LinkedIn, repurposing content with AI tools, crafting viral hooks and A/B testing, and using IRL events and a lean marketing tech stack to find traction.

Nathan Brake, a Mozilla AI engineer and creator of Any-LLM, builds tools for talking to any LLM and hosting models locally. He discusses rapid model switching, running models on local hardware, cost and privacy benefits of small open-source models. He demos Any-LLM tooling, the Platform vault for keys and budgets, and his Porch Songs app that dogfoods model behavior.

Max McRae, founder of Greyhaven and self-hosting advocate, promotes sovereign AI architectures that keep private data under your control. He discusses vendor-agnostic model swapping, personal data indexing for richer context, sandboxed agent workflows, egress control, and practical trade-offs between cloud and local models. Short, practical, and focused on reclaiming control of AI systems.

Arjun Patel, Senior Developer Advocate at Pinecone who builds vector search and RAG systems. He explores what vector stores enable and when they matter. He breaks down chunking strategies, dense vs sparse embeddings, reranking and metadata filtering. He demos Pinecone integrations and a no-code assistant for searching and citing documents.

Greg Schoeninger, CEO of Oxen.ai, explains how to fine-tune image and video AI models for cost, consistency, and scale. He covers when to move beyond prompts, dataset creation and labeling, LoRA versus full fine-tuning, segmentation masks, and real-world wins like a massive product catalog and the Isometric NYC project. Practical tips for training, inference, and tooling round out the conversation.

Justin Borge, a marketer turned growth engineer who built Helios, a personal management system using LLMs. He discusses JSON-based memory for grounded AI, persona prompting and his provocative "bullying" approach to get models to critique code, and a human-in-the-loop workflow for safely editing local files. The conversation covers tooling, debugging without deep coding skills, and practical demos of Helios.

Ryan Carson, founder of Untangle and creator of a divorce AI agent, explains the Ralph Wiggum Loop and agent orchestration. He discusses fresh context windows, deterministic hooks, and agent browser testing. Ryan covers PRD-driven acceptance criteria, scaling with parallel loops, and using cron-like loops to automate marketing and self-healing systems.

Eric Buess, a builder of advanced Claude Code and creator of a hands-free AI system, joins the conversation. He shares fascinating insights on using Claude Code for seamless automation in daily life, from managing emails to monitoring messages. Eric explains the innovative hook system for steering AI behavior and discusses adversarial sub-agents that ensure accuracy. He also highlights the Titus wake word for mobile command, reflecting on how automation can free time for family. Get ready to rethink AI and productivity!

Sukh Saini, an accomplished entrepreneur and creator of Engyne, shares his insights on AI product distribution and personal branding. He discusses the importance of focusing on high-impact projects over multiple low-revenue apps. Sukh's unique method involves validating demand before coding by conducting research and customer interviews. He emphasizes the power of building in public to foster trust and navigate new marketplaces like Stripe and Canva. Listeners gain a tactical framework for ensuring growth and success in the evolving AI landscape.