Tool Use - AI Conversations

Austin Cook, CEO of Alignment Lab AI, and Jordan Parker, marketing expert at the same organization, dive into the world of open source AI. They explore how decentralized models can empower individuals against the monopolies of big tech. Discover the benefits of running AI locally on your hardware, the evolution of resource-efficient models, and the significance of data privacy. They advocate for transparency in AI technologies, highlighting how personalized assistants will become more accessible, fostering a future where everyone can innovate.

Ray Fernando, a former Apple engineer and AI streamer, joins Eric Buess, an AI coding expert and Anthropoc super fan, to demystify Claude Code. They unveil how to maximize Claude's potential, sharing insights on optimal setups and advanced context management. Topics include clever uses of hooks and slash commands, the significance of thinking modes, and strategies to avoid common mistakes like context rot. Get ready to enhance your coding workflows with their expert advice!

Craig McLuckie, co-creator of Kubernetes and CEO of StackLok, dives into the future of AI infrastructure. He emphasizes the critical necessity for secure Model Control Protocol (MCP) servers to prevent data vulnerabilities. The discussion highlights ToolHive, a secure registry enhancing developer efficiency while managing security risks. McLuckie also explores the shift towards solutions engineering amid AI's disruption, promoting adaptability and community-driven innovation as key factors for success in the evolving tech landscape.

Ryan Carson, an expert in AI development, dives deep into the realm of context engineering, emphasizing its importance in optimizing interactions with large language models. He discusses the evolution of AI practices, from prompt engineering to a focus on context to enhance output quality. Ryan shares insights on the necessity of adaptability and curiosity in a rapidly changing tech landscape. He also highlights innovative trends like using WhatsApp for AI product development, along with practical strategies for empowering small businesses through accessible AI education.

Ryan Carson, a seasoned entrepreneur with three successful exits, dives into his journey of building a one-person startup powered by AI. He shares his innovative three-part workflow using tools like Cursor and ChatGPT, drastically enhancing productivity. The conversation covers managing AI developers, tackling challenges like context drift and hallucinations, and unique insights for aspiring founders. Carson emphasizes the vital skills and mindset needed in today's AI landscape, encouraging listeners to embrace these technologies for their entrepreneurial aspirations.

Olga Beregovaya, VP of AI at Smartling and a veteran in language technology, discusses how businesses can leverage AI to cut costs dramatically. She delves into Smartling's internal strategies for implementing AI across various workflows and debates the 'build vs. buy' dilemma for AI tools. Olga emphasizes the need for a 'golden dataset' to benchmark models and shares insights on safely scaling AI without risking quality issues. She highlights the evolution of the workforce, advocating for skills like multilingual prompt engineering as key to thriving in the AI era.

David Cross, a senior content marketer and creative mind behind the Kids Chatterbox podcast, shares his secrets to crafting emotionally resonant AI content. He discusses the importance of incorporating a human element to avoid the uncanny valley and elevate quality. Cross reveals his workflow for generating multilingual narratives, emphasizing emotional engagement. He also debunks myths around AI content creation, advocating for iterative refinement and audience connection to truly resonate with listeners.

Wolfram Ravenwolf, an AI Evangelist at EllaMind with deep expertise in IT and DevOps, dives into the transformative potential of AI for businesses. He tackles common misconceptions, emphasizing the importance of quality tools and employee training. Wolfram shares actionable strategies for deploying local AI models and optimizing performance through proper prompt engineering. He also highlights the significance of fostering an 'AI affinity' culture to boost team productivity and innovation. Join him to explore how to integrate effective AI systems into any organization!

Join Diamond Bishop, the Director of Engineering and AI at Datadog, as he shares his expertise in building self-improving AI agents. He discusses strategies for establishing robust evaluation systems, fostering user trust, and choosing between prompt engineering and fine-tuning. Diamond also explores the balance of AI agents versus traditional scripts, the importance of dataset management, and the exciting future of ambient AI in DevSecOps. This conversation is packed with essential insights for anyone looking to create effective, adaptive AI systems.

Are your AI agents unreliable? In this guide, we reveal a professional system for AI evals to help you build and ship better AI products, faster. Learn how to systematically test LLM performance, evaluate complex tool use, and improve multi-turn conversations. We break down the exact process for building a high-quality eval dataset, using milestones and minefields to track agent behaviour, and how to properly use an LLM as a judge without compromising quality. Stop guessing and start making real, measurable improvements to your AI today.Check out Quotient AIhttps://www.quotientai.co/Sign up for A.I. coaching for professionals at: https://www.anetic.coGet FREE AI tools pip install tool-use-aiConnect with us https://x.com/ToolUseAIhttps://x.com/MikeBirdTechhttps://x.com/freddie_v400:00:00 - intro 00:02:54 - Why You Need AI Evals 00:06:13 - How to Evaluate AI Agent Tool Use 00:29:24 - The Process for Building Your First Eval Dataset 00:42:44 - Using an LLM as a Judge The Right WaySubscribe for more insights on AI tools, productivity, and AI evals.Tool Use is a weekly conversation with AI experts brought to you by Anetic.