Tool Use - AI Conversations

This week, we explore why keeping humans in the loop is crucial for AI agent success. Discover how "outer loop agents" can transform unreliable 80% accuracy into enterprise-grade solutions through strategic human checkpoints.

Our guest, Dexter Horthy explains how human-in-the-loop systems enable AI to handle high-stakes tasks like infrastructure management, supply chain operations, and critical business decisions that would otherwise be too risky. Learn about the practical frameworks for implementing human oversight that major companies are already using to deploy AI safely and effectively.

If you're building AI agents or automations and struggling with reliability issues, this episode reveals the missing piece in your system design. Find out why the future of AI isn't about complete autonomy, but intelligent collaboration between humans and machines.

Check out HumanLayer:

https://www.humanlayer.dev/

12 Factor Agents:

https://github.com/humanlayer/12-factor-agents

Get your daily curated AI news from Anetic Daily Intelligence

Sign up at: https://www.anetic.co

Get FREE AI tools

pip install tool-use-ai

Connect with us

https://x.com/ToolUseAI

https://x.com/MikeBirdTech

https://x.com/FieroTy

https://x.com/dexhorthy

00:00 - Intro

00:53 - How Dexter Horthy Started Building AI Agents

07:02 - Why Human-in-the-Loop is Essential for AI Reliability

17:13 - Best Frameworks and Practices for Building AI Agents

22:22 - Model Context Protocol (MCP): Hype or Essential?

26:45 - Common Mistakes When Building AI Agents

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

Tool Use is a weekly conversation with AI experts brought to you by Anetic.

Want to build powerful A.I. apps faster than ever before?

In this episode of Tool Use, discover Mozilla.AI Blueprints—the new workflow designed to help you turn your AI concepts into fully functional apps in minutes, not weeks. Whether you're creating chatbots, productivity tools, or custom AI solutions, Mozilla.AI Blueprints simplifies the development process, enabling rapid prototyping.Learn step-by-step how Mozilla.AI Blueprints can accelerate your next AI project, reduce complexity, and help you deliver real-world applications quickly. Perfect for developers, entrepreneurs, and tech enthusiasts seeking the fastest path to practical, working AI apps.

Learn more about Blueprints:

https://blueprints.mozilla.ai/

LLM Commit Generator:

https://github.com/ToolUse/llmcommit

Get your daily curated AI news from Anetic Daily Intelligence

Sign up at: https://www.anetic.co

Get FREE AI tools

pip install tool-use-ai

Connect with us https://x.com/ToolUseAI

https://x.com/MikeBirdTech

https://x.com/FieroTy

00:00:00 - Introduction to Tool Use episode 33

00:02:15 - Alex Meckes' journey into AI

00:04:48 - Introduction to Mozilla AI Blueprints

00:08:00 - Getting started with Blueprints

00:11:30 - Community contributions and future blueprints

00:17:25 - Vibe coding tips and best practices

00:24:30 - Open source AI ecosystem needs

00:29:30 - Alex's favorite AI tools and blueprints

(generated by https://www.vibestamps.com/)

Subscribe for more insights on AI tools, productivity, and open source AI.

Tool Use is a weekly conversation with AI experts brought to you by Anetic.

Discover how AI is transforming the way we interact with computers, eliminating the need for traditional keyboards and enabling hands-free computing. In this episode, we explore how voice control, innovative AI tools, and even foot pedals are redefining our digital experiences. Learn about practical AI solutions for accessibility, productivity, and more, and get insights from our guest, an independent developer actively pioneering these advancements.

Get your daily curated AI news from Anetic Daily Intelligence

Sign up at: https://www.anetic.co

Get FREE AI tools

pip install tool-use-ai

Connect with us

https://x.com/ToolUseAI

https://x.com/MikeBirdTech

https://x.com/FieroTy

https://x.com/cj_pais

01:59 - How AI Enables Hands-Free Computing

07:34 - Using a Foot Pedal to Control Your Computer

10:20 - The Future of Voice and AR in Computing

15:29 - How AI Could Revolutionize Community and Social Interaction

31:48 - Improving Productivity and Intentionality with AI

Subscribe for more insights on AI tools, productivity, and the future of accessibility

Tool Use is a weekly conversation with AI experts brought to you by Anetic.

This week, Mike and Ty explore the rapidly evolving AI landscape of 2025. They cover Google's impressive new image capabilities, OpenAI's computer vision API, and the rise of general agents like Manus. Join the conversation as they discuss agent-to-agent communication, the emotional connections possible with Sesame's voice AI, and how Deep Research is changing information access. Whether you're a developer, tech enthusiast, or just curious about where AI is headed, this episode gives you the insights you need to stay ahead of the curve. Discover which AI tools are making real impact and how they could transform your workflow and digital experience.Google - https://developers.googleblog.com/en/experiment-with-gemini-20-flash-native-image-generation/OpenAI - https://openai.com/index/new-tools-for-building-agents/Claude code - https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overviewManus - https://manus.im/Sesami - https://www.sesame.com/research/crossing_the_uncanny_valley_of_voiceFrancisco - https://x.com/fpinghamGet your daily curated AI news from Anetic Daily Intelligence Sign up at: https://www.anetic.coGet FREE AI tools pip install tool-use-ai Connect with us https://x.com/ToolUseAI https://x.com/MikeBirdTech https://x.com/FieroTy00:40 - Google's Native Image Input/Output Capabilities 06:41 - OpenAI Response API and Computer Control Features 12:26 - Manus: The First General AI Agent from China 24:06 - Claude 3.7 Sonnet and Claude Code Updates 28:58 - Sesame Voice AI: Crossing the Uncanny Valley 37:14 - Deep Research Tool Transforming AI ResearchSubscribe for more insights on AI tools, productivity, and the AI ecosystem.Tool Use is a weekly conversation with AI experts brought to you by Anetic.

Get your daily curated AI news from Anetic Daily Intelligence

Sign up at: www.anetic.co

Struggling with inconsistent results from your AI apps? In this episode, learn how to build AI applications that deliver reliable, predictable, and trustworthy outputs every single time. We're joined by Viabhav Gupta, co-creator of BAML.

We dive deep into powerful techniques like structured outputs and effective prompt engineering—key practices used by top developers and industry experts. Gain insights into practical strategies and proven frameworks that will ensure your AI apps are consistent, efficient, and user-friendly.

Whether you're an experienced developer, entrepreneur, or just getting started with AI, this video will equip you with essential tips and best practices to elevate your AI projects to the next level.

Topics covered:

- Ensuring consistent AI results

- Mastering structured outputs

- Advanced prompt engineering techniques

- Practical methods to boost AI reliability

Learn more about BAML

https://www.boundaryml.com/

Get FREE AI tools

pip install tool-use-ai

Connect with us

https://x.com/ToolUseAI

https://x.com/MikeBirdTech

https://x.com/FieroTy

https://x.com/hellovai

2:27 - What is BAML?

16:17 - Implementing BAML in existing projects

28:42 - Prompt Engineering Tips

Subscribe for more insights on AI tools, productivity, and best practices around AI.

Tool Use is a weekly conversation with AI experts brought to you by Anetic.

Tool Use delivers weekly expert conversations, practical demos, and AI tools. We highlight tools you'll actually use, keeping you ahead of the curve. Follow now for fresh AI insights

Ever wonder why the most successful AI builders launch their projects before they're perfect? In this episode of Tool Use, we're joined by Adam Cohen Hillel—AI builder, hardware hacker, and community-driven creator—to explore the real reasons top creators ship early, the hidden pitfalls of hardware projects, and the incredible value of building openly. Discover practical insights on overcoming perfectionism, accelerating your learning through public feedback, and actually finishing the AI projects you've always dreamed of.

Get your daily curated AI news from Anetic Daily Intelligence

Sign up at: www.anetic.co

Get FREE AI tools

pip install tool-use-ai

Connect with us

https://x.com/ToolUseAI

https://x.com/MikeBirdTech

https://x.com/FieroTy

https://x.com/adamcohenhillel

00:40 - Adam's journey into AI

06:03 - What drives people's curiosity to build

15:37 - Adam's workflow and tools

32:53 - Security tips for developers

Subscribe for more insights on AI tools, productivity, and how to actually ship your next project!

Tool Use is a weekly conversation with AI experts brought to you by Anetic.

Sign up for Anetic Daily Intelligence to get the most important AI news, curated just for you. All signal, no noise.

https://anetic.co

Tired of wasting hours managing your inbox? In this episode of Tool Use, we explore how AI is revolutionizing email management with Sarah Allali, founder of Lobby AI. Discover how intelligent email agents can automatically process your messages, prepare meeting invitations, draft responses, and prioritize your communications without you ever opening your inbox. Learn the future of work orchestration as Sarah explains how AI assistants analyze your habits, understand your priorities, and handle the busy work of email management so you can focus on what truly matters.

Check out Lobby AI:

https://thelobby.ai

Get FREE AI tools

pip install tool-use-ai

Connect with us

https://x.com/ToolUseAI

https://x.com/MikeBirdTech

https://x.com/FieroTy

https://x.com/SarahAllali7

03:59 - What makes AI email processing truly valuable

07:44 - How the system prioritizes important emails

12:17 - Knowledge work that can be delegated to AI

14:55 - Creating premium AI experiences

22:10 - Lobby AI demo

Tool Use is a weekly conversation about helpful AI tools you can use today, brought to you by Anetic.

This week we're joined by Nathaniel Whittlemore (NLW), founder and CEO of Superintelligent and host of the AI Daily Brief podcast, for an in-depth discussion on the current state of AI agents. We explore the evolving definition of AI agents, why getting caught up in technical definitions may be missing the point, and examine real-world use cases and limitations of AI agents in business today. NLW shares insights on why most companies are still best suited for single-purpose, specific agents rather than complex multi-agent systems, and discusses the challenges of AI adoption, from data readiness to employee resistance.

The conversation explores how companies are shifting from buying to building their own AI solutions, the cultural and leadership challenges of implementing AI agents, and predictions for AI agent development in 2025 and beyond. NLW also provides practical advice for staying up-to-date in the rapidly evolving AI landscape.

Check out Superintelligent

https://besuper.ai/

Get FREE AI tools

pip install tool-use-ai

Connect with us

https://x.com/ToolUseAI

https://x.com/MikeBirdTech

https://x.com/FieroTy

https://x.com/nlw

00:49 - Definition of AI agents and their practical use cases

13:50 - Hallucinations in AI and impact on business adoption

18:19 - Common mistakes businesses make when implementing AI

25:01 - Cultural readiness for AI adoption

35:59 - Future of work: Everyone becoming managers of AI agents

Tool Use is a weekly conversation about helpful AI tools you can use today, brought to you by Anetic.

In this episode, we dive deep into the world of open source AI with Victor Miller from LLM360. Learn why open source data is crucial for training better AI models (and how it's shaping the future of robotics). Victor shares insights on TXT360 (a 15 trillion token dataset) and explains why data quality matters more than ever in AI development.Key topics covered:- Why open source matters in AI development- The relationship between data quality and model performance- The future of robotics as an AI application layer- How to get started building with open source AI- Practical advice for newcomers to AI developmentVictor also discusses recent developments in open source models, including DeepSeek, Sky T1, and S1, and shares his perspective on the future of AI applications in robotics and beyond.Get FREE AI tools pip install tool-use-ai Connect with us https://x.com/ToolUseAI https://x.com/MikeBirdTech https://x.com/FieroTy02:22 - What makes a good LLM training dataset 06:00 - The importance of open source in AI development 14:12 - MetaGene model for virus detection and public health 24:24 - Challenges and future of home roboticsTool Use is a weekly conversation about helpful AI tools you can use today, brought to you by Anetic.