episode-header-image

Feb 22

37m 40s

MLA 028 AI Agents

About this episode

Up next

MLA 029 OpenClaw

OpenClaw is a self-hosted AI agent daemon that executes autonomous tasks through messaging apps like WhatsApp and Telegram using persistent memory. It integrates with Claude Code to enable software development and administrative automation directly from mobile devices. Links Note ... Show More

MLA 030 AI Job Displacement & ML Careers

ML engineering demand remains high with a 3.2 to 1 job-to-candidate ratio, but entry-level hiring is collapsing as AI automates routine programming and data tasks. Career longevity requires shifting from model training to production operations, deep domain expertise, and masterin ... Show More

Recommended Episodes

High Performance And Low Overhead Graphs With KuzuDB

SummaryIn this episode of the Data Engineering Podcast Prashanth Rao, an AI engineer at KuzuDB, talks about their embeddable graph database. Prashanth explains how KuzuDB addresses performance shortcomings in existing solutions through columnar storage and novel join algorithms. ... Show More

Soumith Chintala: PyTorch

The Rise of Generative AI Video Tools

Episode 13: What impact will AI-generated content have on the entertainment industry? Matt Wolfe (https://x.com/mreflow) and Nathan Lands (https://x.com/NathanLands) dive into this topic, envisioning a future where AI generates interactive movies and complex gaming worlds with in ... Show More

From RAG to Relational: How Agentic Patterns Are Reshaping Data Architecture

SummaryIn this episode of the AI Engineering Podcast Mark Brooker, VP and Distinguished Engineer at AWS, talks about how agentic workflows are transforming database usage and infrastructure design. He discusses the evolving role of data in AI systems, from traditional models to m ... Show More

Code Generation & Synthetic Data With Loubna Ben Allal #51

Our guest today is Loubna Ben Allal, Machine Learning Engineer at Hugging Face 🤗 . In our conversation, Loubna first explains how she built two impressive code generation models: StarCoder and StarCoder2. We dig into the importance of data when training large models and what can ... Show More

Canva Create 2025 - What's New for Educators? - HoET261

In this exciting crossover episode, Chris Nesi teams up with Leena Marie Saleh (The EdTech Guru) for a detailed look into Canva's latest educational innovations unveiled during Canva Create 2025. Whether you're a teacher, instructional coach, or tech integrator, this episode is p ... Show More

806 : Topical English Vocabulary Lesson With Teacher Tiffani about Digital Art

<p>In today’s episode, you will learn a series of vocabulary words that are connected to a specific topic. This lesson will help you improve your ability to speak English fluently about a specific topic. It will also help you feel more confident in your English abilities.</p><h1> ... Show More

Rendering Revolutions: Chaos founder Vlado Koylazov's Journey from V-Ray to Virtual Production

This podcast episode features Vlado Koylazov, co-founder of Chaos and inventor of the widely-used V-Ray rendering software. Koylazov shares his journey in computer graphics, from his early fascination with the field to the development of V-Ray and the latest innovations at Chaos. ... Show More

Pausing to think about scikit-learn & OpenAI o1

Recently the company stewarding the open source library scikit-learn announced their seed funding. Also, OpenAI released “o1” with new behavior in which it pauses to “think” about complex tasks. Chris and Daniel take some time to do their own thinking about o1 and the contrast to ... Show More

Deepdub’s Ofir Krakowski on Redefining Dubbing from Hollywood to Bollywood - Ep. 202

In the global entertainment landscape, TV show and film production stretches far beyond Hollywood or Bollywood — it's a worldwide phenomenon. However, while streaming platforms have broadened the reach of content, dubbing and translation technology still has plenty of room for gr ... Show More

AI agents differ from chatbots by pursuing autonomous goals through the ReACT loop rather than responding to turn-based prompts. While coding agents are currently the most reliable due to verifiable feedback loops, the market is expanding into desktop and browser automation via tools like Claude co-work and open claw.

Links

Notes and resources at ocdevel.com/mlg/mla-28
Try a walking desk - stay healthy & sharp while you learn & code
Generate a podcast - use my voice to listen to any AI generated content you want

Fundamental Definitions

Agent vs. Chatbot: Chatbots are turn-based and human-driven. Agents receive objectives and dynamically direct their own processes.
The ReACT Loop: Every modern agent uses the cycle: Thought -> Action -> Observation. This interleaved reasoning and tool usage allows agents to update plans and handle exceptions.
Performance: Models using agentic loops with self-correction outperform stronger zero-shot models. GPT-3.5 with an agent loop scored 95.1% on HumanEval, while zero-shot GPT-4 scored 67.0%.

The Agentic Spectrum

Chat: No tools or autonomy.
Chat + Tools: Human-driven web search or code execution.
Workflows: LLMs used in predefined code paths. The human designs the flow, the AI adds intelligence at specific nodes.
Agents: LLMs dynamically choose their own path and tools based on observations.

Tool Categories and Market Players

Developer Frameworks: Use LangGraph for complex, stateful graphs or CrewAI for role-based multi-agent delegation. OpenAI Agents SDK provides minimalist primitives (Handoffs, Sessions), while the Claude Agent SDK focuses on local computer interaction.
Workflow Automation: n8n and Zapier provide low-code interfaces. These are stable for repeatable business tasks but limited by fixed paths and a lack of persistent memory between runs.
Coding Agents: Claude Code, Cursor, and GitHub Copilot are the most advanced agents. They succeed because code provides an unambiguous feedback loop (pass/fail) for the ReACT cycle.
Desktop and Browser Agents: Claude Cowork( (released Jan 2026) operates in isolated VMs to produce documents. ChatGPT Atlas is a Chromium-based browser with integrated agent capabilities for web tasks.
Autonomous Agents: open claw is an open-source, local system with broad permissions across messaging, file systems, and hardware. While powerful, it carries high security risks, including 512 identified vulnerabilities and potential data exfiltration.

Infrastructure and Standards

MCP (Model Context Protocol): A universal standard for connecting agents to tools. It has 10,000+ servers and is used by Anthropic, OpenAI, and Google.
Future Outlook: By 2028, multi-agent coordination will be the default architecture. Gartner predicts 38% of organizations will utilize AI agents as formal team members, and the developer role will transition primarily to objective specification and output evaluation.