AI Agents Blog
Deep dives and practical articles about AI agents — agent frameworks, orchestration patterns, MCP integrations, and autonomous workflows. Curated from our main blog: every card links to the full article. 840 articles and growing.
Key AI Breakthroughs from The Batch: Latest in Deep Learning Models, Tools, and Research (Issues Roundup)
Dive into the hottest AI developments from recent Batch issues: from efficient vision models to agentic workflows and beyond. Get the full scoop with links, insights, and actionable takeaways.
Unlocking AI Breakthroughs: Highlights from The Batch Newsletter Page 4
Explore the captivating AI stories, papers, and tools from page 4 of DeepLearning.AI's The Batch newsletter. From model advancements to practical implementations, discover what's shaping the future of AI.
The Batch Letters Archive Page 9: Essential AI Insights from deeplearning.ai Newsletters
Discover the compelling letters featured on page 9 of The Batch's letters tag, offering deep dives into AI advancements, industry trends, and strategic advice from deeplearning.ai experts.
Anthropic's Claude 3.5 Sonnet Revolution: Top-Tier Coding, Interactive Artifacts, and Agentic Dev Tools
Anthropic supercharges Claude 3.5 Sonnet with elite coding skills, live code execution, stunning artifacts, and agentic computer control—perfect for developers building smarter workflows.
Anthropic Unveils Claude 3.5 Sonnet, Claude Agent SDK, and Revamped Claude Code: Empowering Developers with Cutting-Edge AI Tools
Anthropic introduces Claude 3.5 Sonnet, the leading model in coding benchmarks, a powerful new Agent SDK, and major enhancements to Claude Code, transforming developer workflows.
Unlock AI Agents: Dive into DeepLearning.AI's Free Course on Building Powerful Autonomous Systems
Discover how to create intelligent AI agents that handle complex tasks autonomously with this hands-on, free course from DeepLearning.AI. Learn agentic workflows, tools, planning, and more to build your first research agent.
Boost AI Agent Performance Through Evaluations and Error Analysis (Part 1)
Discover how to systematically evaluate and refine AI agents using outcome-based evals and error analysis techniques. This guide provides actionable steps with examples to improve agent reliability in complex tasks.
Exposing Security Gaps in Model Context Protocol: Anthropic Experts Reveal Paths for Data Theft and Code Execution
Anthropic researchers uncover critical flaws in the MCP protocol, enabling attackers to hijack AI agents and steal sensitive data. Explore the attacks, defenses, and actionable steps to fortify your workflows!
GEPA: Advanced Algorithm for Evolving Superior Prompts in Agentic AI Systems
Discover GEPA, a genetic algorithm-inspired method that automatically refines prompts to boost AI agent performance by up to 50% on key benchmarks. Learn how it works and apply it to your agentic workflows.
Enhance AI Agent Performance: Deep Dive into Evals and Error Analysis (Part 2)
Discover practical strategies to debug and optimize agentic AI systems through systematic error analysis. This part 2 explores a real-world code agent case study, revealing common pitfalls and fixes to boost reliability.
Atlas: Pioneering OpenAI's Open-Source Browser Agent for Seamless Web Automation
Discover Atlas, the groundbreaking open-source agent from ServerlessDB that harnesses OpenAI's o1 model to automate complex browser tasks like booking flights or online shopping effortlessly.
Discover DeepLearning.AI Pro: Unlimited Access to Cutting-Edge AI Courses and Certificates
Elevate your AI skills with DeepLearning.AI Pro – get unlimited access to all short courses, endless retries, certificates, and priority support for just $15/month.
Cursor Unveils Cursor-Small: A Specialized 14B Model Engineered for Advanced Coding Agents
Cursor has launched cursor-small, a 14B parameter model trained on 600B tokens specifically for coding agents. It tops benchmarks like SWE-bench and is now open-weights on Hugging Face.
OpenAI's Autonomous Security Agent: Hunting and Fixing AI Vulnerabilities in Real Time
OpenAI deployed an AI agent powered by reinforcement learning to autonomously detect and patch security flaws in ChatGPT plugins, o1 models, and voice systems—uncovering issues humans missed.
Unlocking LLM Math Superpowers with Grokking: Highlights from The Batch Issue #326
Dive into groundbreaking techniques like Grokking for math mastery in LLMs, Meta's V-JEPA 2 for video AI, and more from deeplearning.ai's latest Batch. Boost your AI knowledge with actionable insights!
Key Insights from AI Dev X NYC 2025: Essential Takeaways for AI Builders and Innovators
Discover the top lessons from AI Dev X NYC 2025, where experts shared breakthroughs in AI agents, open models, coding assistants, fine-tuning, drug discovery, and production AI systems.
Kimi K2 Beats GPT-4o and Claude 3.5 Sonnet in Agentic Tool Use: Breakdown of Moonshot AI's Breakthrough Techniques
Moonshot AI's open-source Kimi K2 model surpasses top proprietary LLMs on agent benchmarks using reflection, multi-step planning, and long context handling. Discover how these innovations enable superior tool-using agents.
Coding Agents Under Fire: Can AI Developers Automate Real-World Cyberattacks?
Security researchers demonstrate how AI coding agents like Devin and SWE-agent can autonomously exploit software vulnerabilities, raising alarms about automated supply chain attacks.
Nova-2 Family Delivers Superior Cost-Performance with Advanced Agentic Capabilities
Nova Labs unveils the Nova-2 series: Micro 2, Lite 2, and Pro 2 models that outperform predecessors at lower costs while introducing powerful agentic tools for real-world applications.
Create an Autonomous AI Agent with This Straightforward Framework
Discover a simple, proven recipe for building powerful autonomous agents using large language models (LLMs). Combine tools, reasoning loops, and frameworks like LangGraph to automate complex tasks effortlessly.
Gemini Deep Research API: Supercharge Your Apps with AI-Powered Web Research in Public Beta!
Google DeepMind just dropped Deep Research into the Gemini API—turn complex queries into cited reports with web-browsing AI agents. Perfect for developers building next-gen research tools!
DeepLearning.AI Past Events Archive Page 4: Essential Sessions on Generative AI, LLMs, and ML Engineering
Discover page 4 of DeepLearning.AI's events archive, featuring expert-led sessions on LLM fine-tuning, agentic workflows, and production-ready AI systems. Gain insights from industry leaders with practical resources and code examples.
Explosive AI Discoveries on deeplearning.ai Blog Page 4: Busting Myths and Igniting Innovation
Charge into the future of AI with page 4 of deeplearning.ai's blog! Uncover myth-shattering insights, cutting-edge techniques, and practical tools that transform how you build and deploy intelligent systems.
DeepLearning.AI Blog Highlights: Hands-On Courses on Multi-Agent AI, LLM Bootcamps, Generative AI, and Advanced RAG Techniques
Explore page 2 of DeepLearning.AI's blog for actionable resources on building multi-agent systems with CrewAI, mastering LLMs via bootcamps, free generative AI courses, and cutting-edge topics like Agentic RAG—all with GitHub notebooks for immediate practice.