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. 884 articles and growing.
Constructing an AI-Driven Society: Andrew Ng in Conversation with Greylock's Sarah Guo
Andrew Ng and Sarah Guo explore how AI agents will transform industries, boost productivity, and reshape society, drawing on real-world examples from innovative startups.
Deep Learner Spotlight: Chris Morrow's Path from Mechanical Engineering to Pioneering AI Agents at Anthropic
Discover how Chris Morrow transitioned from mechanical engineering to software engineering at Anthropic, leveraging deeplearning.ai courses to build cutting-edge AI agents like Claude's computer use capabilities.
Top VC Insights from the AI Frontier Conference: Shaping the Future of AI Investments
Discover game-changing perspectives from leading VCs like Vinod Khosla and Keith Rabois on AI trends, from foundation models to agentic systems, shared at the AI Frontier Conference VC Forum.
Boosting Productivity in AI-Driven Development: Salesforce MLE Dillon Laird's Workflow with Claude
Salesforce Machine Learning Engineer Dillon Laird reveals how he integrates Claude AI into daily tasks like code reviews, debugging, data analysis, and agent development for massive efficiency gains.
Boost Your Office Productivity with AI: Lessons from AWS Applied Scientist Matineh Shaker
Discover practical strategies for integrating AI into daily office tasks from AWS expert Matineh Shaker. Her free short course on deeplearning.ai covers prompting, automation, evaluation, and AI agents to supercharge your workflow.
Event Ambassador Spotlight: Ayyuce Kizrak, Machine Learning Engineer Driving AI Innovation at IBM
Discover Ayyuce Kizrak, DeepLearning.AI Event Ambassador and IBM ML engineer, whose open-source projects in healthcare and HR showcase practical LLM applications. Learn her journey from academia to industry leadership.
Collaborating Effectively with AI: Key Insights from Jared Webb on Using Claude for Coding and Development
Jared Webb, founder of Magic.dev, shares his proven methods for treating AI like Claude as a powerful pair programmer. Learn step-by-step workflows, advanced prompting techniques, and strategies for building AI agents that boost productivity.
From Mobile App Developer to AI Engineer: Chiao-Lin Lin's Complete Roadmap and Lessons Learned
Discover how Chiao-Lin Lin transformed from a mobile app developer into an AI engineer through targeted courses, hands-on projects, and strategic job hunting. Follow her exact path for your own career pivot.
Brennan Pursell: 2023 PIE AI Ambassador Spotlight – Innovating with LLM SRE and AI Agents
Meet Brennan Pursell, a Microsoft software engineer turned PIE AI Ambassador, who's pioneering LLM SRE practices and building agent arenas to push AI boundaries. Discover his journey, projects, and tips for aspiring AI enthusiasts.
Unlock DeepLearning.AI Pro: Exclusive Access to Cutting-Edge AI Courses, Live Expert Sessions, and Vibrant Community
Struggling to keep up with rapid AI advancements? DeepLearning.AI Pro offers early access to premium courses, live Q&A with experts, and a dedicated Discord community for just $49/month.
AI Dev Meetup #25 NYC Recap: Mastering Swarm Agents, Unsloth Fine-Tuning, and LlamaIndex RAG Systems
Dive into the key takeaways from AI Dev Meetup #25 in NYC, featuring OpenAI's Swarm for multi-agent systems, Unsloth's 2x faster LLM fine-tuning, and LlamaIndex's advanced RAG pipelines for real-world AI apps.
Scaling Multi-Agent LLM Systems: From Quick Prototypes to Reliable Production Deployments
Discover a practical roadmap for transforming experimental multi-agent LLM prototypes into robust production systems, using a real-world customer support case study with LlamaIndex.
Key Insights from Working with AI: Page 2 of DeepLearning.AI Blog Highlights
Discover essential articles on agentic AI, advanced prompting techniques, and practical AI workflows from the second page of DeepLearning.AI's Working with AI category, packed with actionable strategies for developers and practitioners.
Mastering Working with AI: Essential Strategies, Patterns, and Pitfalls from DeepLearning.AI Experts
Unlock practical frameworks for integrating AI into workflows, from agentic design patterns and scalable pipelines to RAG best practices and multi-agent coordination. Explore GitHub resources and real-world lessons to build robust LLM applications.
Upcoming DeepLearning.AI Courses: Master AI Skills with Expert-Led Programs
Discover the latest upcoming short courses and professional programs from deeplearning.ai. Unlock cutting-edge AI knowledge through hands-on learning with industry leaders like Andrew Ng.
Working with AI: Essential Techniques from Prompt Engineering to AI Agents
Unlock practical skills to harness AI effectively through prompt engineering, RAG, fine-tuning, tool integration, and agent development. Hands-on notebooks guide your journey.
DeepLearning.AI's Latest Press and News: Major Partnerships, Course Launches, and AI Advancements
Discover DeepLearning.AI's exciting updates, from collaborations with NVIDIA and World Labs to new agentic AI courses and educator programs—shaping accessible AI education worldwide.
How AI Agents Are Attacking Robot Dogs: Uncovering Hidden Vulnerabilities in Physical Robotics
Researchers trained AI to exploit weaknesses in robot dogs, causing them to topple and malfunction in real-world tests. This breakthrough highlights urgent needs for robust AI in robotics.
OpenAI's Dota 2 Overlords: Superhuman AI Masters Complex Multiplayer Gaming
OpenAI's latest AI agents dominate Dota 2 at professional levels, showcasing breakthroughs in reinforcement learning. Trained on massive compute, these 'Overlords' highlight scalable RL for real-world challenges.
Key AI Breakthroughs: Gemini 1.5 Pro's 1M Token Context, Grokking Phenomena, and Latest Research Insights
Explore the latest in AI with Gemini 1.5 Pro's unprecedented 1 million token context window, new findings on grokking in mathematical reasoning, and other cutting-edge developments shaping the field.
Rebuilding AI Agents from Failure: Pieces' Epic Journey to Robust Customer Support
Discover how Pieces turned a catastrophic AI agent flop into a success story by tackling hallucination, loops, and planning pitfalls head-on with smart fixes like fallbacks and monitoring.
Unlocking Emotional Intelligence in AI Agents: EmoBench Benchmark and Key Developments
Discover how researchers are equipping AI agents with emotional intelligence through the new EmoBench benchmark, alongside updates on Grok's voice capabilities and Llama 3.2 vision models.
Andrew Ng Tours Taiwan's Top AI Labs: Deep Insights from MediaTek, TAIL, Appier, and Foxconn
Andrew Ng recently visited four leading AI labs in Taiwan, uncovering breakthroughs in edge AI, open-source models, agentic systems, and manufacturing intelligence. Discover practical advancements driving on-device inference and industrial applications.
Enabling Chatbot-to-Chatbot Calls: Practical Guide to Agent-to-Agent Interactions with Anthropic's Computer Use
Discover how AI agents can directly interact by one controlling another's tools, using Anthropic's computer use beta. Build reliable agent systems for real-world tasks like browsing and automation.