DeepLearning.AI

Adding voice to an existing AI agent used to mean rewriting a lot of code. In our new short course, Voice for AI Agents and Applications, built in partnership with @VocalBridge and taught by CEO @_ashwyn, you'll learn to layer voice onto an existing agent using minimal code without touching your prompts, RAG pipeline, or tools. You'll implement three integration patterns: voice embedded in an app, voice layered onto an existing agent, and voice as a callable tool your agent uses to place outbound phone calls. Enroll for free: bit.ly/4eybXIK

🚀 The 7-Day Voice AI Builder Challenge is Officially LIVE! Stop babysitting your terminal.  🗣️ The Challenge: Teach your AI coding agent to call you for backup—but only when human intervention is actually required. Real-time feedback? Yes. Live leaderboard? Absolutely. Epic prizes for the winners? You bet. The clock is officially ticking. Competitors are already shipping.  Are you in? 👉 hubs.la/Q04mkw820

Stop watching the terminal. Teach your agent to call you when it matters. We are excited to host this 7-day Voice AI Builder Challenge in collaboration with @VocalBridge! 🚀 Join the waitlist here to secure your spot: deeplearning.ai/courses/voice-… 🎓 Want a head start? Check out the prerequisite course on Voice AI to get your skills ready before kickoff: deeplearning.ai/courses/voice-…

@VocalBridge @_ashwyn Ready to build with Voice AI? Join the waitlist for the 7-Day Voice AI Builder Challenge: deeplearning.ai/courses/voice-… Your mission: build a voice escalation skill that teaches your coding assistant to call you the moment it needs human intervention.

Adding voice to an existing AI agent used to mean rewriting a lot of code. In our new short course, Voice for AI Agents and Applications, built in partnership with @VocalBridge and taught by CEO @_ashwyn, you'll learn to layer voice onto an existing agent using minimal code without touching your prompts, RAG pipeline, or tools. You'll implement three integration patterns: voice embedded in an app, voice layered onto an existing agent, and voice as a callable tool your agent uses to place outbound phone calls. Enroll for free: bit.ly/4eybXIK

🚀 We just launched our new public DeepLearning.AI GitHub repo! Find: 📚 Course artifacts 🛠️ Developer tools 🔗 A master course catalog ✨ More resources coming soon Follow the repo, and give it a ⭐to stay up to date with new additions. 🔗 github.com/https-deeplear…

New short course: Fast & Efficient LLM Inference with vLLM, built in partnership with @RedHat and taught by @cedricclyburn. Learn to quantize an open-source LLM, serve it with vLLM, and benchmark your deployment across speed, cost, and accuracy. Free to enroll: hubs.la/Q04jXfpR0

A vague prompt gives vague advice. Context changes the quality of the answer. The more clearly you explain your situation, constraints, priorities, and goals, the more useful AI becomes for complex decisions. Learn practical prompting techniques in AI Prompting for Everyone with Andrew Ng: hubs.la/Q04jdlqq0

AI agents seem to be increasingly capable of performing economically valuable tasks, but current benchmarks measure this capability only narrowly. Zora Z. Wang and colleagues at Carnegie Mellon University and Stanford University mapped examples drawn from agent benchmarks to statistics that represent U.S. labor. The mapping revealed a mismatch between the tests, which generally emphasize software development, and the more varied work most people do. Read the full article in The Batch: hubs.la/Q04hYVxR0

China halted Meta’s planned acquisition of Manus, asserting tighter government control over strategically important AI technology. The decision disrupts a popular strategy among Chinese AI startups: relocating abroad to attract Western investment and partnerships. Learn more in The Batch: hubs.la/Q04hJmwT0

“Budget” and “financials” are different words, but embeddings understand they’re related. That’s the foundation behind semantic search and one of the core building blocks of modern multimodal systems. Learn how embeddings power retrieval across text, audio, images, and video in Building Multimodal Data Pipelines: hubs.la/Q04hJ2PZ0

Studies found that Google’s AI system for detecting breast cancer in mammograms identified slightly more cancers than human radiologists. The system caught some cases doctors initially missed. Trials also showed the system could reduce radiologists’ workload. But researchers noted that trust remains a major barrier to clinical adoption. Read our summary of the paper in The Batch hubs.la/Q04hzZ_R0

Your AI image generator needs a critic. In our new short course built in collaboration with @GoogleCloudTech, you’ll build agents that generate images and video, judge their own outputs, and iterate to improve results. This course explores what happens when AI starts evaluating AI. Taught by Katie Nguyen and Wafae Bakkali. Enroll for free: hubs.la/Q04hkdr80

One of the biggest prompting mistakes is asking AI to generate the final draft immediately. A better workflow? Start with the outline first. Small changes to the structure can dramatically improve the final result and help you avoid generic AI writing. Learn practical prompting techniques in AI Prompting for Everyone with Andrew Ng: hubs.la/Q04hdPZW0

Time for another poll! Are current AI image models able to correctly identify the two gym machines in this picture? A. Yes B. No C. Maybe Share your answer in the comments! Learn more about the latest advances in multimodal reasoning models and how to prompt them in the AI Prompting for Everyone course: hubs.la/Q04hdBFp0

This week, in The Batch, Andrew Ng announced the launch of “AI Andrew,” an AI companion designed to reflect his communication style, values, and approach to mentoring. AI Andrew is available for conversations about AI, careers, and personal growth. Plus: 🛡️ U.S. Government Plans Pre-Release AI Model Testing 🎙️ OpenAI Launches Smarter Real-Time Voice Models 🌏 China Blocks Meta’s Acquisition of AI Agent Startup Manus 🎗️ Google’s AI Breast Cancer Detector Shows Promise in Real-World NHS Tests Read The Batch: hubs.la/Q04h093v0

No more words needed. Learn spec-driven development with coding agents now: hubs.la/Q04h0Cq20

AI gives generic answers when your prompts are generic. The fastest way to get more interesting outputs? Give it more specific, unexpected context. In AI Prompting for Everyone, Andrew Ng shares practical techniques to help you get more useful, creative responses from AI systems. Explore the course now: hubs.la/Q04gSTh10

Data is hungry for context. A transcript tells you what was said. Audio can tell you how it was said. Images contain text, diagrams, and visual information. Video brings it all together over time. Most enterprise data lives in these formats, and most of it still goes unused. Learn how to process and retrieve across multimodal data in Building Multimodal Data Pipelines: hubs.la/Q04gFttd0

Want more AI insights like this? Learn the fundamentals behind prompting, context windows, and how AI systems work in AI Prompting for Everyone: deeplearning.ai/courses/ai-pro…

Quick challenge! Don't use AI tools for this one 👀 How many Harry Potter books can you fit with a 750k-token context window?