Deep dives into the technology behind AI voice agents — LLMs, speech-to-text, real-time voice processing, and more.
9 of 81 articles
How to design APIs for AI agent platforms — comparing REST, GraphQL, and gRPC for agent invocation, streaming responses, tool registration, and multi-agent orchestration.
How to build responsive AI applications using streaming, WebSockets, and SSE, with practical patterns for token streaming, agent status updates, and real-time collaboration.
Mastercard completes the first-ever live agentic payment transaction in Singapore with DBS and UOB, where an AI agent autonomously booked and paid for a ride to Changi Airport without human intervention.
DeepL's 2026 Language AI Report reveals that despite massive AI spending, 83% of enterprises still haven't deployed LLMs or agentic AI for translation, with 35% relying entirely on manual workflows.
Figure AI releases stunning video of its Helix 02 humanoid robot autonomously cleaning a living room, picking up clutter, vacuuming, and organizing — marking a breakthrough in whole-body robotics.
A practical guide to building production-grade AI pipelines using LangChain and LlamaIndex, covering when to use each framework, architecture patterns, and lessons from real deployments.
How vector databases and semantic search power AI agent memory, RAG systems, and knowledge retrieval with practical guidance on embedding models, indexing, and query strategies.
A technical guide to modern LLM inference optimization techniques — quantization, speculative decoding, KV-cache optimization, continuous batching, and PagedAttention. Make models faster and cheaper.
