Engineering: AI

You can vibe code almost anything right now. Describe an app, and a model will build a working interface in minutes. So why hasn't that produced a wave of new companies? We wanted to find out. So we picked one of the hardest products to fake, an AI support concierge, the kind of system that handles millions of customer conversations for companies valued in the billions. Then we tried to build one with a single prompt.

You might remember Moltbook, a vibe-coded social network for AI agents that fell apart within a week because messages weren't private and there was no moderation. This piece is about the gap between a vibe-coded demo and a production-ready real-time feature, and why AI tools can't close it for you.

Apps like Slack and WhatsApp made team chat easy. The right AI features can make it better. Here's how to build them into community, collaboration, and team platforms to increase user satisfaction and speed up task completion.

Understanding rarely arrives through a single sense at a time, and neither should an agent. This guide breaks down how to design multimodal AI agent architecture for voice and video apps that hold up in production, using the architectural choices, transport options, and model constraints that matter most.

What we learned building a prescription-intake voice agent with Stream's Vision Agents SDK and AssemblyAI: five lessons for safety-critical AI agents.

A phone support voice AI needs to react in real time - start replying within 300ms, stop the moment a caller interrupts, and handle the telephony edge before the model sees the audio. This guide covers the full pipeline - streaming STT, TTS, turn detection, barge-in, and the latency budget that keeps calls feeling natural.

Warm transfer carries the conversation's context to the human agent - the summary, the intent, the caller's mood - so the human can pick up mid-story. Cold transfer carries only the audio, and the caller starts over. Building warm transfer in a real-time voice system means solving three problems when to escalate, how to generate structured context in parallel with the live call, and how to hand off the audio session without breaking it.

A vision agent watches a live video and audio stream and acts while things are still happening. Here is what a vision agent is, how it differs from batch vision pipelines and voice agents, and how to build one in about 18 lines with Vision Agents, the open-source Python framework from Stream.