If you're building a chat product on Anthropic's managed AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → sessions, this removes the two most annoying layers — session/state persistence and per-platform webhook plumbing — by letting one type-safe streamingSending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.Full definition → handler serve web plus Slack, WhatsApp, Teams and Discord without a database.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Key quotes
“Claude Managed Agents handles the agent loop server-side, including the model, tools, session state, and sandboxed web research.”
“Chat SDK gives that agent a chat interface through a single type-safe handler, with adapters that carry it to Slack, WhatsApp, and more.”
“It runs on Chat SDK's web adapter, so there's no platform registration, webhook verification, or tunnel, just your Anthropic credentials.”
