Loading activity…
@ndrezn
PM @LangChain building Managed Deep Agents. I post demos, code, and what breaks. prev @plotly nathan (at) drezner (dot) xyz
AI
LangChain says the proxy adds tokens only to calls to services users have allowed, so the agent never sees them.
AI
LangChain says developers can use heuristics, decision models or custom logic to build loading states and receipts.
AI
LangChain says agents can find products, prepare purchases and pay, with a person approving every order.
AI
LangChain says @p0 powers the search, with no separate vendor account or search-tool wiring needed.
YouTubeAI
LangChain says agents can take requests from any webhook, not just Slack. It highlights a PhotonHQ-backed expense agent that logs receipts sent by text message.
AI
LangChain introduced the interface with the `mda chat` command. A launch post says it lets users test-drive an agent locally and is handy for lightweight development.
AI
LangChain says it will show the products first on the Interrupt keynote livestream, alongside a look at what's working for agents in production.
AI
A user shares a guide they describe as explaining what makes jev special and how to use it with agents.
AI
A user calls Jev “very cheap and fast,” praising its potential for new user experiences and interfaces built on modern language models.
