Most knowledge agents start the same way. You pick a vector database, then build a chunking pipeline. You choose an embedding model and then tune the retrieval parameters.
I recently authored this piece on the @Vercel blog, breaking down a different and better way you can create knowledge agents. Powered by Vercel Sandbox, Workflows, Chat SDK, and more.
h/t @hugorcd for creating the beautiful template that led to the creation of this blog post.
https://t.co/t5NM22TQRe
Build an AI agent that streams replies into @liveblocks comment threads using the Chat SDK and @aisdk.
New guide on the @vercel KB β¬οΈ
https://t.co/6knLSXRXw8
Chat SDK now ships a built-in @aisdk toolset.
One πππππππ²ππππππππ(ππππ) call adds the full set of chat tools into your agent. Presets scope the surface, and writes are approval-gated.
https://t.co/JLF9N8fAYm
Buttons and modals in Chat SDK now accept a πππππππππππ prop.
Pair it with a @workflowsdk webhook to pause a run, then resume it when a human in the loop clicks a button.
https://t.co/GdOusbCMir
Introducing Files SDK
A unified storage SDK for object and blob backends. One small, honest API. Web-standards I/O. An escape hatch when you need the native client.
β 18 providers - S3, R2, Vercel Blob, Google Drive, etc.
β upload, download, head, delete, copy, list, url
β Works everywhere - Node, Bun, Deno, edge runtimes, browsers
β Tools for OpenAI, Vercel AI and Claude Agents SDKs
Do you like building agents you can talk to and get things done with? That's what Chat SDK gets in just a few lines of code.
Join me and @BenSabic on our latest @VercelCommunity, where we discuss the doors our Chat SDK opens for your agents. Link below: