Workflow tools in eve: deterministically orchestrate subagents, add human-in-the-loop, stream progress, and durably execute multi-step work

Every engine before us got something right. A brief history of what we kept and what we didn't.

It's actually crazy how useful this is. As we've been grinding on driving @workflowsdk overhead close to 0ms - this little tool has gone a long way

Vercel Observability now supports structured search for workflow runs. Filter by workflow, deployment ID, region or any custom run attribute. vercel.com/changelog/expande…

You can now configure where Vercel Workflows keeps each run's state, defaulting to where the run starts. For agents, state can now live in the same region as the loop writing it. vercel.com/changelog/configu…

Navigate traces on Vercel Workflows faster with a new minimap. vercel.com/changelog/vercel-…

𝚆𝚘𝚛𝚔𝚏𝚕𝚘𝚠𝙰𝚐𝚎𝚗𝚝 is now available in AI SDK 7. Build a durable agent that survives restarts, deploys, and approvals that arrive hours later. Learn how to migrate from 𝙳𝚞𝚛𝚊𝚋𝚕𝚎𝙰𝚐𝚎𝚗𝚝 to 𝚆𝚘𝚛𝚔𝚏𝚕𝚘𝚠𝙰𝚐𝚎𝚗𝚝 ⬇️ ai-sdk.dev/docs/agents/workf…

Buttons and modals in Chat SDK now accept a 𝚌𝚊𝚕𝚕𝚋𝚊𝚌𝚔𝚄𝚛𝚕 prop. Pair it with a @workflowsdk webhook to pause a run, then resume it when a human in the loop clicks a button. vercel.com/changelog/chat-sd…

@vercel Ship26 is live! This year, we shipped a 3D device that can create WASM apps using wterm, just-bash, and @workflowsdk ...and a landing full of agents that walk around the site using a dynamic navigation mesh.

The hardest thing about agents and backends is durability. @workflowsdk fixes this. That LLM you're calling *will* go down. That service *will* rate limit you. That database *will* unexpectedly slow down. You *will* get paged 💀 I've been looking for a unicorn for a decade. I wanted the level of reliability of combining stuff like SQS / Kafka / microservices, and I absolutely did not want *that* at the same time 😂 Truly reliable systems like that are notoriously difficult to reason about, to develop locally, to test, to simulate, to deploy… Workflow SDK solves that without compromises. We're doing what Next.js did for the frontend, but for one of the most important problems of the new generation of backend applications. Notably, Workflow SDK has an incredible self-hosting and multi-cloud story from day 0. We've taken amazing lessons from Next.js and poured them into the many Worlds (adapters) you can deploy to. Congrats to Pranay and the Workflow team on a generational ship: vercel.com/blog/a-new-progra…

Vercel Workflows is GA. Your code is the orchestrator. Ship agents, backends, or any long-running process without managing queues, retries, or workers. vercel.com/blog/a-new-progra…

You can now filter workflow logs to easily view all logs for a workflow run in one place. Jump directly from a run to logs, filter by steps, and quickly find relevant requests.

Workflow DevKit is now @WorkflowSDK

A fascinating aspect of Open Agents is how it uses the @WorkflowDevKit SDK to elegantly orchestrate agent sessions efficiently. But before we go deeper, let's understand the problem: Open Agents is a coding agent that runs in the cloud. Naturally, the expectation here is that I should be able to kick off multiple sessions and go to sleep and then wake up to a stack of PRs. This inherently means, the sessions should be - long running - stateful - resumable - reliable A naive way to solve this: - Write an API to start a session, create a session ID and store it in a database - along with other metadata. - Trigger the session inside a sandbox (Vercel sandboxes can run up to 5hours) and stream the responses back to the client using a websocket - Store the responses to the db so when a client reconnects to a session using a session ID, we can resume it by fetching the results and restarting the session Why wouldn't you just do this?