vf CLI, and the MCP server.
Build and run
Build
Create and manage the pieces an agent is built from: playbooks, functions, tools, API tools, MCP servers, variables and knowledge base documents.
Running agents
Run conversations against an agent over HTTP. Send what a user would say, read the traces that come back, and inspect or reset the state between turns.
Publishing
Ship changes with environments. Edit a draft, publish it live, clone one to work in isolation, merge it back, and split traffic between versions.
Manage
Create and administer the containers your agents live in: workspaces that group projects and people, and projects that each own a single agent.
Measure and improve
Observe
Read the conversations your agent actually had. Search transcripts, fetch a single one, and attach your own properties to record what happened.
Insights
Score conversations against criteria you define, so agent quality becomes a number you can track over time instead of a sample you skim.
QA
Replay scripted conversations against your agent and assert what it does, so a change that breaks a scenario fails loudly instead of silently.
Analytics
Query usage and cost: tokens, calls, conversations and unique users, plus the spend attributed to individual functions, playbooks and tools.
Webhooks
Session lifecycle webhook
Receive events whenever conversations start or end, on both chat and voice.
Organization events webhooks
Receive events when projects are created, published, or deleted.