Agents and builds
Ship versioned workers with prompts, AOPs, tools, connections, evaluation notes, and release history instead of one-off scripts.
Runs
Start, inspect, pause, resume, approve, and replay agent work from your app, backend service, or operator workflow.
Queue
Build intake for claims, invoices, tickets, alerts, leads, or files so agents can claim and process work at controlled concurrency.
Human-in-the-loop
Pause for approvals, missing context, policy decisions, or exception review without breaking the run or losing state.
Files and sandboxes
Stage evidence, generated artifacts, browser downloads, and temporary execution state alongside the run that produced them.
Connections and MCP
Use hosted tools, your own MCP servers, enterprise APIs, browser automation, and desktop access through one controlled runtime.
Schedules and triggers
Run work on events, files, webhooks, queues, or cadences without turning every use case into custom orchestration code.
Automations and Modules
Manage Automations and Modules from the API, MCP or CLI: access policy, readiness, roles and dashboard data, set up Modules without the web app, and let Ask Duvo or the CLI generate process maps, proposals and builds.
Operating Insights dashboards
Create, refine, refresh, publish and export live dashboards over runs, queues and cases from the API, MCP or CLI, so reporting ships with the process.
Evaluations
Every completed agent run is scored automatically against more than 30 built-in rubrics plus criteria written for that agent. Each agent run's check results and reasons are in the agent's Evaluations tab and available through the API, MCP and CLI.
Skills and plugins
Package reusable capabilities so teams can share specialist behavior across agents instead of copying prompts between them.
Included
Queue state, Retries, Tool auth, File staging, Schedules, Webhooks, Handover, Approvals