Built for agents. Not just compatible.
UserTold.ai exposes a full MCP server and CLI with machine-readable JSON output at every layer. Your agent designs studies, triggers interviews, reads structured evidence, verifies review packets, and pushes evidence-backed work items — all programmatically.
The research loop
projects.get_context
Assess evidence distribution, work item status, active studies, and coverage gaps for the current project.
studies.create
Create a structured study from a script. Idempotent — safe to call repeatedly.
Interviews run
The widget embeds in your product. Interviews capture real usage, silent observation, planned debriefs, and recordings.
evidence.list
After interviews complete, list extracted evidence: struggling_moments, desired_outcomes, workarounds.
work.create_from_evidence
Create evidence review packets from evidence clusters. Each packet links back to interview quotes for verification.
Packet verification
Review the packet against source evidence and project context before deciding whether it becomes delivery work.
work.push
Push verified work items to GitHub Issues or Linear with source quotes and evidence context attached.
Linear completion sync
When a linked Linear issue is completed, resolve the current work item evidence and keep watching new interviews for similar evidence that may resurface.
Start from MCP
Start from CLI
Output contract
Every command outputs --json. Every MCP resource is structured JSON. Schema is stable across releases.
{
"id": "sig_abc123",
"signal_type": "struggling_moment",
"quote": "I tried this flow three times and still cannot find where to change billing.",
"confidence": 0.91,
"intensity": 0.8,
"session_id": "ses_xyz789",
"timestamp_ms": 142300,
"page_url": "/checkout/step-3"
}Ready to build?
Connect your agent to the MCP server or set up the CLI and start your first study in minutes.