Design the study
Define what to learn, which participants to recruit, and where the script should talk, observe silently, debrief, or speak a transition.
AI-led user interviews, built into your product
UserTold.ai turns real user interviews into evidence your agent can ship against.
Launch interviews inside your product, capture voice and screen, and turn what users say into reviewable evidence — then push the work that survives review to GitHub or Linear. Readable from the dashboard, MCP, CLI, or REST API.
Pay only for what you useBring your own key — no markupGitHub, Linear, MCP, CLI
Live interview
One conversation becomes one shipping decision
Transcript moment
"I tried this flow three times and still cannot find where to change billing settings."
/settings/billing00:42
Extracted evidence
Struggling moment with strong confidence and source evidence.
TypeStruggling moment
Confidence0.91
Work item payload
{
"title": "Clarify billing settings entry point",
"source": "sig_billing_findability",
"push": "linear",
"watch_for_recurrence": true
}How the loop works
From interview capture to evidence-backed delivery
The point is not to collect transcripts. The point is to create a repeatable operating loop: capture reality, review evidence, route work, then keep resolved evidence connected to future recurrence.
Run the interview
Embed the interviewer inside your product so interviews capture the real screen, voice, transcript, and workflow context.
Extract reviewable evidence
Convert raw interviews into evidence with source quotes, confidence, page paths, and enough context for a human or agent to verify.
Verify and route
Review evidence packets against source context, then push verified work into GitHub or Linear with the quotes and interview context still attached.
Watch for recurrence
When Linear marks the issue complete, resolve the current evidence and watch future interviews for similar evidence that may resurface.
$ usertold init --name "My Product" --format json --yes
$ usertold project use <projectRef> $ usertold project overview Interviews: 24 total (22 completed, 2 active) Evidence: 61 total Work items: 12 total
Source evidence
Review the evidence before your agent writes the work item
UserTold.ai is built so the quote, the source, the confidence, and the resulting work item stay connected. That makes the output useful to both humans and agents instead of collapsing into vague summaries.
Evidence packet
“I expected billing to live under account settings, not workspace settings.”
Interview replay, transcript context, and the exact page path all stay attached to the evidence so reviewers can validate the interpretation.
Interview replayPage pathBehavioral contextWork item link
Issue routing
Push the evidence into GitHub or Linear with source quotes, evidence context, and enough structure for an agent to understand why the work item exists.
Completion sync
When the linked Linear issue is completed, UserTold resolves the current evidence and watches future interviews for similar evidence that may resurface.
Operator visibility
Studies, interviews, and evidence live in one workspace so the whole research loop stays reviewable.
Choose the surface
Use UserTold.ai from the product, the dashboard, or the agent loop
The same research system can live inside your product for real interviews, in the dashboard for review, and inside agent workflows for routing and orchestration.
Embed path
Launch an in-product interviewer with the widget and REST API so real users participate in context.
- Widget embed
- Screen + voice capture
- Study + intake control
Agent path
Let your coding or ops agent design studies, trigger interviews, read evidence, and create work items without touching the browser.
- MCP tools
- CLI --json output
- GitHub + Linear routing
Completion path
Keep delivery connected by syncing Linear completion, resolving current linked evidence, and watching new interviews for possible recurrence.
- Linear completion sync
- Resolved evidence
- Recurrence watch
Pricing and operating terms
Simple pricing for autonomous systems
Use our AI and pay only for what you use — billed per token against prepaid credits, with no key required to start. Or bring your own provider key and pay them directly, with no markup from us.
Platform
Pay as you go
No key required to start. You pay only for the AI you use, drawn from prepaid credits and capped at a limit you control — so you never get a surprise bill. Credit packs start at $10.
Inference
BYOK
Bring your own OpenAI key and your provider bills you directly — we add no markup, so you keep full visibility and control over inference cost.
Common questions
By default, UserTold runs the AI for you, and you pay only for what you use — billed per token against prepaid credits, with no key required to start. New accounts start with about $2 of platform credits, and your usage and balance are always visible in Billing. Credit packs start at $10. Prefer your own provider? Add an OpenAI key and we charge nothing for inference — your provider bills you directly.
Start the loop
Your agent deserves evidence, not guesses.
Set up a project, embed the interviewer, review the extracted evidence, and route a real pain point into work in under an hour.