Nobody books the call
You email ten users a calendar link. One replies. Zero show. The personalized feedback email? Crickets — even from the power users.
Code got cheap. Knowing what to build didn’t.
Ask your users why, while they can still tell you.
UserTold.ai runs a voice interview about the moment a real user gets stuck, in the same session — the quote, the screen, and the page path stay together. You and your coding agent review the Evidence before it supports a Finding.
Voice + screen + navigationMCP · CLI · REST$0.25 / recorded minute
REC · interview in progress — trial user, day 3study: onboarding-friction
navigation/pricing/settings/account← back ×2/settings/accountscreenvoice
01:12 observed02:22 said02:41 asked why
Observed01:12
Opens account settings. Scans. Goes back. Returns and scans again.
/settings/account → back ×2
Said02:22
“I expected billing under account settings. I went back twice and still couldn’t find it.”
Asked why — 19 seconds later02:41
The debrief asks about the exact moment it just watched — while the user can still explain what they expected and where they looked.
Evidenceextraction confidence 91%
Quote, replay, and page path stay attached.
Quote, replay, and page path stay attached.
Draft FindingClarify where billing settings live — 3 linked moments from 3 users.
✓ Pushed to LinearReviewed first: you or a project-aware agent open the linked moments and review the Finding. Product triage decides whether it becomes delivery work, and sources travel with any issue.
● WatchingWhen the Linear issue completes, later Evidence can prompt a review for possible recurrence.
The gap
You have the users. You keep missing the moment.
Analytics say what, never why
The funnel shows where they left. Session replays pile up that nobody has time to watch. The reason walks away untold.
Feedback arrives without context
A churn survey says “too complicated.” Which screen? Which task? By the time you can ask, they’re gone.
UserTold asks at the only moment users can actually answer: while it’s happening, inside your product.
How it works
From a real moment to a merged fix
Each step leaves something you can open: the widget in your product, the recording, the evidence card, the issue in your tracker. Nothing in the chain asks to be taken on faith.
→ a widget in your product
Embed once
One script tag. Choose the mode per study: silent observation, a guided task, or an open conversation.
→ a recorded session
Meet users in the moment
An AI interviewer talks with users in their language, or quietly captures real usage — voice, screen, and navigation.
→ source-linked evidence
Get evidence, not opinions
Struggling moments, desired outcomes, workarounds — each with the quote, the timestamp, the page path, and the replay.
→ a verified issue
Ship it, then watch
Related evidence groups into one draft. You open the linked moments, mark it ready, and push it to Linear or GitHub with the source evidence attached. When a linked Linear issue completes, UserTold watches later interviews for the same evidence.
Evidence-first
Open the evidence. Don’t trust the summary.
AI research tools hand you conclusions. UserTold hands you conclusions with the receipts attached — what a person said, what was observed, and what the model inferred stay in three separate fields, next to the second of the recording they came from.
Evidence · struggling_momentses_xyz789 · 02:22
“I tried this flow three times and still cannot find where to change billing.”
Replay 02:22/checkout/step-3Extraction confidence 91%2 similar moments
The same evidence, as your agent sees it
{
"signal_type": "struggling_moment",
"quote": "I tried this flow three times and still cannot find where to change billing.",
"observed_facts": ["Returned to /checkout/step-3 three times"],
"interpretation": "Billing settings are not where users look for them during checkout.",
"confidence": 0.91,
"intensity": 0.8,
"interviewRef": "ses_xyz789",
"timestamp_ms": 142300,
"page_url": "/checkout/step-3"
}For coding agents
Your agent can ship. Now it can find out what’s worth shipping.
UserTold puts MCP, the CLI, and the API first. A coding agent can design a study, wait for real users to take part, and read the evidence as JSON, where every tool declares the exact shape of its answer up front, before it proposes a fix.
MCPmcp.usertold.ai/mcp — OAuth, tools for projects.* studies.* interviews.* evidence.* findings.*
CLIusertold study create --title "My Product Study" --activate --format json
HandoffReviewed Findings can be sent to Linear intake or GitHub delivery with quotes and source moments attached.
See how agents use UserTold →# an agent-run study, end to end
read usertold://projects
call studies.create
… real users take part, inside your product …
call evidence.list
call findings.create_from_evidence
… human or agent verifies the grouping …
call findings.send → Linear UT-214On purpose
Three things UserTold refuses to do
Recruit strangers
No panels, no rented respondents. It interviews people already using your product — and a Study with no takers stays at zero Interviews instead of producing Evidence from nowhere.
Interrupt a struggle
During observation, stuckness is evidence. The interviewer doesn’t jump in to rescue, hint, or steer — it asks why afterward, when the moment is on record.
Fake certainty
What a participant said, what was observed, and what the model inferred are never blended. Every Evidence card carries its source and a confidence score.
Pricing
Priced like an API, not a research department
Pay for recorded interview minutes. No subscription, no seats, no per-interview minimum — billed on exact recorded seconds, itemized in Billing.
Managed AI
Inference included$0.25 / recorded minute
One predictable UserTold charge. We operate and pay for the interview AI.
5 min $1.2520 min $5.0060 min $15.00
BYOK
Your OpenAI key$0.15 / recorded minute
UserTold charges the platform fee. OpenAI bills inference directly to your provider account.
5 min $0.7520 min $3.0060 min $9.00
Questions
Before you ask
From your product. UserTold interviews users you can already reach — it does not recruit, and it does not guarantee responses. In-product timing is the point: the user is already there, in the moment you want to ask about.
The next thing you ship should be something a user told you.
Add the script to your product, verify it on one page, and take the starter interview yourself. Read the evidence it produces before you point it at real users.