User feedback is messy.We make it actionable.
Pipe in feedback from your app, inbox and app-store reviews. Sentriment clusters it into themes, prices what each one costs you in MRR, and scores every user's health — so you see churn coming while it's still preventable. Hosted entirely in the EU.
No credit card · Set up in 5 minutes · 100% EU-hosted, GDPR-first
Two ways in
Ship it before lunch — or wire it your way.
One line for product teams, a full REST API for engineers. Both feed the same real-time analysis pipeline.
For product teams
5-Minute Snippet
<script src="https://app.sentriment.com/widget.js"
data-key="pk_live_7f3a91c2" async></script>- Shadow-DOM widget, ~5 KB, framework-free
- Keys locked to your domains — useless anywhere else
- PII redacted before anything is stored
For engineers
Robust API
await fetch("https://app.sentriment.com/api/v1/feedback", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.SENTRIMENT_KEY}`,
},
body: JSON.stringify({
text: "Checkout freezes when I apply a coupon",
userId: "usr_8231", source: "in-app",
metadata: { plan: "pro", version: "4.2.1" },
}),
});- Pipe in support tickets, NPS verbatims, call transcripts
- Idempotency keys, rate limits, RFC 7807 errors
- Identify users with traits · signed webhooks out
Nothing to build? Feedback also flows in on its own — App Store reviews, Intercom, Zendesk sync automatically, and CSV imports handle the backlog. See all integrations ↓
One queue, whatever the source
The aha moment
From 10,000 comments to the one thing to fix — before your standup.
Clusters update in real-time as feedback streams in. Spikes get flagged, summarized, and routed to the right team automatically.
Feedback Overview
Last 24 hours · 1,284 items ingested
Trending Issues
▲ 340%42 users report cart freezing
AI summary: Freezes occur on coupon apply, iOS Safari only. First seen 6h ago — correlates with checkout v4.2.1 rollout.
“Coupon field just spins forever on my iPhone.”
“Cart freezes the second I apply SAVE20.”
42 items cited · claude-opus-4-8 · prompt 2026-07-19.3
Sentiment
Top clusters
- Checkout · Payments42
- Onboarding confusion27
- Search performance19
- Editor praise14
User Health — new
See churn coming while it's still preventable.
Churn tools tell you who left. Sentriment reads what every user is telling you and scores how they feel right now — so you reach out while there's still a customer to save.
- Every identified user gets an explainable 0–100 health score — recomputed nightly and the moment new feedback lands. No black box: the score shows its math.
- The instant someone drops into at-risk, Slack or email tells you who, why, and what they pay — with a one-click jump to their full history.
- Health history is charted per user and across any segment — so you can see whether last month's fixes actually moved the people who complained.
- Scores sync back into Mixpanel and Amplitude as user properties. Build cohorts, trigger campaigns, gate onboarding — in the tools you already use.
At risk ↓ declining
7 items weighed · sentiment −0.42 · emotion penalty −12
nightly score · dots = their feedback, colored by sentiment
User at risk: usr_8231
dropped to 23 · plan: pro · 290 MRR → open their history
The full pipeline
Everything between raw quote and roadmap.
Collection is the easy part. Sentriment handles what happens after — the reading, tagging, counting, and summarizing your team never has time for.
Themes, priced in revenue
Every theme carries the MRR behind the people reporting it, so the roadmap argument is about money rather than volume.
Correlated from the identity traits you already send — no extra tracking.
Ask anything. Get a cited answer.
Natural-language questions over your whole corpus, answered with a verdict, a number, and the quotes it rests on. Track one and it re-answers on a schedule.
“What do enterprise users say about SSO?”
“We can't roll this out without SAML.”
“Okta or it's a non-starter for our security team.”
Every answer records the model and prompt version that produced it.
Sentiment & emotion
Beyond positive and negative: frustration, confusion, delight and churn-risk, per theme.
Alerts that matter
Slack or email when a theme surges, a fixed issue returns, or a user drops into at-risk.
Spiking: checkout freezes
7 in 24h · 4.2× baseline
User health
An explainable 0–100 score per identified user, synced back into Mixpanel and Amplitude.
Also in the box
- Semantic search
- Saved reports
- Trait segments
- Triage workspace
- GitHub & Linear filing
- “You asked, we shipped” notes
- CSV import & backfill
- Outbound webhooks
- Public REST API
🇪🇺 EU-first, by architecture
GDPR isn't our checkbox. It's our architecture.
Sentriment was built inside the EU rules from the first commit — not retrofitted for a compliance page. These aren't policies. They're how the pipeline works.
PII is redacted before storage
Not encrypted-and-hoped-for. Emails, names, phone and card numbers are replaced with typed placeholders before a single byte hits the database — so there's no raw PII to breach, subpoena, or leak into a model.
# in-app widget
"refund me at sara.k@acme.io, card 4242 4242 4242 4242"
received…
# POST /api/v1/feedback
"Marta Ellis — call me on +34 612 04 88 91"
received…
100% EU data residency
Database in Frankfurt, compute in the EU. Your users' feedback doesn't cross the Atlantic — not at rest, not in processing.
database
Frankfurt
compute
EU only
backups
EU only
Right to be forgotten, built in
One API call erases a user's feedback and identity everywhere — clusters recount, exports comply. Deletion is a feature, not a ticket.
DELETE /api/v1/users/usr_8231
204 No Content · cascade completed
Your data trains nothing
Feedback is processed to serve your dashboard — never used to train shared models. Every AI output records the exact model and prompt that produced it.
every output stamped · claude-opus-4-8 · prompt 2026-07-19.3
Integrations
Feedback lives everywhere. Sentriment reads all of it.
Every channel flows into one stream — support tickets, store reviews, community chatter, survey verbatims.
Slack & email alerts
Spikes, regressions, and at-risk users — the moment they happen
Mixpanel & Amplitude sync
Health scores pushed onto user profiles — cohort and campaign on them
GitHub & Linear issues
File from a theme; feedback linked to the fix
Daily digest
What changed overnight, in your inbox
Dashboard, API & webhooks
Query clusters programmatically, push events out
How it works
Three steps. No analysts required.
Connect
Drop in the snippet, hit the API, or plug in your support stack. Historical backfill included.
Cluster
Our AI reads every item, dedupes it, groups it by theme, and scores sentiment — in real-time.
Act
Get ranked issues, cited summaries, and alerts where you work. Ship the fix, watch the cluster shrink.
0.0s
from raw feedback to a labeled, sentiment-scored theme — measured in production
0.0KB
widget footprint — framework-free, shadow-DOM isolated, one script tag
0%
EU-hosted — data in Frankfurt, compute in the EU, PII redacted before storage
One real item, straight through the pipeline
“Love the new dashboard, but the export button is impossible to find”
Actual output from our production pipeline — theme label and emotions included. 8.7 seconds, end to end.
FAQ
Questions, answered.
PII (emails, names, phone and card numbers) is redacted before anything is stored — the raw text never touches the database. Everything is hosted in the EU (data in Frankfurt), encrypted in transit and at rest, never used to train shared models, and deletable via API at any time. SOC 2 is on the roadmap; the GDPR architecture is live today.
Stop guessing what your users want.
Create your workspace and see real clusters from your own feedback in minutes. Free while we're in beta.