AI & Analysis
AI at every step of your feedback program.
Every comment read, every market asked and every chart ready in seconds, so your CX team acts on what customers say while it still matters. It all runs on the model your IT team already approved, with your experience data in your own infrastructure.
Pick a time right in the form.
- Draft a survey1
Find out how customers feel about delivery after their parcel arrives.
- How satisfied are you with your delivery?
- What made your delivery good or bad?
Draft survey · 4 questions
- Translate it2
Germande-DE
Frenchfr-FR
Spanishes-ES
- All translated
- Sort comments3
“Paket kam einen Tag früher an.”Parcel arrived a day early.
Very positiveJoyTopic Delivery › Delivery time › Arrived early
- Chart results4
Delivery CSAT by country this quarter
- Germany91%
- France88%
- Spain86%
- United Kingdom84%
- Ask an agent5
What do customers want next from delivery?
Used 2 Formbricks tools
To pick a delivery slot: 23 comments ask for it. I drafted a follow-up survey for your review.
The path
Start with the foundation.
The CX teams that get the most from AI start where IT can say yes: experience data in your own infrastructure, AI on the model you already approved, no new sub-processor. With that signed off, value comes fast and every team can share in it.
Step 1Start here
Set the foundation
Led by IT and compliance
IT signs off in one review
Step 2
Prove the value
Led by the CX team
CX shows value in weeks
Step 3
Scale to every team
Shared across the company
Every team gets answers in chat
Surveys
A survey in minutes, in every language.
Describe what you want to learn and Formbricks writes the draft question by question, in the language of your prompt. Regenerate until it fits, then open it in the editor. Nothing reaches a customer until someone activates it.
Translate with AI fills every empty field for a language in one pass, choices and button labels included, and leaves what you translated by hand alone. Review it, save it, and every market answers the same survey.
Your prompt
Find out how customers feel about delivery after their parcel arrives.
- 1How satisfied are you with your delivery?CSAT
- 2What made your delivery experience good or bad?Open text
- 3Which delivery option did you choose?Single select
- 4How likely are you to recommend Northwind to a friend?NPS
Translated20%100%
- 1.1How satisfied are you with your delivery?Wie zufrieden sind Sie mit Ihrer Lieferung?(by hand, kept)
- 2.1What made your delivery experience good or bad?Was hat Ihr Liefererlebnis gut oder schlecht gemacht?
- 3.1Which delivery option did you choose?Welche Lieferoption haben Sie gewählt?
- 3.1Standard · Express · Pickup pointStandard · Express · Abholstation
- 4.1How likely are you to recommend Northwind to a friend?Wie wahrscheinlich ist es, dass Sie Northwind einem Freund empfehlen?
Enrichment
Know what customers say before anyone reads it.
Every open answer, review and ticket gets a sentiment label, its emotions and a translation into your working language, with the original kept next to it.
Topics & Subtopics sorts the comments into themes up to four levels deep, in every language. You see that 712 comments praise parcels arriving early before anyone has read one.
“Paket kam einen Tag früher an. Super!”de
Parcel arrived a day early. Great!
Very positiveJoyArrived early“Livré le jour même, impressionnant.”fr
Delivered the same day, impressive.
Very positiveSurpriseArrived early“Came right on the day they promised.”en
PositiveJoyOn schedule“El embalaje llegó en perfecto estado.”es
The packaging arrived in perfect condition.
PositiveJoyArrived intact
Every open answer gets a sentiment, its emotions and an English translation, original kept.
L1Delivery1,640
L2Delivery time1,210
L3Arrived early712
L3On schedule498
L2Packaging430
L3Condition286
L4Arrived intact204
L4Damaged in transit82
L3Packaging waste144
Charts
Ask for a chart in plain English.
Type “Delivery CSAT by country this quarter” and Formbricks builds the query and draws the chart. Fine-tune it in the builder, save it to a dashboard, and every team quotes the same number the same day.
The model is given source names, question labels and languages, never the feedback itself.
Describe the chart you need
Delivery CSAT by country this quarter
Delivery CSAT by country87%
This quarter · Bar · 1,460 CSAT answers
- Germany91%
- France88%
- Spain86%
- United Kingdom84%
Agents
Agents do the legwork. People decide.
Connect Claude, ChatGPT, Codex or your own agents to Formbricks over MCP. They search your feedback by meaning, add records, and draft surveys and workflows from one request in chat.
Every agent works with the login and role of the person who connected it, and the workflows it builds wait as drafts for a person to switch on.
Customers love our fast delivery. What do they want next? Draft a short follow-up survey and a workflow that tells Logistics.
Used 4 Formbricks tools
The next wish is choosing a delivery slot: 23 comments ask for it. I drafted a three-question survey and a workflow that shares new requests with Logistics. Both are waiting for your review.
search_feedback_records
23 comments ask to pick a delivery slot
create_survey
Delivery slots · 3 questions
create_workflow
Slot requests to Logistics · draft
test_workflow
Dry run passed, nothing sent
- Anna's role and scopes apply to every call.
For IT
One model, one switch, a clear data path.
Point Formbricks at the model your company approved, from an open model you host to Gemini, Azure OpenAI or Amazon Bedrock, including through your company's AI gateway. Enrichment runs on the model you set for it in Formbricks Hub.
AI stays off until a model is configured and an Owner or Manager switches on Smart functionality. Each feature sends the model only what it needs.
- Survey creationYour prompt
- TranslationThe survey's own text
- ChartsLabels and languages, no feedback
- EnrichmentComments, to your Hub model
- AgentsWhat the agent reads, to your AI tool
Responses and records stay in your PostgreSQL.
Customer stories
Trusted by teams that own their data
See how public sector, research and product teams run feedback on Formbricks.
Public Sector
How DigitalService runs user research for German ministries on self-hosted Formbricks
- 2 weeks
- From decision to production
- >15
- Ministry projects
- 0h
- Manual compliance work
Read full story“Self-hosting makes us faster. Because we work on a project basis with various ministries, it is our responsibility to respect their rigorous standards for data protection.”
Joshua Nowak
User Researcher @ DigitalService
Market Research
How Borderless Access went from months to minutes, with zero engineering time per survey
- 15 days
- Implementation
- Mins
- To launch a new survey
- 0 hours
- Engineering time
Read full story“The rule with Formbricks was simple: do the integration once, and then leave it. My engineering team spent about 15 days getting everything set up, and since then marketing has been completely self-sufficient.”
Srihari Udugani
Director of Technology @ Borderless Access
Market Research
How Opinodo gathers millions of responses with a self-hosted instance of Formbricks
- 38%
- Cost reduction
- 8%
- Higher completion rate
Read full story“Big Formbricks fan here! It has enabled us to radically improve our customer retention and even exploring new revenue streams.”
Rasmus Lønne
Managing Director @ Opinodo
Frequently asked questions
Which license includes it?
Can AI help us move from Qualtrics?
Is our feedback used to train AI models?
Where does it run?
- Read the code
- ISO 27001 certificate on request
- SOC 2 Type II report on request
- Accessibility report available
See AI at work on your own program.
Tell us which programs you run and which models your IT team has approved. We'll show you a survey drafted, translated, enriched and charted, on feedback like yours.