An AI pipeline does the first pass (clustering, labelling, mapping), and every decision waits for human review before it counts. This page follows one real comment the whole way through, then hands you the running app to try.
The pipeline, one comment at a time
Classifies each comment's stance toward the subject — supportive, opposed, or unclear — before any theming begins.
responses_df[response_id, response] (100 rows)df[response_id, response, position] (100 rows)prompt You are analyzing PUBLIC SUBMISSIONS to the consultation question described above.
I don't usually put opinions because when you are satisfied you don't do it often (wrongly) but for a business class flight the boarding route was not really up to par, we didn't even have a communication about the delay and for a company like Emirates leaving 3 days without a replacement flight is regrettable
Classified OPP ahead of any theming.
Onboarding, captured from the real product
Real screens from the pilot wizard, captured while it drove the actual AI-assist endpoints over 100 Emirates reviews. Two of the four steps are drafted by Gemini; the prospect only confirms.
The prospect uploads a CSV or Excel file — one comment per row, straight from a survey tool or review export. No pre-formatting, no template to fill in.
The dashboard, captured from the demo stack
These are screens from the running app analysing 1,643 real Emirates reviews. Run the bundle below and every one of them is yours to open on your own machine.
Comment volume, respondent counts, a demographics breakdown, and the research questions behind the analysis. The whole engagement on one screen, over 1,643 real Emirates reviews.
The AI groups its themes into parent categories you expand into their child themes. Each row carries a mention count and its share of the corpus; click one to pull up the comments behind it.
Search the comment text by keyword and stack filters: sentiment, theme, rating, source, date. Here “delay” takes 1,643 comments down to 213, with every match highlighted in place.
Each comment shows whether it is still AI-mapped or Analyst Verified, next to the themes and sentiment the AI assigned. An analyst confirms or corrects each one before it counts toward the reported numbers.
Run it yourself
Everything above is a real product. Clone the bundle and the same dashboard comes up on your machine, pre-loaded with the analysed Emirates data. You do not need an account or a sales call.
git clone https://github.com/fridai-dot-dev/agora-demo
cd agora-demo && docker compose up -d
# → http://localhost:3000 (login: demo / agora-demo)