PandaiBesi finds posts about your restaurant on TikTok, Instagram Reels, X and Threads, uses AI sentiment analysis to read their tone, and shows the words behind every label.
The feed: newest posts first, each with its overall tone and element labels.Details: every element label quotes the post's own words.
Design mockup. Restaurant, accounts and posts are invented.
How it works
03 steps
01 / Collect
Find the posts.
PandaiBesi searches TikTok, Instagram Reels, X and Threads for posts about one restaurant, within a fixed monthly budget per restaurant.
02 / Judge
AI sentiment analysis.
An AI model reads each caption: is it about the restaurant, and is it positive, negative or mixed? Then it reads the tone for food, service, value, ambience and convenience separately.
03 / Show
Keep the evidence.
Every element label quotes the words it came from, so a person can check it. No label means no opinion was read, never neutral.
In private testing.
PandaiBesi runs privately while we test how well it finds and reads posts. It is not open to the public yet, but restaurants can join the test for free.
It is built with Claude Code, step by step, and each step is checked before the next one starts.