BrowserAct-Powered Movie Recognition & Search Bot

This template builds an AI-powered Movie Finder assistant connected to Telegram. It can identify movies from user text, screenshots, or other files by combining Google Gemini and BrowserAct’s “AI Film Finder Bot: Smart Scene & Concept Identification” workflow. Text route: When a user sends a message, the scenario checks whether it looks like a movie description. Valid inputs are rewritten by Gemini into a clean, structured description. The bot sends this refined text back to the user, then calls the BrowserAct Film Finder workflow with the description (and optional FilmFinder / Google URLs). BrowserAct searches the web, returns a JSON list of candidate movies and summaries, and Gemini turns that JSON into a friendly “movie analysis” block that is sent back to Telegram. File route: When a user sends an image or other attachment, the file is downloaded from Telegram and uploaded to Gemini. After a short delay to allow processing, Gemini analyzes the visual content and produces a single, compact paragraph describing the scene. That paragraph is then used in the same Film Finder workflow to search for matching movies, and the final results are again summarized by Gemini and returned to the chat. This template is ideal for building a conversational movie assistant or recommendation bot that can understand either written descriptions or visual clues and reply with likely movies, short summaries, and optional similar-title suggestions—fully formatted for Telegram.

make
BrowserAct-Powered Movie Recognition & Search Bot

This template builds an AI-powered Movie Finder assistant connected to Telegram. It can identify movies from user text, screenshots, or other files by combining Google Gemini and BrowserAct’s “AI Film Finder Bot: Smart Scene & Concept Identification” workflow.

Text route: When a user sends a message, the scenario checks whether it looks like a movie description. Valid inputs are rewritten by Gemini into a clean, structured description. The bot sends this refined text back to the user, then calls the BrowserAct Film Finder workflow with the description (and optional FilmFinder / Google URLs). BrowserAct searches the web, returns a JSON list of candidate movies and summaries, and Gemini turns that JSON into a friendly “movie analysis” block that is sent back to Telegram.

File route: When a user sends an image or other attachment, the file is downloaded from Telegram and uploaded to Gemini. After a short delay to allow processing, Gemini analyzes the visual content and produces a single, compact paragraph describing the scene. That paragraph is then used in the same Film Finder workflow to search for matching movies, and the final results are again summarized by Gemini and returned to the chat.

This template is ideal for building a conversational movie assistant or recommendation bot that can understand either written descriptions or visual clues and reply with likely movies, short summaries, and optional similar-title suggestions—fully formatted for Telegram.

$2.99
Last updated September 5, 2026
30-day money-back guarantee
Instant download
Lifetime updates included

New buyers can create an account from the cart to unlock a controlled $10 first-purchase credit on eligible orders of $25+.

Secure checkout powered by Stripe

Support

How to import this workflow into Make

  1. 1Purchase or download the workflow to get the Make blueprint JSON file.
  2. 2In Make, create a new scenario, click the three-dots menu, and choose "Import Blueprint".
  3. 3Reconnect each module to your own app connections when prompted.
  4. 4Run the scenario once to verify it, then set your schedule and turn it on.

Related Data Extraction workflows

More from Bruno Jonsson

Need this deployed? We'll set it up for you.

Our automation experts deploy this workflow in your stack, connect your accounts, and verify it works — or build a custom solution from scratch.