← Back to portfolio

SK Telecom · Jan 2024 – Dec 2024

Movie Booking Agent (T Membership & A-dot)

Role · UX & LLM workflow design, RAG development

12%booking conversionT Membership movie booking · bookings / visitors
110Kcumulative usersmovie-booking agent
8,000MAUT Membership movie booking

01Background & Goals

  • A conversational agent for T Membership movie booking, meant to make getting recommendations, searching and booking as easy as talking to cinema staff.
  • The service combines chat with UI elements such as buttons, so the UI/UX and the LLM workflow had to flow into each other naturally.

02Key Challenges

  • C1 Slot filling through conversation, with personalization
  • C2 Integrating the UI/UX with the LLM workflow
  • C3 Movie search accuracy, latency and API cost

03Contributions

Slot-filling agentC1
  1. Designed a function-calling LLM workflow that informs the user while collecting what the booking needs
  2. Personalized recommendations using the user's location, recently visited cinemas and favorite theaters
  3. Added a state-management module so slots collected in long conversations are not lost
RAG for movie searchC3
  1. Preprocessing: tags movie titles in the request with a Trie built from a title-synonym dictionary
  2. Keyword extraction: uses the LLM to extract movie metadata and keywords from the request
  3. Retrieval: vector search with metadata filtering on the extracted keywords
  4. Final pick: uses the LLM to choose the movies that fit the request
Automated movie-metadata pipelineC3
  1. Extracted keywords, summaries and metadata from daily movie updates with Airflow, an LLM and preprocessing modules
  2. Converted the results to vectors and synced them to the vector DB
UI/UX and LLM workflow integrationC2
  1. Fed the results of UI actions (buttons, etc.) into the LLM workflow's prompt so both flow into each other naturally
Log-based data collection and trainingC3
  1. Collected training data from service logs and fine-tuned GPT models on Azure OpenAI to raise function-calling accuracy and multi-turn fluency

04Tech Stack

Framework / Platform
Azure OpenAI, Datadog, Airflow
Methodology
Prompt engineering, Function calling, RAG

05Results

  • 8,000 MAU for T Membership movie booking; 110K cumulative users of the movie-booking agent
  • 12% booking conversion (T Membership movie booking: completed bookings / visitors)

06Reference Material