Skip to content

AI customer assistant for an OTT platform

Designed and shipped a retrieval-augmented AI assistant grounded in subscriber and content data — deflecting 62% of tier-1 tickets.

Client
Streaming OTT provider
Name withheld under NDA
Industry
Media
Year
2024
Capabilities
AI, RAG, LLM, Vector DB
  • 62% ticket deflection
  • 4.6/5 CSAT
  • $4.2M annual savings

Overview

We designed and shipped a production retrieval-augmented AI assistant for a streaming provider — grounded in subscriber, billing, and content data — that resolves the majority of tier-1 support queries autonomously, with evaluation, guardrails, and cost controls built in.

The challenge

The OTT provider’s support costs were ballooning as the subscriber base scaled, and customers were frustrated by slow, repetitive tier-1 responses. Off-the-shelf chatbots hallucinated and could not access real account context.

Our approach

We built a RAG pipeline over the provider’s knowledge base and account systems, with a vector store for retrieval, strict grounding guardrails, and an evaluation harness to measure accuracy before every release. Human handoff was designed in for the cases the assistant should not handle.

Outcomes

  • 62% of tier-1 tickets deflected
  • 4.6/5 customer satisfaction on AI chats
  • $4.2M estimated annual savings
  • Faster resolution for subscribers

Tell us what you’re building.

A senior lead reads every message and replies within one business day — with questions, a first view of the approach, and an honest sense of cost.