What challenges did OTTO face before AI implementation?

Turn list-based search into a true conversational, expert-advisory voice shopping experience with low latency and reliable guardrails during multi-turn interactions.

What was the impact of the AI solution?

Cut voice response latency from about 8-9 seconds to under 2 seconds. First EMEA retailer with native voice shopping live in production. Scaled expert product advisory from 5 to 50 categories and expanding. Open beta results showed voice sessions capture more customer context than typed chat.

Source

GCPProductionEvidence: Medium65/100

OTTO voice shopping assistant with Gemini Enterprise and Gemini Live API

Use case typeVoice automationUpdated Jul 1, 2026

OTTO built a conversational voice shopping assistant to turn retail search into expert advisory dialogue. The assistant supports real-time, multi-turn voice interactions for shopping advice and product discovery.

AI-generated summary. Generated from indexed evidence or computed site data. Underlying records pass applicable deterministic checks; verify important details with source links where available. How content is created.

Organization: OTTO
Industry: Retail
Location: Germany
Published: July 2026

Reported outcomes

Voice response latency: 8–9 seconds to under 2 seconds

Time & speed

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Voice response latency: 8-9 seconds to under 2 seconds decrease

Google Cloud Customer StoryJul 1, 2026Customer storyInferred claimMedium evidence strength

End-to-end latency dropped from 8–9 seconds to under two.

Normalized claim

Product categories covered: 1,000% increase

Google Cloud Customer StoryJul 1, 2026Customer storyInferred claimMedium evidence strength

The advisory pattern itself scales. OTTO began with five product base classes hand-crafted alongside category experts, then used Gemini to extend the same structure to fifty more, with the next wave covering the full catalog now in progres...

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: OTTO
Provider: GCP
Maturity: Production
Linked source: Google Cloud Customer Story

First EMEA retailer with native voice shopping live in production

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 2 of 2

1Voice automation
2Customer service agent

Built a text assistant first, then migrated the voice path to Gemini Live's native audio model for real-time turn-by-turn conversation.
Implemented an internal orchestration layer based on Petri nets to keep critical guardrails intact mid-flow.
Used hybrid lexical and vector retrieval followed by a Gemini 2.5 Flash validation pass for subjective requests.

Technologies

Gemini Enterprise Agent Platform Gemini Live API Gemini 2.5 Flash Chirp 3

Cut voice response latency from about 8-9 seconds to under 2 seconds.
First EMEA retailer with native voice shopping live in production.
Scaled expert product advisory from 5 to 50 categories and expanding.
Open beta results showed voice sessions capture more customer context than typed chat.

Architecture

OTTO built the assistant on Gemini Enterprise Agent Platform. The voice path uses Gemini Live API with native audio while a separate text assistant continues to drive guardrails, recommendations, and search. Chirp 3 handles German speech recognition. A custom internal orchestration layer based on Petri nets coordinates the conversation flow and preserves guardrails. Hybrid lexical and vector retrieval is followed by a Gemini 2.5 Flash validation pass for subjective requests.

Sources & evidence1

Evidence: Medium65/100Evidence strength