← Multimodal Sources 🕐 2 min read
Multimodal Sources

Zapia solving "real world tasks" for millions with Google Cloud and Gemini

> We're using it for everything. We're running things on cloud run.

Show: Google Cloud Next · Publisher: Google Cloud · Host: Google Cloud editorial

Episode URL: https://www.youtube.com/watch?v=xT11wgQMPMY

Publish date: 2026-04-14
Duration: 151.0s
Default source credibility: MEDIUM — Vendor conference — Google keynotes and product launches are marketing (LOW for claims about own products). Named F500 customer talks with production metrics stay HIGH. Filter aggressively for customer sessions with named speakers and quantified outcomes; skip product demos and partner pitches.

  • Zapia uses Google Cloud and Gemini models to solve real-world tasks for millions of users.
  • The system was designed to scale from the start, handling millions of users with various models based on task complexity.
  • User satisfaction with Zapia’s service is consistently high, with over 92% of users rating conversations positively.

Extracted quotes

# Credibility Speaker Org Timestamp Topic Quote
1 MEDIUM Nicholas Lo (CTO) Zapia 1:03 02-corporate-tools We’re using it for everything. We’re running things on cloud run. From the start we designed the system even when we had 10 users that so that it could scale to millions of users which is what we have right now.
2 MEDIUM Nicholas Lo (CTO) Zapia 1:53 07-adoption-challenges We ask users to rate conversations as good or bad and consistently things have been improving and we are over 92% at this point of people being happy with the service that is provided.

Per-quote detail

1. Nicholas Lo — Zapia (1:03)

We’re using it for everything. We’re running things on cloud run. From the start we designed the system even when we had 10 users that so that it could scale to millions of users which is what we have right now.

  • Credibility: MEDIUM — Named exec with specific claim about scaling, but vendor context.
  • Topic tag: 02-corporate-tools

2. Nicholas Lo — Zapia (1:53)

We ask users to rate conversations as good or bad and consistently things have been improving and we are over 92% at this point of people being happy with the service that is provided.

  • Stat: 92% of users are happy with the service, measured by user ratings.
  • Credibility: MEDIUM — Named exec with specific metric, but vendor context.
  • Topic tag: 07-adoption-challenges

Extracted 2026-04-14T12:54:37 via scripts/podcast_mine.py (MLX mlx-community/Qwen2.5-32B-Instruct-4bit).