# How Respan is scaling LLM observability with ClickHouse Cloud

DevFeed: [How Respan is scaling LLM observability with ClickHouse Cloud](<https://devfeed.tech/articles/how-respan-is-scaling-llm-observability-with-clickhouse-cloud-5550.md>)

Original publisher: [Read original article](<https://clickhouse.com/blog/respan-ai-llm-observability>)

Author: ClickHouse

Published: 2026-04-06T15:11:14Z

Content type: article

Language: en

Sources: [ClickHouse Blog](<https://devfeed.tech/sources/clickhouse-blog.md>)

Topics: [clickhouse](<https://devfeed.tech/topics/clickhouse.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>), [Back end](<https://devfeed.tech/topics/backend.md>), [data](<https://devfeed.tech/topics/data.md>), [Django](<https://devfeed.tech/topics/django.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [app](<https://devfeed.tech/tags/app.md>), [backend](<https://devfeed.tech/tags/backend.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [django](<https://devfeed.tech/tags/django.md>), [llm](<https://devfeed.tech/tags/llm.md>), [logging](<https://devfeed.tech/tags/logging.md>), [observability](<https://devfeed.tech/tags/observability.md>), [performance](<https://devfeed.tech/tags/performance.md>), [platform](<https://devfeed.tech/tags/platform.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [scale](<https://devfeed.tech/tags/scale.md>), [startup](<https://devfeed.tech/tags/startup.md>)

## AI overview

Respan migrated its high-throughput LLM observability ingestion and analytics from Postgres to ClickHouse Cloud after reaching 50-100 writes per second. Incremental materialized views and trace aggregations support fast dashboards as observability data grows to billions of rows and about 50 million events per day.

## Source excerpt

Respan AI uses ClickHouse Cloud to power high-throughput LLM observability across 50 million daily events. After outgrowing Postgres at 50-100 writes per second, the team migrated ingestion and analytics to ClickHouse Cloud. Incremental materialized views