# How we're building a data platform for a new user: agents

DevFeed: [How we're building a data platform for a new user: agents](<https://devfeed.tech/articles/how-we-re-building-a-data-platform-for-a-new-user-agents-5002.md>)

Original publisher: [Read original article](<https://clickhouse.com/blog/building-a-data-platform-for-agents>)

Author: Al Brown

Published: 2026-03-27T00:00:00Z

Content type: article

Language: en

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

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [llm](<https://devfeed.tech/tags/llm.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [observability](<https://devfeed.tech/tags/observability.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [sql](<https://devfeed.tech/tags/sql.md>)

## AI overview

The article presents an agentic analytics data platform in which AI agents explore schemas, generate and run SQL, and iterate on query results. Its reference architecture combines LibreChat, ClickHouse with MCP, and Langfuse for LLM observability.

## Source excerpt

Agents need real-time ingestion, fast aggregation, flexible handling of semi-structured events, low-latency concurrency, and economics that still work at massive scale. ClickHouse already has this foundation