Summary

Simon Späti argues that local-first, developer-friendly tools like MotherDuck (serverless DuckDB) and Rill (BI-as-code) are naturally suited for AI agent workflows because what's readable by developers is also readable by agents. He demonstrates how declarative YAML dashboards, SQL-based metrics layers, and CLI-first workflows create an architecture where agents can read, reason about, and build analytics autonomously. The post walks through three practical examples including Stack Overflow survey analytics and multi-cloud cost analysis. Späti contends that dashboards won't disappear but will coexist with conversational BI, and that the key enabler is having semantic context defined as code. He acknowledges limitations around natural language ambiguity and the tension between AI's non-determinism and data's need for reproducibility.

Key Insight

The most agent-friendly analytics architecture turns out to be the one built on old principles — local-first, text-based, SQL-defined, and version-controlled — because tools designed for developer simplicity naturally provide the readable context that AI agents need.

Spicy Quotes (click to share)

• 3

  What is developer-friendly is also agent-friendly, with the needs of readable code, fast engines, and deterministic semantics.

• 5

  The 'small data' thesis didn't anticipate the AI agent revolution, but it created the conditions for it: when your data fits on a laptop and your dashboards are YAML files, an AI agent can read, reason about, and act on your entire analytics stack.

• 5

  If you feed any AI agent with a mess, you're going to end up with an even bigger mess.

• 6

  The irony is that going back to local-first, text-based, SQL-defined analytics turns out to be the most forward-looking architecture. And dashboards become agents when they're written as code.

• 5

  Instead of hiding business logic in a proprietary GUI that only humans can click through, you make it readable code that anyone, or anything, can openly read and reason about.

• 3

  Context is king for the near future. Everything that can be locally defined, such as Rill's metrics layer and dashboards, will be so much faster and better built with agents.

• 4

  The challenge with data exploration is not that people don't have the ability to manipulate data; it's that they don't know what they're looking for.

Tone

optimistic, technical, promotional