Buyers ask whether a predictive database can hold up at SaaS scale. Here are the numbers from a 10-million-row invoice routing benchmark, run end-to-end through Aito's HTTP API the way production traffic actually hits it: low-hundreds-of-milliseconds predict latency, sub-linear scaling from 1k to 10M, and what the cold-start looks like before the cache warms.

A predictive database lets you query predictions (classifications, recommendations, missing values) from structured data, using the same query interface you use for data retrieval. No training step.

Databases are absorbing AI capabilities. A taxonomy of the four categories emerging in 2026: vector databases, ML-in-database platforms, LLM-augmented databases, and predictive databases.

Aito uses a layered system of Bayesian priors to make accurate predictions even when training data is sparse. This is how it works, why it matters for cold-start scenarios, and what the numbers look like.

We raised API limits by 25x on Dev and removed them entirely on Prod. The free Sandbox trial window is back to 30 days. Here is what changed and why.

Starting October 1, we’re updating our pricing and enhancing API access limits to continue delivering top-quality services. These changes reflect increased operational costs and our commitment to improving our platform. We appreciate your understanding and continued partnership.

Part 2 of ideas and examples of how Airtable can be a central tool for growing businesses.

Part 1 of ideas and examples of how Airtable can be a central tool for growing businesses.

What brains to add to your software robot - early 2022 edition.