2 posts tagged with "ai agents"

Anthropic recently published The AI-Native SDLC playbook, and it's the most concrete writeup I've seen discussing the effects of cheaper code generation on a delivery process, written by a company where AI authors 80% of merged code. If you run engineering at any scale, I suggest you read it.

It consists of six stages from Plan to Maintain that work in a loop rather than a linear chain of handoffs. Each stage commits an artifact that the next stage reads. The chain of commits is the audit trail. Humans stop reading every line and start judging intent and risk.

GitLab's CEO responded with the line that will likely outlive the playbook itself: "when implementation becomes abundant, trust becomes scarce."

Code is abundant now. Your data is not. An agent can regenerate your code in an afternoon, but it cannot regenerate the production state your company accumulated over years. The playbook's recovery model quietly assumes otherwise, which leads to our claim: the loop does not close at the database.

The database is the one stateful component in your infrastructure. It's where the history lives, and you cannot roll back history by redeploying an older version of it.

AI agents are becoming a core part of daily development. We utilize them to help us write code, fix syntax errors, and perform tasks that speed up routine work. However, when it comes to high-risk operations like database schema changes, we are more hesitant to hand off control.

If you're currently partaking in the online conversation around AI agents, you have likely seen many posts like this where an AI agent executed improper schema changes or, in the case of our vibe coder, deleted whole databases.

While the AI agent can generate migrations and provide suggestions, it’s important to ensure these operations are performed safely.

Atlas is a database schema management tool that ensures safe and reliable schema changes. Users define their schemas as code, and Atlas performs migrations based on changes to these code definitions. With Atlas, you can configure lint checks, pre-migration validations, and schema testing, making it an ideal counterpart for AI agents.

In this post, we'll show you how to configure popular AI agents to work with Atlas to ensure that schema changes made by the agent are secure.