Meet Slate.

When should I use slate?

Our early users see notable improvements when using slate primarily when using it for more involved tasks like:

• Codebase deep research
• Full feature additions
• Large scale migrations or refactors
• Lower level programming (e.g. rust)
• Debugging systems
• etc.

We built slate to autonomously work in production codebases. In pursuit of this, we made sure slate can:

• Work reliably with you for hours (8+)
• Understand large codebases (1M lines+, yes this is tested lol)
• Handle interconnected systems
• Exit vim, unlike you! (probably)
• etc.

Slate should be used as an agent, not an api call. This means that slate perfoms best when allowed to manage its own context. You can use it like you would Cursor or Claude code, but we would not recommend it.

This version of slate is available through our cli. For more information on how to use slate, check out our docs!

So when should I not use slate?

• You do not trust llm based systems to be autonomous
• You do not care much about the quality of the output
• You do not work with agents for long periods of time
• You believe agents require every piece of context and that you need pack the context window
• You are not solving *engineering* problems (you know who you are)

In any of these cases, you will likely treat it like an API call which is not our goal with Slate and you will not see mindblowingly good results (yet). Slate is *not* like most agents in that it has been designed to have a high level of autonomy and variability in the frontier of tasks it solves.