The interesting part is not the CLI. It’s the login flow.
Run explore login, approve it in the browser, and your agent gets authenticated access to the real app.
Not a toy sandbox.
Not a pasted API key.
Not some half-baked “AI feature”.
The actual app.
This is where software is going.
We’re moving from “has an API” to “an agent can actually use it properly”.
Auth inside the LLM workflow is a big part of that.
Once that clicks, the app stops being a website with endpoints and starts becoming a system an agent can work with directly.
That’s when it gets interesting.
Run explore login, approve it in the browser, and your agent gets authenticated access to the real app.
Not a toy sandbox.
Not a pasted API key.
Not some half-baked “AI feature”.
The actual app.
This is where software is going.
We’re moving from “has an API” to “an agent can actually use it properly”.
Auth inside the LLM workflow is a big part of that.
Once that clicks, the app stops being a website with endpoints and starts becoming a system an agent can work with directly.
That’s when it gets interesting.
