Vibeleaderboard
← All Intel
Intel / article

Spaces: A CLI Built for Humans and Agents

Source
mistral.ai
Date

Context

Mistral AI made its internal Spaces command-line tool usable by coding agents by giving interactive questions equivalent command-line inputs. The team describes an getting stuck at a visual component picker because it could not operate the menu. Supplying choices through flags allowed the same underlying project-creation logic to proceed. Its engineering account makes the failure and repair concrete.

Spaces also defines how unattended execution behaves: inputs resolve from supplied values or defaults, and missing information produces an error instead of an indefinite wait. The useful design principle is to expose required information explicitly, so software can operate a tool whose human interface still includes interactive prompts.

Terms in this piece · Glossary
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
  • MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
Key quotes

“Every prompt is a flag in disguise”

“There's an old saying that content is king. With agents, context is.”

“Implicit State is the Enemy”

“Designing for agents forced us to build a better tool for everyone.”

Recommended reads
Comments

Checking sign-in…

Loading comments…