Engineering Multi-Agent AI Teams That Build and Test Themselves

A Salesforce team built AI agents that design and test teams of other agents, aiming to cut hours to minutes, with an engineer approving every design.

Engineers in Marketing Cloud, the marketing software business of Salesforce, spent two to four hours building and testing each team of cooperating AI agents by hand. Sohini Arya, who leads AI delivery for Marketing Cloud, describes Agent Designer, a system her team built in which AI agents do that work instead. The goal was a tested team in 15 to 30 minutes, with an engineer approving each design before any file is written.

• A coordinating agent directs seven specialist agents, which analyse the design, write and check the files, and run a test. The coordinating agent is not allowed to write any agent file itself.
• Agents that check other agents' work must answer pass, warn or fail in a fixed format. The coordinating agent compares their answers before a design goes further.
• Automatic repair of a failing agent team stops after two attempts or $3 of spending, and the problem then goes to an engineer.
• The post says the system helped about 200 Marketing Cloud engineers begin working as managers of AI agents.

An engineering team that lets AI agents repair their own work can set a hard limit on attempts and spending, after which a person takes over. This is Salesforce's account of its own internal tool, and the wider application is an inference.

Derived by Working Surface from the article. Source line: The team limited the self-healing process to two fix attempts and a $3 spending ceiling.

28 September 2026: when agents build, people keep the first screen, the review, the files agents read and the whole product.