How Deterministic Controls Turn AI Output Into Reliable Prompt Templates

Salesforce engineers let an AI agent draft prompt templates for administrators but gave it no power to save, publish or run them, so a person approves every change.

Salesforce, the business software company, sells Prompt Builder, a tool in which administrators write reusable instructions for its AI features. Vaibhav Raizada, a senior software engineer, and colleagues Kumar Kasimala and Ashish Gite built an AI agent that drafts these templates. They feared templates that looked correct but broke in use, so they split the work between the AI model and ordinary code.

• The AI model interprets the administrator's request and writes the text of the template.
• Ordinary code decides the routing, keeps record numbers intact and checks the output format, so the AI model cannot corrupt them.
• The agent shows its draft as a set of proposed changes, and accepting them updates only the draft in the editor.
• Saving is a separate action by the administrator, and the authors report drafts in under a minute against more than 25 minutes by hand.

A team can give an AI agent the language work and keep identifiers, formats and the final save in ordinary code and human hands. This is a vendor describing its own product, and the article gives no testing results.

Derived by Working Surface from the article; more in the Playbook. Source line: The agent could generate or refine a template, but it could never save, publish, or execute one.

2 October 2026: teams building with AI agents are deciding in advance, and writing down, where the agent stops and a person checks: in product code, in what the product promises users, and in visibility of agent behaviour.