---
title: "Engineering Multi-Agent AI Teams That Build and Test Themselves"
description: "Salesforce Marketing Cloud’s AI Delivery Lead Sohini Arya and team built Agent Designer, a system that automates the creation and testing of multi-agent AI teams. The orchestrator cannot write agent files itself; instead, seven specialist agents analyze architecture, failure modes, and compliance before the orchestrator synthesizes findings for human review. The system transforms an engineer’s request into a tested multi-agent team in 15-30 minutes, down from 2-4 hours manually, and helped approximately 200 engineers adopt the manager-of-agents model. Governance challenges included enforcing write-scope boundaries via prompts, reconciling independently produced design conflicts, and applying topology-specific budget formulas that account for flat, swarm, or team structures. Verifier agents return structured PASS/WARN/FAIL blocks, and self-healing is limited to two fix attempts and a $3 ceiling to prevent runaway repairs, with the orchestrator’s 500-turn budget divided across analysis, approval, generation, testing, and retries."
---

# Engineering Multi-Agent AI Teams That Build and Test Themselves

[Salesforce](https://yomu.fyi/company/salesforce) · Scott Nyberg · Sep 28, 2026

**Type:** Problem & solution

## Summary

Salesforce Marketing Cloud’s AI Delivery Lead Sohini Arya and team built Agent Designer, a system that automates the creation and testing of multi-agent AI teams. The orchestrator cannot write agent files itself; instead, seven specialist agents analyze architecture, failure modes, and compliance before the orchestrator synthesizes findings for human review. The system transforms an engineer’s request into a tested multi-agent team in 15-30 minutes, down from 2-4 hours manually, and helped approximately 200 engineers adopt the manager-of-agents model. Governance challenges included enforcing write-scope boundaries via prompts, reconciling independently produced design conflicts, and applying topology-specific budget formulas that account for flat, swarm, or team structures. Verifier agents return structured PASS/WARN/FAIL blocks, and self-healing is limited to two fix attempts and a $3 ceiling to prevent runaway repairs, with the orchestrator’s 500-turn budget divided across analysis, approval, generation, testing, and retries.

## Context

Salesforce Marketing Cloud’s AI Delivery Lead describes how her team built Agent Designer to automate multi-agent AI team design and testing, addressing governance, verification, and self-healing challenges.

## Approach / What changed

Agent Designer uses an orchestrator and seven specialist agents to analyze architecture, failure modes, and compliance; synthesizes findings for human approval; then generates and tests agent files with bounded self-healing. It enforces write-scope via prompts, uses structured verifier output, and applies topology-specific budget formulas.

## Takeaways

- Agent Designer reduces multi-agent team creation from 2-4 hours to 15-30 minutes by automating file generation, testing, and repair, with the orchestrator prohibited from writing agent files itself.
- Governance is enforced through write-scope boundaries in prompts, topology-specific budget formulas (flat, swarm, team), and structured PASS/WARN/FAIL verifier output to prevent false approvals.
- Self-healing is limited to two fix attempts and a $3 spending ceiling, with the test doctor classifying failures into categories like violations, tool errors, and soft failures to avoid misdiagnosis.

## FAQ

### How does Agent Designer enforce write-scope across agents?

Since the agent specification lacked a native write-scope field, the team enforced each member's write boundaries within its prompt, creating deterministic boundaries that prevent agents from modifying overlapping artifacts or assuming unassigned authority.

### How are budget limits calculated for different multi-agent architectures?

Agent Designer stores budgets, turn limits, and cost ceilings in one config file and applies topology-specific formulas: flat check for single agent, items × cost × steps for swarm, whole-roster ceilings for team. The orchestrator's 500-turn budget is divided across phases.

### How does Agent Designer prevent verifier agents from approving wrong designs?

Verifiers return structured PASS/WARN/FAIL blocks instead of free-form text, with rules like 'warn rather than fail when uncertain'. The orchestrator performs a meta-check across verifier outputs to determine agreement and correctness.

**Tags:** [AI Agents](https://yomu.fyi/topic/ai-agents), [AI Governance](https://yomu.fyi/topic/ai-governance), [Automation](https://yomu.fyi/topic/automation), [Testing](https://yomu.fyi/topic/testing)

- Source: [Salesforce](https://engineering.salesforce.com/engineering-multi-agent-ai-teams-that-build-and-test-themselves)
- Source URL: https://engineering.salesforce.com/engineering-multi-agent-ai-teams-that-build-and-test-themselves
- Ingested by Yomu: 2026-09-28T21:00:10.929Z

[Read original post](https://engineering.salesforce.com/engineering-multi-agent-ai-teams-that-build-and-test-themselves)