Allie Miller Details 34-Agent AI Workforce Architecture and Prompt Tips
alliekmiller · x · 2026-08-13
In a recent AI Agent Workshop, Allie K. Miller shared how she built and runs an AI workforce of 34 agents. She emphasizes that the core is building a system, not just writing prompts. Her architecture includes an 'AI chief of staff' that routes all tasks (the only agent she interacts with directly), six 'director' agents managing different business lines, and numerous temporary task-specific agents, enabling her to run multiple parallel workstreams.
She also shared her favorite highly efficient two-word prompts:
- now what: Used after wrapping up a project to get AI suggestions for the next steps.
- plz fix: Accompanied by a screenshot to quickly have AI identify and fix errors or bugs.
- do this: Used with a photo or screenshot to have AI extract information or implement a specific task.
More from coding & agent
- Conway's Law for DevTools: High-Quality Internal Tools Breed High-Quality External Products — alex_frantic · 2026-08-13
- First-Person Blender Control: MCP Shows 3D Interaction Potential — XRarchitect · 2026-08-13
- Building Specialized AI Harnesses: The Core Software Engineering Challenge of the Decade — bendee983 · 2026-08-13
- Fable AI Agent Review: Powerful for Complex Prod Operations but Plagued by Downtime — generativist · 2026-08-13
- GBrain v0.45 Released: Adds 17 New Skills for Personal AI Agents — garrytan · 2026-08-13
- Cursor UX Orders of Magnitude Better Than Codex and Claude Code, But Pricey — jacob_posel · 2026-08-13