---
id: "action-develop-specification-skills"
type: "action-item"
source_timestamps: ["00:10:15", "00:10:30"]
tags: ["upskilling", "management"]
related: ["concept-non-technical-engineering"]
action: "Train teams to write strict specifications and evaluation metrics for agentic workflows."
outcome: "Ability to effectively manage and scale output from autonomous AI agents."
speakers: ["Nate B. Jones"]
sources: ["s35-compounding-gap"]
sourceVaultSlug: "s35-compounding-gap"
originDay: 35
---
# Develop Specification and Evaluation Skills

## Action: Develop Specification and Evaluation Skills

**Action**: Train teams — including non-technical workers — to write strict specifications and evaluation metrics for agentic workflows.

**Expected outcome**: Ability to effectively manage and scale output from autonomous AI agents.

### Why this matters
Non-technical workers must learn to:

- Write **crisp requirements**
- Define **success metrics**
- Build **evaluation harnesses**
- Manage **agent throughput**

Without these skills, workers cannot effectively direct AI agents and will be displaced by colleagues who can.

### Underlying argument
This action operationalizes [[concept-non-technical-engineering]] and is the practical response to [[contrarian-non-technical-becomes-technical]].

### Prerequisites
Familiarity with software engineering paradigms helps — see [[prereq-software-engineering-paradigms]].