All work
AI agents

Smith, Competency Framework Agent

A three-prompt pipeline I built that turns a job description into a complete role-based competency framework, exported to Excel via Power Automate. Designed so L&D teams can produce a defensible competency model in minutes instead of the six weeks of expert workshops it used to take.

Copilot StudioPower AutomateOffice ScriptsExcel
Outcomes
99.9%
Build time cut (6wk → 6min)
85%
Match vs expert frameworks
200+
Roles mapped in production

Building a competency framework from scratch is six weeks of expert workshops. Building one from a job description and a competency dictionary is six minutes, if you have a pipeline that knows what it’s doing. I built Smith as that pipeline.

What I built

Three prompts in sequence:

  1. Decompose, extract the actual work activities, responsibilities, and required outcomes from the JD
  2. Map, match each work activity to competencies from a curated competency dictionary
  3. Calibrate, assign proficiency levels (Awareness / Working / Practitioner / Expert) based on seniority and scope

The output drops straight into a structured Excel workbook via Power Automate, formatted to match the L&D team’s existing template. No retyping, no reformatting, no manual matching.

What it improved

The architectural lesson here is that most useful enterprise AI is not one big model call. It’s a chain of small, well-scoped prompts where each one does something narrow and verifiable. When the chain breaks, you can see exactly which step broke. When it works, you have a defensible artifact at the end, not a black-box answer.

In production use, Smith has mapped 200+ roles and matches expert-built frameworks at around 85% on first pass, with the remaining 15% adjusted by a human reviewer in minutes rather than weeks. That’s the right division of labour for this kind of work: model does the structural drafting, human does the judgement calls.