Smith, Competency Framework Agent
A three-prompt pipeline I built that turns a job description into a role-based competency framework and exports it to Excel through Power Automate. L&D teams get a defensible competency model in minutes, where it used to take six weeks of expert workshops.
- Build time cut (6wk → 6min)
- 99.9%
- Match vs expert frameworks
- 85%
- Roles mapped in production
- 200+
Copilot Studio, Power Automate, Office Scripts, Excel
Building a competency framework from scratch is six weeks of expert workshops. With a job description, a competency dictionary, and the right pipeline, it takes six minutes. I built Smith as that pipeline.
What I built
Three prompts in sequence:
- Decompose:
- extract the actual work activities, responsibilities, and required outcomes from the JD
- Map:
- match each work activity to competencies from a curated competency dictionary
- 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.
What it improved
The architectural lesson here is that most useful enterprise AI is a chain of small, well-scoped prompts rather than one big model call, with each prompt doing something narrow and verifiable. When the chain breaks, you can see exactly which step broke, and when it works you have an artifact at the end that you can defend.
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. For this kind of work, I let the model do the structural drafting and leave the judgment calls to a person.
