training
Should you take that $4,000 ML systems course? The Coursera specialization? The expensive AWS certification? training mode scores a learning investment against your stated career direction and surfaces the actual return on time and money.
What it does
The training mode reads the course or certification details (syllabus, time commitment, cost), reads your North Star section from config/profile.yml, and scores the investment against three dimensions: skill gap closure, signal value for target roles, and opportunity cost.
When to use it
Use training when you are tempted by a learning offering but unsure if it actually moves you toward your stated direction. Particularly useful for expensive certifications and bootcamps.
Example
`/career-ops training` + course name and URL — output is a scored evaluation with recommendation.What a run looks like
A training run scores a course or certification across six dimensions and returns one of three verdicts, so you see the return on time and money before you commit to either. You give it the offering — syllabus, weeks, hours per week, and cost — and it grades that against your stated career direction.
Training Evaluation — "Production LLM Systems" (8 weeks, 6 h/wk, $1,200)
North Star alignment Moves toward the Applied AI target
Recruiter signal HMs read this as production-grade, not tutorial
Time and effort 8 weeks x 6 h = 48 h
Opportunity cost ~2 portfolio projects foregone
Risks Syllabus current; brand is mid-tier
Portfolio deliverable Yes -- a graded eval harness
Verdict: DO WITH TIMEBOX (max 6 weeks)
Condensed plan, essentials only, weekly scoreboardA DO verdict comes with a four-to-twelve-week plan with weekly deliverables and a scoreboard. A DON'T DO verdict names a better alternative and explains why. DO WITH TIMEBOX caps the weeks and strips the plan to essentials, which is the common outcome for courses that are useful but padded.
What scores highest
The mode weights offerings that build credibility in production-grade AI over generic credentials. In priority order, that means LLM evaluation and testing, observability and monitoring, cost and reliability trade-offs, AI governance and safety, and enterprise AI architecture. A course that ends in a demonstrable artifact — an eval harness, a monitored deployment — outscores one that ends in a certificate alone, because the artifact is what a hiring manager can actually see.
Gotchas
The mode is biased toward your stated North Star. If you have not filled in config/profile.yml's North Star section thoughtfully, the evaluation will be shallow.
Related
Generates a tailored PDF resume against a specific JD using Playwright to render markdown through a clean typographic template. The output is structurally simple — no tables, no columns, no graphics — exactly what ATS parsers handle reliably.
project
Builders accumulate ideas faster than they can ship. project mode scores a portfolio project idea against your target roles, your existing portfolio, and the time investment, surfacing whether it is worth building.