The agent generates and validates outcome-focused OKR sets using Christina Wodtke's Radical Focus methodology. It produces inspirational objectives with measurable key results, applies counter-metric tests, and scores quality against proven criteria.
okr_validator.py scores sets and flags disguised tasks, missing metrics, output-framed KRs, and missing counter-metricsBefore generating the OKR sets, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.
python3 project-management/execution/brainstorm-okrs/scripts/okr_validator.py \
--input project-management/execution/brainstorm-okrs/assets/sample_okrs_clean.json
--threshold N changes the bar; --format json for pipelines; --demo runs the built-in mix.
Exit codes: 0 every set scores at or above the threshold, 1 at least one below (assets/sample_okrs.json exits 1 by design: "Increase revenue by 25%" with two task KRs scores 75), 2 missing file, invalid JSON or wrong shape.
Mistake: Every KR is one the team is 95-100% sure to hit, such as a 4% MRR lift that would happen anyway.
Why it happens: A green scorecard at quarter end feels safer than a visible miss.
Instead: Set targets at 60-70% confidence and ask the team for its confidence number on each KR. A hit rate above 90% sustained over three quarters means the bar is too low.
Mistake: In week 8 a KR is behind, so the team cuts the target from 35% to 20% and reports it green.
Why it happens: A red KR feels like failure in front of leadership.
Instead: Keep the week-1 targets. Mark the KR red, look for what would close the gap, and if nothing realistic will, record the miss and its cause in the retrospective.
Mistake: The OKR has five KRs, each "Ship X" for a planned roadmap item.
Why it happens: The roadmap already exists, and copying it skips the hard choice of what to focus on.
Instead: Keep three KRs per Objective (primary, secondary dimension, counter-metric) that measure change for customers or the business. List supporting initiatives separately. More than 4 KRs on one Objective is a flag.
Nine more, each with a bad and a good example: references/red-flags.md.
| File | Purpose |
|---|---|
scripts/okr_validator.py | Structural OKR scorer and gate |
assets/sample_okrs.json | Three sets incl. a flawed one (exit 1) |
assets/sample_okrs_clean.json | Two strong sets (exit 0) |
assets/okr_template.md | OKR document and quarterly review template |
examples/q3-okrs-shared-dashboards-launch.md | Worked quarter |
okr_validator.py flag + JSON-schema reference. Read when generating OKRs or wiring up the validator.In Scope:
Out of Scope:
senior-pm/ for portfolio alignment)Important Caveats:
| Integration | Direction | Description |
|---|---|---|
scrum-master/ | Receives from | Sprint velocity and capacity data inform realistic KR target-setting |
senior-pm/ | Receives from | Portfolio strategic priorities shape quarterly OKR themes |
execution/outcome-roadmap/ | Feeds into | OKR key results become success metrics for roadmap Now/Next items |
execution/prioritization-frameworks/ | Complements | Prioritized initiatives inform which OKR theme to focus on |
discovery/identify-assumptions/ | Receives from | Validated assumptions increase confidence in OKR target feasibility |
discovery/brainstorm-experiments/ | Feeds into | Experiment metrics may become OKR key results when validated |