name: brainstorm-okrs description: > OKR brainstorming and validation using the Radical Focus framework. Generates outcome-focused objectives with measurable key results and counter-metrics. Use when setting quarterly OKRs, validating existing OKRs against quality criteria, aligning team goals to company objectives, or teaching teams the difference between outputs and outcomes in goal-setting. license: MIT + Commons Clause metadata: version: 1.0.0 author: borghei category: project-management domain: pm-execution updated: 2026-03-04 python-tools: okr_validator.py tech-stack: okr, radical-focus, goal-setting, strategic-planning

OKR Brainstorming Expert

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.

Workflow

1. Identify the Theme

The agent asks: "What is the single most important thing this team needs to change this quarter?" The answer becomes the theme. Every OKR must connect back to this theme.

Validation checkpoint: If the user provides more than one theme, the agent pushes back. One theme per team per quarter. Multiple themes means no focus.

2. Generate 3 Distinct OKR Sets

For each set, the agent produces:

1. Objective -- One qualitative, inspirational statement (no numbers)
2. Key Result 1 -- Primary metric proving progress
3. Key Result 2 -- Secondary metric capturing a different dimension
4. Key Result 3 -- Counter-metric preventing gaming of KR1 and KR2
5. Rationale -- 2-3 sentences on why this set matters and how it connects to the theme

Objective quality criteria:

• Qualitative (numbers belong in key results)
• Inspirational (team would be excited to achieve it)
• Time-bound (achievable within one quarter)
• Actionable (team can directly influence the outcome)

Key result quality criteria:

• Measurable (has a metric with a number)
• Outcome-focused (measures results, not activities)
• Set at 60-70% confidence (not sandbagging, not demoralizing)
• Limited to 3 per objective

3. Apply the Counter-Metric Test

For every pair of key results, the agent asks: "Could we hit these numbers by doing something harmful?" If yes, it adds a counter-metric.

Example: If KR1 is "Increase sign-ups by 40%", a counter-metric is "Maintain activation rate above 60%." Without it, the team could game KR1 by lowering sign-up barriers so far that unqualified users flood in.

4. Validate with Tool

python scripts/okr_validator.py --input okrs.json

The validator scores each OKR set and surfaces quality issues: disguised tasks, missing metrics, output-framed key results, or missing counter-metrics.

Validation checkpoint: Any OKR set scoring below 70% must be revised before committing.

Example: Quarterly OKR Generation

Input: Theme is "retention" for a SaaS product team.

Output:

OKR Set 1:
  Objective: "Become the product teams can't imagine leaving"
  KR1: Reduce monthly churn from 4.2% to 2.5%
  KR2: Increase 90-day retention cohort from 68% to 82%
  KR3 (counter): Maintain NPS score above 45 (prevent forced lock-in tactics)
  Rationale: Churn is the top revenue leak. Improving retention directly
  increases LTV and reduces pressure on acquisition spend.

OKR Set 2:
  Objective: "Make our onboarding so good that users hit value in their first session"
  KR1: Increase Day-1 activation rate from 34% to 55%
  KR2: Reduce time-to-first-value from 12 minutes to under 4 minutes
  KR3 (counter): Maintain support ticket volume below 200/week (don't hide complexity)
  Rationale: Users who activate on Day 1 retain at 3x the rate. Onboarding
  is the highest-leverage retention lever.

OKR Set 3:
  Objective: "Turn our power users into vocal advocates"
  KR1: Increase referral-sourced signups from 8% to 20% of new users
  KR2: Grow active community members from 500 to 2,000
  KR3 (counter): Maintain power user retention above 95% (don't distract them)
  Rationale: Advocacy compounds. Referred users have 37% higher retention
  than paid-acquisition users.

$ python scripts/okr_validator.py --input okrs.json

OKR Validation Results
======================
Set 1: 92/100 - PASS
  Objective: Qualitative, inspirational, time-bound
  KR1: Measurable, outcome-focused, stretch target
  KR2: Measurable, different dimension from KR1
  KR3: Valid counter-metric for churn reduction

Set 2: 88/100 - PASS
  Objective: Qualitative, inspirational, time-bound
  KR1: Measurable, outcome-focused
  KR2: Measurable, tracks different dimension
  KR3: Valid counter-metric
  Note: "under 4 minutes" - verify baseline measurement exists

Set 3: 85/100 - PASS
  Objective: Qualitative, inspirational
  KR1: Measurable, outcome-focused
  KR2: Measurable, but "active" needs precise definition
  KR3: Valid counter-metric

Common OKR Mistakes

OKRs vs KPIs vs North Star Metric

Relationship: OKRs are the lever pulled to move KPIs toward the North Star Metric. KPIs indicate business health. The NSM indicates core value delivery. OKRs define what changes this quarter.

Tools

Troubleshooting

Success Criteria

• Each OKR set scores above 80/100 on the validator before committing to the quarter
• Maximum 1-2 objectives per team per quarter (focus over breadth)
• Every objective is qualitative and inspirational (no numbers in the objective itself)
• Each objective has exactly 3 key results: primary metric, secondary dimension, and counter-metric
• Key results are set at 60-70% confidence (stretch, not sandbagged)
• Weekly confidence check-ins are conducted, not just end-of-quarter reviews
• OKR retrospectives run at quarter end with structured review of what was learned

Scope & Limitations

In Scope:

• OKR brainstorming using Christina Wodtke's Radical Focus methodology
• Generating 3 distinct OKR sets per theme with counter-metric testing
• Automated validation and scoring of OKR quality (output detection, metric presence, structural checks)
• Guidance on OKR vs. KPI vs. North Star Metric distinctions
• Common OKR mistake identification and remediation

Out of Scope:

• OKR tracking and progress monitoring over the quarter (use dedicated OKR platforms)
• Company-level OKR cascade and alignment across teams (see senior-pm/ for portfolio alignment)
• Individual performance-linked OKRs (OKRs should be team goals, not performance reviews)
• Metric instrumentation or analytics setup for measuring key results

Important Caveats:

• OKRs work best when combined with weekly check-ins. Teams that review OKRs only at quarter end see 30-45% lower completion rates.
• The validator catches structural issues but cannot assess strategic quality. A perfectly scored OKR can still be the wrong goal.
• OKRs should be aligned top-down (strategic direction) and bottom-up (team insight). Pure top-down OKRs reduce team ownership.

Integration Points

Tool Reference

okr_validator.py

Validates and scores OKR sets against quality criteria. Checks objectives for qualitative/inspirational language, key results for measurable outcomes, and structural completeness.

Input JSON schema:

{
  "okr_sets": [
    {
      "objective": "string (qualitative, no numbers)",
      "key_results": [
        {
          "description": "string",
          "metric": "string (unit of measurement)",
          "target_value": "number",
          "current_value": "number (baseline)"
        }
      ]
    }
  ]
}

References

• references/okr-best-practices.md -- Detailed OKR guide with examples and anti-patterns
• assets/okr_template.md -- OKR document template and quarterly review format