Log Evidence

• Who did you talk to? (role and context, not name -- privacy)
• What did you learn? (open-ended first, let them tell the story)
• Any direct quotes worth capturing?
• Anything surprising or contradicting our current assumptions?
• JTBD signals: functional job, emotional job, social job?
• Any follow-up conversations needed?

Task Cancellation

If the user reports a task couldn't be completed (contact unavailable, timing didn't work, etc.):

1. Ask: "Should we cancel this task or reschedule it?"

2. If cancel: move to completed_tasks with source_class: cancelled and a note explaining why

3. If reschedule: update the task's objective or target_persona if needed, keep in pending_tasks

4. Either way: "The evidence gap still exists. Consider /handoff to plan an alternative approach."

5. Check for contradictions:

   • Compare findings against existing canvas data
   • If findings contradict assumptions: flag clearly
     • "This contradicts [canvas section / assumption]. The user said [X] but we assumed [Y]."
     • Suggest: "Consider running /devils-advocate to stress-test this assumption, or update the canvas with /canvas-update."
   • If findings support assumptions: note the confirmation
     • "This supports [canvas section]. Confidence for [item] can increase."

6. Recalculate confidence:

   • Show before/after: "Diamond confidence: 0.45 -> 0.52 (added 1 external_human source)"
   • If this was the first external evidence: "First external human voice recorded. Evidence ratio improved from 0% to [X]%."

7. Suggest next steps:

   • If more conversations needed: "One conversation is a start. Consider /handoff for 1-2 more to reach triangulation."
   • If enough evidence: "Evidence looks solid for /diamond-progress to attempt the next transition."
   • If contradictions found: "Before progressing, resolve the contradiction. Run /devils-advocate or revisit the canvas."

Canvas Output

• Updates: relevant canvas file provenance (evidence_sources, source_classes, evidence_type, confidence)
• Updates: canvas/human-tasks.yml (moves task to completed)
• May update: canvas/opportunities.yml, canvas/user-needs.yml, canvas/jobs-to-be-done.yml depending on findings

Theory Citations

• Torres (CDH): Triangulation requirement (3+ sources for data-supported)
• Gilad (Evidence-Guided): Confidence ladder classification
• Christensen (JTBD): Functional/emotional/social capture structure
• Argyris (Double-Loop): Contradiction detection triggers assumption questioning