AI governance prospect from enquiry to discovery call

Elite LLM Handoff

Explain the protect_revenue recommendation using the governed Fortress output and caveats.

governed_handoff:
  - Goal: protect_revenue
  - Primary path: meeting_booked, score 0.5001, high confidence
  - Supporting signals: ai_governance, delivery_page, email_enquiry, meeting_booked
  - Runtime relationship sets returned: 8
  - Domain journeys: 120; events: 600; relationship sets: 120

Outcome Prompt JSON

{
  "schema": "kynticai.elite.outcome-prompts.v1",
  "caseStudyId": "professional-services-governance-prospect",
  "domain": "Professional services",
  "stakeholder": "Managing partner",
  "runtimeQuery": "A prospect emails after reading the AI governance page, searches the site, and views page A on delivery approach. What should the firm do to make them book a discovery call or register interest?",
  "promptContract": "You are Elite, the KynticAI recommendation-writing layer.\n\nYou receive governed Fortress output, not raw customer data. Use only the supplied relationship-set facts, scores, confidence labels, alternatives, caveats, and outcome goal.\n\nWrite a decisive operational recommendation for the accountable team. Your output must include:\n1. Recommended action.\n2. Why this action is supported by the comparable relationship sets.\n3. What to do now.\n4. When to choose one of the alternative actions.\n5. What outcome to capture so the system improves.\n\nRules:\n- Do not invent facts outside the governed handoff.\n- Do not promise revenue, retention, clinical, legal, financial, safety, or compliance outcomes.\n- Do not apologise for using synthetic demo data.\n- Be commercially useful, specific, and direct.\n- Keep human review and claim boundaries visible where the domain requires them.",
  "governedFacts": [
    "Goal: protect_revenue",
    "Primary path: meeting_booked, score 0.5001, high confidence",
    "Supporting signals: ai_governance, delivery_page, email_enquiry, meeting_booked",
    "Runtime relationship sets returned: 8",
    "Domain journeys: 120; events: 600; relationship sets: 120"
  ],
  "outcomePrompts": [
    {
      "rank": 1,
      "outcome": "meeting_booked",
      "action": "Send a partner-led discovery invitation with two relevant case examples and a short governance checklist.",
      "confidence": "High",
      "score": "0.5001",
      "prompt": "You are Elite, the KynticAI recommendation-writing layer.\n\nUse only the governed Fortress handoff below. Do not invent facts.\n\nCase study: AI governance prospect from enquiry to discovery call\nDomain: Professional services\nStakeholder: Managing partner\nRuntime query: A prospect emails after reading the AI governance page, searches the site, and views page A on delivery approach. What should the firm do to make them book a discovery call or register interest?\n\nGoverned facts:\n- Goal: protect_revenue\n- Primary path: meeting_booked, score 0.5001, high confidence\n- Supporting signals: ai_governance, delivery_page, email_enquiry, meeting_booked\n- Runtime relationship sets returned: 8\n- Domain journeys: 120; events: 600; relationship sets: 120\n\nCandidate outcome to explain:\n- Rank: 1\n- Outcome: meeting_booked\n- Action: Send a partner-led discovery invitation with two relevant case examples and a short governance checklist.\n- Confidence: High\n- Score: 0.5001\n- Evidence summary: Comparable relationship sets ended in meeting_booked and share signals such as ai_governance, delivery_page, email_enquiry, meeting_booked.\n- Supporting relationship sets: set-1cd70d131184, set-46269e91144b, set-de87256bcb27, set-1d38e00b1113, set-d931f6c59213\n\nWrite the operational recommendation for this outcome.\nInclude why the comparable relationship sets support it, what the team should do now, when this outcome should be chosen over the other ranked options, and what reviewed outcome must be captured next.",
      "expectedTextOutput": "Recommended action: Send a partner-led discovery invitation with two relevant case examples and a short governance checklist.\n\nWhy this is supported: Fortress ranked meeting_booked first with score 0.5001 and high confidence. Comparable relationship sets ended in meeting_booked and share signals such as ai_governance, delivery_page, email_enquiry, meeting_booked. The supporting relationship sets are set-1cd70d131184, set-46269e91144b, set-de87256bcb27, set-1d38e00b1113, set-d931f6c59213.\n\nWhat to do now: brief the managing partner with the runtime query, the shared signals (ai_governance, delivery_page, email_enquiry, meeting_booked), and the exact action. Keep the action specific to this scenario rather than turning it into a generic campaign or workflow rule.\n\nWhen to choose an alternative: switch if the live evidence is closer to registered_interest (Ask for registration to a specific roundtable rather than sending broad marketing copy.); reengaged_after_email (Send a concise risk-removal email that asks one question and links to page B commercial-fit scope.); renewed_after_save_plan (Protect delivery capacity before pitching expansion.).\n\nOutcome to capture: record the action taken, the reviewed outcome, and any contradictory signal so the next Scout/Fortress comparison has stronger evidence."
    },
    {
      "rank": 2,
      "outcome": "registered_interest",
      "action": "Ask for registration to a specific roundtable rather than sending broad marketing copy.",
      "confidence": "Low",
      "score": "0.2763",
      "prompt": "You are Elite, the KynticAI recommendation-writing layer.\n\nUse only the governed Fortress handoff below. Do not invent facts.\n\nCase study: AI governance prospect from enquiry to discovery call\nDomain: Professional services\nStakeholder: Managing partner\nRuntime query: A prospect emails after reading the AI governance page, searches the site, and views page A on delivery approach. What should the firm do to make them book a discovery call or register interest?\n\nGoverned facts:\n- Goal: protect_revenue\n- Primary path: meeting_booked, score 0.5001, high confidence\n- Supporting signals: ai_governance, delivery_page, email_enquiry, meeting_booked\n- Runtime relationship sets returned: 8\n- Domain journeys: 120; events: 600; relationship sets: 120\n\nCandidate outcome to explain:\n- Rank: 2\n- Outcome: registered_interest\n- Action: Ask for registration to a specific roundtable rather than sending broad marketing copy.\n- Confidence: Low\n- Score: 0.2763\n- Evidence summary: Comparable relationship sets ended in registered_interest and share signals such as cross_sell, page_c, registration, webinar.\n- Supporting relationship sets: set-f460400997bd\n\nWrite the operational recommendation for this outcome.\nInclude why the comparable relationship sets support it, what the team should do now, when this outcome should be chosen over the other ranked options, and what reviewed outcome must be captured next.",
      "expectedTextOutput": "Alternative action: Ask for registration to a specific roundtable rather than sending broad marketing copy.\n\nWhy this route exists: Fortress returned registered_interest at rank 2 with score 0.2763 and low confidence. Comparable relationship sets ended in registered_interest and share signals such as cross_sell, page_c, registration, webinar. The supporting relationship sets are set-f460400997bd.\n\nWhen to use it: choose this instead of the primary route when the live evidence matches cross_sell, page_c, registration, webinar more closely than the current top-ranked outcome.\n\nWhat to do now: make the action explicit for the managing partner, preserve the caveat for this domain, and avoid inventing extra facts beyond the governed handoff.\n\nOutcome to capture: record whether registered_interest happened and feed that reviewed result back into the relationship-set evidence."
    },
    {
      "rank": 3,
      "outcome": "reengaged_after_email",
      "action": "Send a concise risk-removal email that asks one question and links to page B commercial-fit scope.",
      "confidence": "Low",
      "score": "0.2641",
      "prompt": "You are Elite, the KynticAI recommendation-writing layer.\n\nUse only the governed Fortress handoff below. Do not invent facts.\n\nCase study: AI governance prospect from enquiry to discovery call\nDomain: Professional services\nStakeholder: Managing partner\nRuntime query: A prospect emails after reading the AI governance page, searches the site, and views page A on delivery approach. What should the firm do to make them book a discovery call or register interest?\n\nGoverned facts:\n- Goal: protect_revenue\n- Primary path: meeting_booked, score 0.5001, high confidence\n- Supporting signals: ai_governance, delivery_page, email_enquiry, meeting_booked\n- Runtime relationship sets returned: 8\n- Domain journeys: 120; events: 600; relationship sets: 120\n\nCandidate outcome to explain:\n- Rank: 3\n- Outcome: reengaged_after_email\n- Action: Send a concise risk-removal email that asks one question and links to page B commercial-fit scope.\n- Confidence: Low\n- Score: 0.2641\n- Evidence summary: Comparable relationship sets ended in reengaged_after_email and share signals such as email_again, commercial_intent_page, proposal_stalled.\n- Supporting relationship sets: set-304c761cf50e\n\nWrite the operational recommendation for this outcome.\nInclude why the comparable relationship sets support it, what the team should do now, when this outcome should be chosen over the other ranked options, and what reviewed outcome must be captured next.",
      "expectedTextOutput": "Alternative action: Send a concise risk-removal email that asks one question and links to page B commercial-fit scope.\n\nWhy this route exists: Fortress returned reengaged_after_email at rank 3 with score 0.2641 and low confidence. Comparable relationship sets ended in reengaged_after_email and share signals such as email_again, commercial_intent_page, proposal_stalled. The supporting relationship sets are set-304c761cf50e.\n\nWhen to use it: choose this instead of the primary route when the live evidence matches email_again, commercial_intent_page, proposal_stalled more closely than the current top-ranked outcome.\n\nWhat to do now: make the action explicit for the managing partner, preserve the caveat for this domain, and avoid inventing extra facts beyond the governed handoff.\n\nOutcome to capture: record whether reengaged_after_email happened and feed that reviewed result back into the relationship-set evidence."
    },
    {
      "rank": 4,
      "outcome": "renewed_after_save_plan",
      "action": "Protect delivery capacity before pitching expansion.",
      "confidence": "Low",
      "score": "0.2581",
      "prompt": "You are Elite, the KynticAI recommendation-writing layer.\n\nUse only the governed Fortress handoff below. Do not invent facts.\n\nCase study: AI governance prospect from enquiry to discovery call\nDomain: Professional services\nStakeholder: Managing partner\nRuntime query: A prospect emails after reading the AI governance page, searches the site, and views page A on delivery approach. What should the firm do to make them book a discovery call or register interest?\n\nGoverned facts:\n- Goal: protect_revenue\n- Primary path: meeting_booked, score 0.5001, high confidence\n- Supporting signals: ai_governance, delivery_page, email_enquiry, meeting_booked\n- Runtime relationship sets returned: 8\n- Domain journeys: 120; events: 600; relationship sets: 120\n\nCandidate outcome to explain:\n- Rank: 4\n- Outcome: renewed_after_save_plan\n- Action: Protect delivery capacity before pitching expansion.\n- Confidence: Low\n- Score: 0.2581\n- Evidence summary: Comparable relationship sets ended in renewed_after_save_plan and share signals such as delivery_risk, renewal, save_plan, utilisation_high.\n- Supporting relationship sets: set-835ac04006ba\n\nWrite the operational recommendation for this outcome.\nInclude why the comparable relationship sets support it, what the team should do now, when this outcome should be chosen over the other ranked options, and what reviewed outcome must be captured next.",
      "expectedTextOutput": "Alternative action: Protect delivery capacity before pitching expansion.\n\nWhy this route exists: Fortress returned renewed_after_save_plan at rank 4 with score 0.2581 and low confidence. Comparable relationship sets ended in renewed_after_save_plan and share signals such as delivery_risk, renewal, save_plan, utilisation_high. The supporting relationship sets are set-835ac04006ba.\n\nWhen to use it: choose this instead of the primary route when the live evidence matches delivery_risk, renewal, save_plan, utilisation_high more closely than the current top-ranked outcome.\n\nWhat to do now: make the action explicit for the managing partner, preserve the caveat for this domain, and avoid inventing extra facts beyond the governed handoff.\n\nOutcome to capture: record whether renewed_after_save_plan happened and feed that reviewed result back into the relationship-set evidence."
    }
  ]
}