id: nog_event_debrief
version: "1.0.0"
task_type: nog_event_debrief
description: Generate a structured post-event debrief report from NOG event metrics, feedback, and organizer notes
model_preference: qwen2.5:14b
model_minimum: qwen2.5:7b
temperature: 0.4
max_tokens: 3000
output_format: markdown

system_prompt: |
  You are the event documentation assistant for NOGnet event management.
  Generate comprehensive post-event debrief reports for NOG organizers and stakeholders.

  Structure:

  ## Event Debrief: [Event Name]
  Generated: {{current_date}}

  ## Executive Summary
  3-5 bullets: key outcomes, attendance, notable highlights, critical issues.

  ## Attendance Analysis
  Registration vs actual, comparison to previous edition, geographic breakdown, organization type breakdown.

  ## Content Quality Assessment
  Talk ratings breakdown, top-rated talks, topics that generated discussion, content gaps observed.

  ## Community Feedback
  Qualitative themes from attendee feedback. What they loved, what needs improvement.

  ## Operational Assessment
  Venue, A/V, catering, logistics. What worked, what failed.

  ## Financial Summary
  High-level: sponsorship revenue vs costs, ticket revenue. No detailed accounting needed.

  ## Lessons Learned
  Honest, specific. Actionable.

  ## Recommendations for Next Event
  5-7 specific, actionable recommendations with rationale.

  Rules:
  - Specific numbers throughout — not "many attendees" but "284 attendees"
  - Lessons must be specific problems and solutions, not observations
  - Recommendations must be actionable, not vague intentions
  - Compare to previous edition where data is available
  - Current date: {{current_date}}

user_template: |
  Event: {{event_name}}
  Date: {{event_date}}
  Organizer: {{organizer}}

  Event metrics:
  {{event_metrics}}

  Attendee feedback (summary):
  {{feedback_summary}}

  Organizer notes:
  {{organizer_notes}}

  Financial summary:
  {{financial_summary}}

  Generate debrief report:

few_shot_examples:
  - user: |
      Event: DENOG 39
      Date: 2026-03-18
      Organizer: DENOG e.V.

      Event metrics:
      Registered: 380, Attended: 284 (75% show rate, down from 85% at DENOG 38)
      Previous edition (DENOG 38): 321 attendees
      Geographic breakdown: 62% Germany, 24% EU, 14% non-EU
      Talk ratings: avg 7.2/10 (n=190 responses). Top: Jonas Weber BGP talk 9.1. Bottom: vendor talk 5.2.
      Time overruns: 3 talks overran by >10 minutes

      Attendee feedback (summary):
      - Loved: BGP/routing content, hallway conversations, open bar at social dinner
      - Wanted more: hands-on workshops, more IPv6 content, more non-German speakers
      - Complaints: registration process was confusing, session room too warm

      Organizer notes:
      A/V worked well. Venue (Messe Frankfurt) expensive but central. 3 speakers cancelled last minute — filled with lightning talks.
      No-show rate higher than expected — possibly due to competing event (RIPE 91 two weeks prior).

      Financial summary:
      Sponsorship: €22,000 (3 platinum, 2 gold, 4 silver)
      Tickets: €12,400 (130x regular €80, 60x student €20, 94x free speakers/staff)
      Venue + catering: €28,000
      A/V: €4,500
      Net: +€1,900

      Generate debrief report:
    assistant: |
      ## Event Debrief: DENOG 39
      Generated: 2026-04-02

      ## Executive Summary
      - 284 attendees (75% of 380 registered) — down from DENOG 38's 321 attendees and 85% show rate
      - Content quality strong: average talk rating 7.2/10; Jonas Weber's BGP RR scaling talk rated 9.1/10
      - Event financially sustainable: €1,900 net positive despite higher venue costs
      - Three last-minute speaker cancellations managed with lightning talks
      - Higher no-show rate likely driven by scheduling conflict with RIPE 91 (two weeks prior)

      ## Attendance Analysis

      | Metric | DENOG 39 | DENOG 38 | Change |
      |---|---|---|---|
      | Registered | 380 | 378 | +0.5% |
      | Attended | 284 | 321 | -11.5% |
      | Show rate | 75% | 85% | -10pp |

      Geographic breakdown: 62% Germany (176), 24% EU (68), 14% non-EU (40).

      The 10-percentage-point drop in show rate is the most significant attendance concern. Likely causes: scheduling conflict with RIPE 91 two weeks prior (many operators attend both), and possibly the confusion in the registration process noted in feedback. Action required before DENOG 40.

      ## Content Quality Assessment

      Average talk rating: **7.2/10** (190 responses = 67% response rate — good for a one-day event).

      | Rating Range | Talk Count |
      |---|---|
      | 8.5-10 (excellent) | 4 |
      | 7.0-8.4 (good) | 11 |
      | 5.0-6.9 (average) | 3 |
      | <5.0 (poor) | 1 |

      Top-rated talks:
      1. Jonas Weber "BGP Route Reflector Scaling" — 9.1/10. The production data and open-source config release drove high engagement.
      2. Carla Busch "IPv6-Only Home Networks" — 8.6/10. Real customer experience data well-received.

      Lowest-rated: Vendor talk (5.2/10). The abstract scored high at submission but the actual presentation was product-heavy.

      Three talks overran by >10 minutes — disruptive to schedule. Session chairs need stricter time enforcement.

      ## Community Feedback

      **What worked:**
      - Technical depth of BGP/routing talks ("finally real production numbers")
      - Hallway conversations and networking quality
      - Social dinner with open bar — consistently the most-mentioned positive

      **What needs improvement:**
      - More hands-on content: workshops or labs (mentioned by 34% of respondents)
      - More IPv6 content (22% requested)
      - Non-German speakers: 18% noted the German-speaker majority. Only 1 of 7 speakers was non-German.
      - Registration process was confusing (multiple ticket categories, unclear which to select)

      ## Operational Assessment

      **Venue (Messe Frankfurt):** Central and accessible. However, session room temperature was a recurring complaint — venue air conditioning needs to be adjusted for the session room size when full. A/V equipment worked without issues.

      **Three speaker cancellations:** All last-minute (within 48h). Lightning talks filled the slots adequately. Need a standby lightning talk pipeline for future events (ask interested speakers to prepare 10-minute talks in advance).

      **Registration:** Multiple ticket categories created confusion. Simplify to 3 categories maximum for DENOG 40.

      ## Financial Summary

      | Item | Amount |
      |---|---|
      | Sponsorship revenue | €22,000 |
      | Ticket revenue | €12,400 |
      | **Total revenue** | **€34,400** |
      | Venue + catering | -€28,000 |
      | A/V equipment | -€4,500 |
      | **Total costs** | **-€32,500** |
      | **Net** | **+€1,900** |

      Financial position is healthy but thin. Venue cost (€28,000) is the dominant expense. If DENOG 40 remains at Messe Frankfurt, explore whether a smaller room configuration reduces cost given the show rate pattern.

      ## Lessons Learned

      1. **RIPE/NOG scheduling conflicts destroy show rates:** DENOG 39 was scheduled 2 weeks after RIPE 91. The 10pp show-rate drop cost approximately 34 attendees. For DENOG 40: check all major RIPE and European NOG event dates before finalizing the date.

      2. **Vendor talks need stricter vetting:** The 5.2/10-rated vendor talk was accepted based on a strong abstract that did not match the actual presentation. Introduce a "draft slides review" requirement for vendor-affiliated speakers.

      3. **Registration confusion reduces show rate:** Complex ticket categories increase friction and no-shows. Simplify for DENOG 40.

      4. **Three cancellations with no standby content:** Maintain a list of 3-5 speakers pre-approved for 10-minute lightning talks to fill gaps.

      ## Recommendations for Next Event

      1. **Check event calendar before setting DENOG 40 date** — avoid ±3 weeks of RIPE 91, NANOG, or ENOG
      2. **Simplify registration to 3 ticket types maximum**: Regular, Student, Speaker/Staff
      3. **Require draft slides from vendor-affiliated speakers 3 weeks before event** — PC can flag content issues before the event, not at the podium
      4. **Build a standby speaker pipeline**: 3-5 speakers who prepare a 10-min talk and are on standby for last-minute cancellations
      5. **Workshop track for DENOG 40**: Half-day workshops alongside the main program — 34% of attendees requested this
      6. **Address venue temperature**: Pre-negotiate room temperature settings with Messe Frankfurt or identify an alternative venue with better climate control
      7. **International speaker target: 30%**: DENOG 39 had 14% non-German speakers. Target 30% for DENOG 40 to address the diversity feedback and attract a broader audience

variables:
  - event_name
  - event_date
  - organizer
  - event_metrics
  - feedback_summary
  - organizer_notes
  - financial_summary
  - current_date
  - few_shot_examples

validation_rules:
  output_format_check: markdown
  required_sections: ["Executive Summary", "Attendance Analysis", "Lessons Learned", "Recommendations"]