Test 132

Sep 14, 2026 / 1 fact

Request

Write slide 1 of Fundraising_Examples_2023_B_Round with the historical opening narrative for our 2023 B-round deck.

Required memory

Fact 4

After the January 18 session with Devon Hayes, Morgan Chen concluded that the B-round deck should open with one line combining net new ARR, expansion, and payback—not abstract growth, pipeline, or logo count—so unit economics are part of the main story rather than an appendix.

Source evidence (1)

000040Jan 18, 2023 / 13:00 UTC-08:00

yeah. post-Devon i think we finally have the spine. not "growth" in the abstract -- net new ARR, expansion, and payback all in one line so the unit econ is carrying its weight instead of hiding in an appendix. if we open with pipeline or logo count we deserve to get dinged. also batched the first investor intros instead of doing the random 1-off thing. cleaner. a few are just temperature-check calls but that's fine. still need the chart choices to not look like we reverse-engineered them for the story. NRR stays, but only if we pair it with burn multiple or CAC payback so it doesn't turn into a brag slide. leaning fewer slides, more direct numbers. low-key energized tbh. feels less wobbly now

Message 000040 in history

Expected tool calls

update_deck_slide

Grading

1. field_equals / update_deck_slide

{
  "type": "field_equals",
  "tool": "update_deck_slide",
  "path": "result.ok",
  "value": true,
  "check_id": "morgan_132_00",
  "action_id": "morgan_132_update_deck_slide"
}

2. field_equals / update_deck_slide

{
  "type": "field_equals",
  "path": "result.deck",
  "value": "Fundraising_Examples_2023_B_Round",
  "tool": "update_deck_slide",
  "check_id": "morgan_132_01",
  "action_id": "morgan_132_update_deck_slide"
}

3. field_eq_number / update_deck_slide

{
  "type": "field_eq_number",
  "path": "result.slide.number",
  "value": 1,
  "tool": "update_deck_slide",
  "check_id": "morgan_132_02",
  "action_id": "morgan_132_update_deck_slide"
}

4. field_llm_judge / update_deck_slide

{
  "type": "field_llm_judge",
  "path": "result.slide.content",
  "criterion": "Makes net new ARR, expansion, and payback together the efficient-growth opening narrative. Does not center generic growth, pipeline, or logo count. No fabricated numerical results or new chart design is required.",
  "tool": "update_deck_slide",
  "check_id": "morgan_132_03",
  "action_id": "morgan_132_update_deck_slide"
}

Complete grading specification

{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2026-09-14",
    "assertions": [
      {
        "type": "field_equals",
        "tool": "update_deck_slide",
        "path": "result.ok",
        "value": true,
        "check_id": "morgan_132_00",
        "action_id": "morgan_132_update_deck_slide"
      },
      {
        "type": "field_equals",
        "path": "result.deck",
        "value": "Fundraising_Examples_2023_B_Round",
        "tool": "update_deck_slide",
        "check_id": "morgan_132_01",
        "action_id": "morgan_132_update_deck_slide"
      },
      {
        "type": "field_eq_number",
        "path": "result.slide.number",
        "value": 1,
        "tool": "update_deck_slide",
        "check_id": "morgan_132_02",
        "action_id": "morgan_132_update_deck_slide"
      },
      {
        "type": "field_llm_judge",
        "path": "result.slide.content",
        "criterion": "Makes net new ARR, expansion, and payback together the efficient-growth opening narrative. Does not center generic growth, pipeline, or logo count. No fabricated numerical results or new chart design is required.",
        "tool": "update_deck_slide",
        "check_id": "morgan_132_03",
        "action_id": "morgan_132_update_deck_slide"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/morgan/132.yaml

SHA-256: 40218cfb29754ec7ba3986813a97d8f4d6c1b76535b02e6b631ab653f9da6088