jpmschweitzerandClaude Opus 4.6
0100b33635
Long-term content strategy workshop: 300-world generator model, cultural ingredients menu, three-system NPC architecture (9 patterns x 6 motivations), Sacred/Profane/Middle Kingdom framework. 9 agents across 4 rounds plus lead interview establishing the production path from hand-authored Sova to generated 300 worlds. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
5.6 KiB
Lead Interview — Between Round 3 and Round 4
Date: 2026-02-12 Format: Interactive 5-topic interview, one topic at a time Interviewer: Team lead (Claude Code) Interviewee: Jeroen (project lead)
Topic 1: Cultural Groups
Decision: Ingredients menu, not fixed taxonomy.
Cultural groups are assembled by picking and combining from a menu of ingredients per society:
- Heritage roots (recognizable but not directly mappable — "feels Nordic" not "is Finnish")
- Settlement motivation
- Economic function
- Philosophical alignment
- Corporate presence
- Time since settlement / drift stage
Key rules:
- NOT required to pick from every category. What a society doesn't care about is as defining as what it does. Varying what matters creates flavor.
- Output must feel like a SOCIETY, not a matrix entry.
- Mechanical parameters (access tiers, trust defaults, investigation dynamics) DO need a structured matrix underneath.
- Heritage should be identifiable as a culture without feeling disparate.
- People migrate between heritages. Drift varies per location.
- Economics is missing from Nigel's 7 mechanical questions — must be added (what makes extra income tempting).
On heritage specificity: The specific real-world roots (Finnish/Estonian/Latvian for Krenn) are Miri's reference material for building the culture, not something the player should clock directly. A character with a Nordic-sounding name in an East Asian-heritage district isn't wrong — they're a person with a history. The culture is the place, not the individual.
Topic 2: Content Patterns (NPC Archetypes)
Decision: Three separate systems, not one list.
A. Thematic Patterns (what the character means to the story)
FRIEND, MIRROR, ANCHOR, GHOST, CATALYST, THRESHOLD, REMNANT, SYSTEM, NOBODY
THE NOBODY is new — a person who is just... there. Background becomes foreground when the player pays attention.
Major system decision: Evolving relationships. The lead explicitly wants a NOBODY to be able to become something more if the player invests attention. Quote: "evolving relationships sounds like a can of worms I would LOVE to open." This implies dynamic tier promotion, relationship-driven content unlocking, emergent narrative from player attention.
B. Functional Motivations (what the character is doing in gameplay)
HANDLER, WITNESS, TURNCOAT, CIVILIAN, OPERATOR, SKEPTIC
These are Nigel's list — motivations, not archetypes. Developed in parallel with thematic patterns.
C. Composition
Each NPC gets a thematic pattern + a functional motivation. ANCHOR + OPERATOR plays very differently from ANCHOR + CIVILIAN. At 300-world scale, generators pick these combinations.
Topic 3: PC Archetypes
Decision: 8 archetypes at v1.0 as stress test.
- Insider + Investigator are deep because of v0.1 but must NOT become the permanent center. Other archetypes should feel equally primary in their districts.
- Newcomer = v0.2 content update centerpiece. Natural tutorial, fresh eyes on established world.
- Archetypes are FLUID. Players can move districts, change jobs, buy houses. The archetype is a current position in a community, not a character class. Archetype transitions are a game mechanic.
- "What still feels alive enough" is the question, not "how many per district." A bar 20 minutes from the gate in no-man's land still needs characters.
- The freedom to change your life flows naturally from the refocus on living a life.
Topic 4: Randomization
Decision: Nigel's Sacred/Profane/Middle Kingdom framework approved.
With a key refinement from the lead:
- Sacred = rules of the system (mass interactions). "You DO randomize gravity — you don't randomize mass interactions."
- Profane = parameters the rules operate on. Drawn from pools. Gravity varies by world; the physics engine doesn't.
- Middle Kingdom = sacred structure, profane cast.
Gate topology as macro randomization:
- Core worlds always connected (Sacred)
- Peripheral systems vary per playthrough (Profane)
- Number of accessible systems may be fixed, which ones varies (Middle Kingdom)
- Unlockable worlds through random gate events or quests = chapter-level randomization
- Future possibility: planetary owner/developer DLC
Perception system note: Varying gravity is a great way to breathe life into stepping onto another world. Flag for perception team.
Generation is LIGHT — pick from pools of authored content, don't generate from scratch.
Topic 5: Scale
Decision: 300 worlds before DLC.
This is why we're building strategy and generator inputs, not authoring content by hand.
Release path:
- v0.1 = proof of the interaction model (1 district, hand-authored)
- v0.2-v0.5 = testing generation systems and tooling
- v0.6-v0.10 = content pipeline at scale
- pre-v1.0 = 300 worlds populated via generators + style briefs + naming algos
Tooling first is absolute. The authoring/generation pipeline must be proven before scaling.
Key reframe: The style briefs, naming algorithms, character generators, and cultural parameter matrices ARE the product of this strategy work. They're generator inputs, not documentation. The planetary cultural identities are basically seeds — the cultural brief for a world IS the generation seed that parameterizes everything.
Theme — Still Open
The lead has not picked a canonical framing. Candidates:
- Cost of participation (Gore)
- Collective bargain (Mellanie)
- What do you owe the people around you? (Ozzie)
- What do systems do to people inside them? (Miri)
- Cost of connection / entanglement (Paula)
- Knowledge as burden (Gestalt)
May resolve as strategy solidifies.