# Latent Spark: headless game understanding

The same calibrated understanding of a game, in the UI or over the wire. Belief states with explicit uncertainty, not RAG chunks or tag-graph hops.

## One capability catalogue across the UI, MCP, OpenAPI, and A2A.

### MCP: Ask what a game is, in session.

Inspect beliefs, find comps, and run counterfactuals as MCP tools. Copilots get mechanics, identity, and uncertainty as structured state, not store-page chunks ranked by cosine.

### API: Ask what it could become, at scale.

Same capability IDs over OpenAPI and POST /capabilities/{id}/invoke. Decoder edits like “more co-op” or “lean premium” shift the neighbourhood; batch retrieval keeps session state and lineage.

### A2A: Ask which comps hold, across agents.

Publish an agent card so peers can call Latent Spark for asymmetric similarity with mechanics rationale. Tag-graph hops stay out; thin evidence stays flagged.

## Why not just ask an LLM?

An LLM can describe the games it happens to know. Latent Spark measures an industry-wide corpus in one coordinate system—from evidence, with known uncertainty—so “games whose community behaves like Rust's without the obligation load” returns a ranked, checkable set, not an anecdote from the famous two hundred.

### The long-tail ceiling.

We've measured it. Frontier LLMs return nothing useful for the long-tail. For most games they know a store blurb or less—and invent genre-typical answers rather than say so.

### No shared coordinate system.

Comparison needs a common scale; chat doesn't have one. Ask about Rust and Valheim and you get two essays—ask it to rank 500 survival games by social obligation and you get a confident, unverifiable list. With Latent Spark, distance, blends, and axis moves are geometry.

### Traceable, priced evidence.

Every Latent Spark score cites its atoms, which cite reviews. Certainty says how much evidence backs it; unknowns stay explicit. When claims fail against observed evidence, the system catches it. A chat answer has no trail to audit—and hides its surprises.

## Related

- [Latent Spark overview](https://iridae.com/understand/)
- [Capabilities catalog](https://iridae.com/understand/capabilities/)
- [FAQ](https://iridae.com/understand/faq/)

## Site map

- [Home](https://iridae.com/) — Iridae decision infrastructure for game studios

### [Latent Spark — Understand](https://iridae.com/understand/)

Calibrated game belief, comps, and market atlas

- [Overview](https://iridae.com/understand/)
- **Headless + Integrated** (this page)
- [Capabilities](https://iridae.com/understand/capabilities/)
- [FAQ](https://iridae.com/understand/faq/)

### [Anchored Horizon — Forecast](https://iridae.com/forecast/)

Comp-based Bayesian commercial forecasting

- [Overview](https://iridae.com/forecast/)
- [Headless + Integrated](https://iridae.com/forecast/headless/)
- [Capabilities](https://iridae.com/forecast/capabilities/)
- [FAQ](https://iridae.com/forecast/faq/)

### [Patient Cartographer — Plan](https://iridae.com/plan/)

Live strategic pathfinding under uncertainty

- [Overview](https://iridae.com/plan/)
- [Portfolio](https://iridae.com/plan/portfolio/)
- [Capabilities](https://iridae.com/plan/capabilities/)
- [FAQ](https://iridae.com/plan/faq/)

### [Subtle Beacon — Learn](https://iridae.com/learn/)

Continuous Bayesian experimentation

- [Overview](https://iridae.com/learn/)
- [Capabilities](https://iridae.com/learn/capabilities/)
- [FAQ](https://iridae.com/learn/faq/)

### Also

- [Book a Demo](https://iridae.com/demo/)
- [Company](https://iridae.com/company/)
- [Careers](https://iridae.com/company/careers/)
- [Blog](https://iridae.com/blog/)
- [Legal](https://iridae.com/legal/)

---

Canonical: https://iridae.com/understand/headless/