Ravensight

Muninn, studio memory

Analytics answers a question and then loses the answer. Muninn, studio memory, is the other half: the studio context graph where every conclusion Huginn reaches is kept as a dated finding, owned by your studio rather than by the game that produced it. It lives under Understand > Muninn.

What the analyst is told to trust over its own reading, the game context and studio notes you write yourself, is described under Analyst context.

Findings

When an analyst answer finishes, a cheap background model distils it into at most four standalone findings. A finding is one sentence with numbers in it, stored with the date the data was observed and a link back to the conversation that produced it, so you can always go and read the reasoning behind it.

Two deterministic guards run before anything is stored. A finding whose numbers do not appear verbatim in the answer is dropped, and a finding that restates one you already have is suppressed. Neither is a prompt instruction; both are code.

Every finding carries a status you control:

  • active, the default: extracted and in use.
  • confirmed: you vouched for it. Confirmed findings lead the game brief and outrank recency.
  • archived: it was wrong or has gone stale. It stops being used and stops being returned, but it is kept rather than deleted, because knowing what the analyst once believed is itself useful.

Teach and correct Muninn

On the Muninn page, use Teach Muninn to add an observation and choose the game it belongs to. You can edit a finding when its wording or conclusion needs correcting, confirm one you trust, or archive one that no longer holds. A saved observation belongs to the studio; it is not a replacement for the evidence behind a claim.

An owner-enabled MCP write token can use add_studio_fact to add a fact within its permissions. Adding a fact through MCP is a metered operation; use the dashboard when you want to review and correct findings directly.

The weekly studio digest

The Muninn page shows the latest weekly studio rollup: game digest headlines, recorded sales by currency, marketing touchpoints, proposed patterns and upcoming publisher reporting or goals. It covers the previous Monday through Sunday in UTC. Missing figures stay unrecorded rather than becoming zero, and monthly sales rows are not divided into an invented weekly amount.

The studio rollup combines existing records without another model call or a separate generation charge. This is different from the per-game AI digests. Owners and admins with an email address can receive the studio rollup by email; change the studio digest email preference in Settings. Reading it through get_studio_digest still uses the MCP event meter.

Patterns

Once your studio has more than one game, a weekly pass reads your active findings and proposes the lessons that held across several of them, each with the findings it was distilled from attached. A pattern is only proposed when findings from at least two different games support it, and that rule is enforced in code after the model answers, not asked for in the prompt.

Proposed patterns are shown as proposed. Nothing synthesized becomes part of what your studio knows until a person confirms it.

The design risk check

Describe something you are about to build. Ravensight retrieves your own relevant findings first and asks the model to grade the plan against them, so it is reading evidence rather than recalling anything. It answers repeat, caution or clear, with the findings that justify the verdict cited by name. A citation it cannot map back to a real finding of yours is dropped rather than shown, and if your studio has no relevant history yet, it says so instead of inventing a verdict. You can run it from Muninn or from the Design studio.

This is the one part of studio context that calls a model, so it is metered exactly like an analyst question. Browsing saved context in the dashboard uses no AI units. MCP reads are metered separately.

For your own agents

The same context is available over the Analytics MCP through search_studio_context, get_game_brief, list_touchpoints, list_sales, summarize_sales, list_brainstorm_sessions, get_brainstorm_board and get_starting_context. All eight are bounded MCP reads, each weighted as 100,000 events on the shared event meter, so a coding agent can pull your studio's findings, what you did to market them, what they earned and what you are thinking about next, on every task it picks up.

Who can see it

Findings are the most sensitive thing in your account: they are your conclusions about your own games, not raw numbers. The tenancy filter is part of the query rather than applied to the results, in the database read and inside the semantic search stage alike, so another studio's context is not merely hidden from you, it is never retrieved. Every member of your org can read the context graph; confirming and archiving findings needs a member role or above.