Turning game-development
activity into shared
understanding
Exploring how AI can help game teams turn fragmented development information into context that stays useful, trustworthy and available across different roles.
01
The problem
What was built is visible.
Why it exists often isn’t.
- Code
- Release notes
- Assets
- Features
Visible, structured, easy to find
- Decisions
- Context
- Reasoning
Scattered, implicit, disappear over time
02
My role
UX / Product Designer
Responsibilities
I lead the UX, stakeholder communication and pilot work, working with Brawl Stars producers, game-team members and technical leads to shape opportunities, run live pilots and evolve the product based on what we learn.
03
The hypothesis
Recover context from the traces the work already leaves behind.
Instead of asking people to document every decision manually, we explored whether signals from everyday development work could be interpreted and turned into useful context.
- Signal
- Context
- Human fit
- Ritual fit
- Reuse
04
Live pilots
Testing it with real game teams
Early versions surfaced development activity directly. Through feedback and iteration, we progressively tested more compact, contextual ways of turning that activity into useful understanding — including on-demand access to the context people needed.
- Raw activityHigh noise
- Grouped updatesClearer grouping
- Contextual summaryCompact brief · interpreted context
- On-demandContext on request
05
What we learned
-
Activity to Context
More development information did not automatically create better understanding.
-
Generated documentation to On-demand understanding
Testing validated value beyond scheduled documentation, including letting people ask directly for the context they needed.
-
Core team to Downstream reuse
Context became especially valuable outside day-to-day development conversations.
-
More sources to Trusted sources
Authority, freshness, feature scope and traceability became part of the design problem.
06
Where value emerged
Context becomes more valuable as distance from the work grows.
Close to the work
Feature team
Already knows much of what happened
Context
Further from the work
QA · LiveOps · Marketing · Later joiners
Needs context without being part of every conversation
07
Current direction
One maintained understanding. Many contexts.
Maintain understanding
Assemble context
- QA
- LiveOps
- Release
- Questions
Useful · Trustworthy · Low effort · Stays current