# GameDev Day 2026 MOC > Event map. Topic homes: [[3. Resources/MOCs/AI & the Future of Knowledge Work MOC]] · [[3. Resources/MOCs/AI Agent Safety MOC]] · Index: [[3. Resources/MOCs/MOCs|Maps of Content → Events & Conferences]] Seven talks from JetBrains GameDev Day Online 2026, published to the JetBrains channel on 2026-10-19 and captured to Reader and Obsidian the same day. This is a session index, not a synthesis: each linked note carries its own analysis, caption corrections and unverified-claim flags. ## Core Question When a coding agent can read live tool state instead of repository files, which game-development work gets easier, and what still needs a deterministic check or a human decision? > [!note] JetBrains hosts the event, and three talks present JetBrains products (TeamCity, Rider Kit, Qodana). Treat performance and productivity figures as speaker claims. Each note says which numbers appear only on slides. --- ## Agents that read live tool state Four talks give an agent a connection to something beyond the file tree: a CI server, the Unreal Editor plus the Rider IDE, a Godot scene tree and console, a Figma file. - [[3. Resources/Readwise/Articles/Fix Your CI Without Leaving the IDE TeamCity MCP and CLI - Artem Rokhin - GameDev Day 2026]] — Artem Rokhin (TeamCity) argues that one interface, the IDE or terminal, lets a developer resolve CI problems without switching to a browser. Covers the TeamCity CLI, an MCP server with scoped tokens, and configuration stored as code. The productivity claim is untested in the source. - [[3. Resources/Readwise/Articles/Agentic Development in Unreal Engine With JetBrains Rider - Alexander Dzerakh - GameDev Day 2026]] — Alexander Dzerakh presents Rider Kit, an AI chat inside the Unreal Editor that connects editor state to the Rider IDE so a coding agent sees both. A product preview: the performance claims aren't measured. - [[3. Resources/Readwise/Articles/Live-Building AI-Driven PCG With Godot, C, and Gemini - Sharmishtha Sen - GameDev Day 2026]] — Sharmishtha Sen connects a local Godot MCP server to cloud and local models so assistants in Rider write compilable Godot 4 C# for procedural terrain. Slide narration, not live coding; no repo or benchmarks. - [[3. Resources/Readwise/Articles/How We Automated Figma-to-Unity UI Integration With AI Agents - GameDev Day 2026]] — Alina and Olia Chupakhina describe a Figma-to-Unity pipeline: an MCP server, six agent skills and a deterministic converter. They report about 4x faster UI work; the comparison table is on a slide the transcript doesn't carry. Thread across the four: each builds the agent's advantage from state the agent can query (build logs, editor state, console output, design structure). None of the four reports a measurement the transcript lets you check, so the shared claim that live state helps is untested here. ## A deterministic check around AI edits - [[3. Resources/Readwise/Articles/How Static Analysis Can Help in the Age of AI - Kai Schmithusen - GameDev Day 2026]] — Kai Schmithusen (Qodana) argues AI raises code volume and so defect volume, and proposes AI writes, static analysis checks, AI repairs, static analysis re-checks. Speaker is a vendor; the cited studies have no sources in the talk. This talk pairs with the scoped-token and config-as-code points in the TeamCity talk: the agent acts, a fixed check decides. ## Engine architecture and frame time Two talks have no AI content. They cover how to change a running game engine and how to find where gameplay time goes. - [[3. Resources/Readwise/Articles/Evolving a Live Game Engine Introducing ECS Without a Full Rewrite - Alex Zhorau - GameDev Day 2026]] — Alex Zhorau lays out staged ECS adoption in a shipped engine: tools, core, low-risk features, then complex gameplay. Expects a permanent hybrid with legacy code. No quantified outcomes. - [[3. Resources/Readwise/Articles/Death by a Thousand Ticks Why Gameplay Systems Become Slow - Konrad Słoń - GameDev Day 2026]] — Konrad Słoń says gameplay slowness comes from many cheap operations, and splits every optimization into cost, frequency and scale. The talk works on frequency and scale. The speaker's millisecond figures come from slides the transcript doesn't carry. ## Using this map - Start with the four tool-state talks if you evaluate agent tooling; read the static-analysis talk next for the checking side. - Treat the two engine talks as practitioner design guides. ## Synthesis additions (2026-10-19 — Permanents from the GameDev Day, agent-site and religious-history batch) - [[3. Resources/Permanent Notes/A Green Pipeline Proves the Stages Ran Not That the Deployed Build Behaves]] — A green pipeline reports that each configured stage exited cleanly. - [[3. Resources/Permanent Notes/A Quality Gate Holds Only If the Agent It Checks Cannot Edit the Gate]] — A static-analysis gate checks an agent's work only when the agent has no write access to the gate's configuration. - [[3. Resources/Permanent Notes/Applying Only the Diff to a Generated Artifact Keeps Scripts and Hand Fixes a Rebuild Erases]] — When a generated artifact has gained hand-written scripts, cross-references and manual fixes, an update that compares it with the changed source and applies only the differences keeps them. - [[3. Resources/Permanent Notes/Running Work Less Often Can Raise the Worst Frame When Every Instance Shares One Schedule]] — Cutting how often a repeated job runs lowers total work, but if every instance moves to the same new schedule, the instances fire together and one frame takes the whole load.