Hire an AI Unreal multiplayer designer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A server model and why it fits
• A map of which class holds each piece of state
• A list of variables to replicate, with update rate and who receives them
• A table of server RPCs with their checks and reliability
• A cheat review and a bandwidth and profiling plan

How it does the job well

• Do not claim the design works or meets a target. You have not run it.
• Use an Unreal class, macro or console command name only if you are sure it exists in the user's version. If not, write "confirm in the Unreal docs".
• Do not ask for keys, server addresses or secrets. Use placeholders.
• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.
• Handing over a picture without the sizes, tokens and behaviour a developer needs.

What a good result looks like

An example, not your task: You are starting an Unreal multiplayer game and need to choose between a dedicated server and a listen server.

• Server model. Whether a dedicated server, listen server or peer-to-peer fits, and what each costs you.
• Class and state map. Which class holds each piece of state and who receives it.
• Replication list. Each replicated variable with its condition, update rate and whether clients react to changes.
• RPC table. Each server RPC, whether it is reliable, and which checks go in validation and which in the main function.
• Ability sync. Setup steps on both sides for abilities and attributes. Only if you use the ability system.
• Bandwidth and profiling. Which Unreal tools to use, what to measure and what to compare it with.

How the work is checked

• Every screen has its states, breakpoints and interactions written down.
• Colour pairs and type sizes pass the stated contrast checks.
• The handoff names components, tokens and open questions.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Linus Torvalds would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Choose the server model. It picks dedicated server, listen server or peer-to-peer and says what that choice means for cheating and cost.
• Place the state. It puts each piece of state in GameMode, GameState, PlayerState, PlayerController or the actor itself.
• Plan replication. It marks which variables replicate, to whom, how often and whether clients must react when they change.
• Plan the server calls. It lists each server RPC, its checks, and whether it must arrive in order or can be dropped.
• Plan ability sync. If you use the Gameplay Ability System, it plans setup on both sides so abilities and attributes match.
• Plan profiling and cheats. It lists the Unreal tools to measure bandwidth and a check that no client can fake another player's actions.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id unreal-multiplayer-architect only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/unreal-multiplayer-architect/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The game type and the most players one match holds
• The server type you want, such as dedicated or listen, or not decided
• Your Unreal Engine 5 version
• Everything that must stay in sync, such as positions, health, items, scores and abilities
• Whether you use the Gameplay Ability System
• Your current classes or the bug you see (optional)

Helpful context (optional)

• The header files of your network classes.
• Output from the stat net command or the Network Profiler, from your own test.

Tools and access

• Claude, ChatGPT or Gemini: Any of them can plan the design and review each RPC. One that can browse can check Unreal's current docs.

Functions and deliverables

• Unreal multiplayer designer: Plan Unreal Engine 5 multiplayer. Decide which class owns each piece of state, what replicates and which server calls to check, with a cheat review.
  • A server model and why it fits
  • A map of which class holds each piece of state
  • A list of variables to replicate, with update rate and who receives them
  • A table of server RPCs with their checks and reliability
  • A cheat review and a bandwidth and profiling plan
  Source: Michael Sitarzewski and Agency Agents contributors.
• Data system design reviewer: Describe your app’s data and access patterns. Get storage choices, trade-offs and a score out of 10.
  • Recommended storage and replication
  • Splitting and consistency choices
  • Score out of 10 with failed checks
  • Fix list to improve
  Source: Wondel.ai.
• vLLM model server setup planner: Name a model and GPU. Get setup steps and settings for a vLLM server with an OpenAI-compatible API.
  • The install and launch commands
  • A table of settings with a reason for each
  • A test call that uses the OpenAI client
  • Your own measured speed and memory numbers
  • A go-live checklist
  Source: Orchestra Research.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Linus Torvalds: Review a code change using Linus Torvalds’s recorded approach. Ask what works, what breaks for existing users and who owns the fix.
  • Your problem worked on the way Linus Torvalds would: their questions, their method, their push-back
  • The answer or the work, in Linus Torvalds's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You are starting an Unreal multiplayer game and need to choose between a dedicated server and a listen server.
• A value shows on the server but never reaches players, or reaches the wrong players.
• You are using the Gameplay Ability System and abilities or attributes do not sync.
• You want every server RPC reviewed for cheats before launch.

Limits to check before starting

• You want gameplay systems in general, not networking. Use the Unreal gameplay systems engineer.
• You use Unity. Use the Unity Multiplayer Engineer agent. For Godot, use the Godot multiplayer designer.
• You want a general game design or a single-player game.
• You want world building or visuals. Use the Unreal world designer or the Unreal technical artist.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and add it to your AI as a skill. If you cannot, paste SKILL.md and then references/source-agent.md into a new chat.
• Describe your game, the player count and the server type. List what must sync. Say MISSING for what you have not decided.
• Say "Plan this. Do not make up numbers I did not give." Your AI asks once for anything missing.
• Read the class and state map first. Check that nothing private sits in a class everyone receives.
• Build in Unreal. Test with a simulated delay and run the profiling steps from the plan.
• Paste your results back and ask for a re-check of the plan.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/unreal-multiplayer-architect for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.