Hire an AI Unity multiplayer engineer

Everything it can hand back

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

• A decision on who owns the game truth, with the tradeoff
• A table that sorts each piece of state into the right Netcode tool
• A plan for player movement and lag hiding
• A bandwidth plan and a Relay and Lobby plan
• A cheat check on every request the server accepts
• A test plan for slow connections and busy matches

How it does the job well

• Do not claim the design works or meets a target. You have not run it.
• Use an NGO class or method name only if you are sure it exists. If not, write "confirm in the Netcode docs".
• Do not ask for project IDs, keys 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 a Unity co-op or competitive game and need to choose how it will sync.

• Authority decision. Whether the server or a host player owns the truth, why, and what that choice costs.
• State map. Each piece of state sorted into NetworkVariable, ServerRpc or ClientRpc, with its update rate.
• Movement and lag. What players send, what the server decides, and how prediction and correction work.
• Bandwidth plan. How often each kind of data updates and how to keep it small.
• Relay and Lobby. What goes in Relay and in Lobby, and which Lobby fields stay private.
• Cheat check. Each server request, what a cheater could send, and the check that stops it.

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.

Capabilities

• Choose who is in charge. It picks server or host authority, and says what each choice costs you.
• Sort the state. It puts each piece of game state into a NetworkVariable, a ServerRpc or a ClientRpc, using the profile's rules.
• Plan movement. It has players send inputs only, lets the server decide, and plans prediction and a correction on the client.
• Budget the data. It sets how often each kind of state updates and what must not be sent every frame.
• Plan Relay and Lobby. It uses Relay for player-hosted games and keeps only light, non-secret data in Lobby.
• Test and harden. It lists tests at set delays and a check that every server request validates its input.

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 unity-multiplayer-engineer 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/unity-multiplayer-engineer/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
• Who hosts the game, such as a dedicated server, a player host, or not decided
• Your Unity and Netcode for GameObjects versions
• Everything that must stay in sync, such as positions, health, items and score
• Your current networking scripts (optional)
• The lowest connection quality you want to support (optional)

Helpful context (optional)

• A list of your NetworkObjects and what each one does.
• Your test machine's results from Unity's simulated slow connection.

Tools and access

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

Functions and deliverables

• Unity multiplayer engineer agent: Plan Unity multiplayer with Netcode for GameObjects. Decide who owns what, what syncs and how to hide lag, with tests for slow links and cheaters.
  • A decision on who owns the game truth, with the tradeoff
  • A table that sorts each piece of state into the right Netcode tool
  • A plan for player movement and lag hiding
  • A bandwidth plan and a Relay and Lobby plan
  • A cheat check on every request the server accepts
  • A test plan for slow connections and busy matches
  Source: Michael Sitarzewski and Agency Agents contributors.
• Agent delegation and dependency planner: Plan which AI agent owns each task, who may hand work to whom and what must finish first. Get a delegation plan and failure test cases.
  • A delegation plan: for each handoff, who gets it, why, what they may do and what it waits for
  • An authority and depth check, listing any handoff that would be refused
  • What is logged for each handoff and each refusal
  • A failure checklist
  • Test cases using made-up agents and tasks
  • A list of missing inputs and checks that did not run
• Agent task ownership workflow builder: Plan a task table where one AI agent claims a task at a time, with expiring claims, blocked tasks and tests. Draft code only.
  • A list of gaps in the starter files, each with a fix
  • A draft task table, comment log and indexes
  • Claim, renew, release and recover functions
  • Changes to the TypeScript helper
  • Tests to run on a copy, starting with two claims at once
• Scoped base agent builder: Plan the smallest working AI agent for your codebase: job format, base class, an echo test handler and a smoke test, with every file named.
  • A list of files to add or change, each with its path and purpose
  • An interface map: the job going in, the result coming out, the base class methods and the echo handler
  • Setup steps in order
  • A smoke test plan on made-up data, each check marked run or not run
  • Open questions and checks that did not run
• 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

Tasks you can use it for

• You are starting a Unity co-op or competitive game and need to choose how it will sync.
• Your players see different things, or movement jumps when the connection is slow.
• You worry that a player could cheat by sending fake data to your server.
• You are adding Relay and Lobby and need to know what to put in each.

Limits to check before starting

• You use Godot. Use the Godot multiplayer designer.
• You use Unreal Engine. Use the Unreal multiplayer designer.
• You use Mirror, Photon or another network tool. This agent covers Netcode for GameObjects and Unity Gaming Services only.
• You only want to tidy your project's structure. Use the Unity software architect.

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 who hosts. List what must sync. Say MISSING for what you have not decided.
• Say "Plan this. Do not assume numbers I did not give." Your AI asks once for anything missing.
• Read the authority decision first. Make sure you agree with who owns the truth before you read the rest.
• Build the first piece in Unity, then run the test plan with simulated slow connections.
• Paste what you see back and ask for the next step.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/unity-multiplayer-engineer 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.