Hire an AI real-time collaboration engineer

Everything it can hand back

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

• A table that sorts each piece of data by how it merges
• A plain statement of what users see when the connection drops
• A reconnect plan so no edit is lost or applied twice
• A plan for live cursors and who is online, kept apart from saved data
• A scaling plan for one busy room and for many small rooms
• A test list that attacks the design with bad networks

How it does the job well

• Design the reconnect before the connect. Every client tracks the last acknowledged sequence number and resumes from it. A connection that can't resume is a data-loss bug with a UX costume.
• Every operation is idempotent, keyed by a client-generated ID. Networks duplicate and retries re-send. Applying the same op twice must be a no-op, on the server and on every client.
• The server owns ordering; clients own intent. Client timestamps are wishes, not facts. Sequence numbers or Lamport clocks from the authority define order — wall clocks resolve nothing.
• Pick the convergence model per data type. A text field wants a CRDT or OT; a "status" dropdown wants last-writer-wins with server arbitration; a counter wants a CRDT counter, not a race. One document, several models — that's normal.
• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You are adding shared documents, a task board or live cursors to your app, like Google Docs does.

• Data map. Each field marked saved or live-only, with its merge rule and the reason for it.
• Promise to users. What users see offline, what saved means, and which clashes show on screen.
• Reconnect plan. How edits resume after a drop, how repeats are ignored and how order is kept.
• Live presence. What is shared, such as cursors, how long it lasts and how often it updates.
• Scaling plan. Separate plans for one busy room, many small rooms and deploys.
• Tests to run. Bad-network scenarios, each with what must be true afterwards.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• 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

• Sort the data. It labels each field as saved or live-only, and picks a merge rule for each, such as text merge, last save wins or add-one counters.
• Write the promise to users. It states what users see while offline, what "saved" means, and which clashes show on screen.
• Plan the reconnect. It numbers every edit, resumes from the last one the user got, and makes repeats harmless.
• Keep live presence apart. Cursors and who is online expire on a timer and never touch saved data.
• Plan for load. It treats one busy room and many small rooms as different problems, and plans for deploys that do not drop users.
• Plan the attack tests. It lists network cuts, long offline gaps and same-word edits, with what must be true after each.

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 engineering-realtime-collaboration-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/engineering-realtime-collaboration-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

• What people edit together, such as documents, a task board or a form
• The tech you use today, such as your web framework, database and hosting
• How many people share one room or document, and how many rooms you expect
• Whether it must work offline, and on which devices
• Your current sync code or data model (optional)
• Reports of lost or doubled edits, with what the user did (optional)

Helpful context (optional)

• A short list of the worst sync bugs your users reported, in their words.
• Your peak number of people in one document or room.

Tools and access

• Claude, ChatGPT or Gemini: A chat is enough to write the design. Paste your code so it can name the real gaps.

Functions and deliverables

• Real-time collaboration engineer: Plan live editing, shared cursors and offline sync for your app, with merge rules and network tests that prove no edit is lost.
  • A table that sorts each piece of data by how it merges
  • A plain statement of what users see when the connection drops
  • A reconnect plan so no edit is lost or applied twice
  • A plan for live cursors and who is online, kept apart from saved data
  • A scaling plan for one busy room and for many small rooms
  • A test list that attacks the design with bad networks
  Source: Michael Sitarzewski and Agency Agents contributors.
• Live app security tester: Run a safe security scan on your own staging web app or API. You get a list of weaknesses, the request behind each one, and how to fix them.
  • Findings by type and severity
  • The request that triggered each issue
  • Fix advice for each finding
  • A report you can share
  • A schedule for repeat scans
  Source: Burhan Sebin.
• Network launch planner: Plan a network launch for a marketplace or app that needs many users. Pick your first small group, win the hard side, and get a plan score out of 10.
  • The smallest network to launch in
  • Which side to win first and how
  • Density measures to track
  • Steps to move to the next group
  • A score for your plan
  Source: Wondel.ai.
• Live app readiness reviewer: Share a deployed app's code. Find problems with data rules, webhooks, credentials, payments and mobile use.
  • A list of gaps by area
  • A severity ranking
  • Fix suggestions
  • A saved report for later sessions
  Source: sickn33.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.

Tasks you can use it for

• You are adding shared documents, a task board or live cursors to your app, like Google Docs does.
• Two people edited the same record and one change vanished.
• Your app has to work offline on a phone and sync when the signal returns.
• Live updates work in your demo but you fear what happens at ten times the users.

Limits to check before starting

• You only need a page that refreshes every few seconds or a notification. A simple refresh plan is enough, and the Backend Architect agent can size it.
• Your app is down right now. Use the Incident response coordinator.
• You want the full system layout or a database choice. Use the Backend Architect agent or the 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 from this page and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then references/source-agent.md.
• List what people edit together and paste your data model or sync code if you have one.
• Add your user counts, devices and whether offline use matters. Say "Write the collaboration design. Ask me once if anything is missing."
• Check the data table first. Each row should name one merge rule, and each rule should make sense to your users.
• Run the tests it lists on a real slow or broken connection. The agent cannot run them for you.
• Take the design to your developers. Ask the agent to rewrite any part you do not follow in plain words.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-realtime-collaboration-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.