Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for game designers

Game Telemetry Funnel Agent

Find where players drop off and why, every week

Game Telemetry Funnel Agent: what goes in, what the agent does and what you get

What it does

Every build changes how players move through the game, but nobody has time to dig through dashboards each week. This agent builds funnels for key player journeys: tutorial completion, first session, first purchase, level progress and return days. It finds the step with the largest new drop compared with the previous build. It then splits that step by platform, device, region and player type, and checks technical causes first, such as crashes and load times. If a technical cause does not explain the drop, it looks at design causes like a difficulty spike, using level data. It drafts one clear finding with evidence and a suggested test, such as an A/B change. The team lead decides the next step. Edge case: a drop that only appears on low-memory phones points to performance rather than design.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Weekly review 2 USES A TOOL Build funnels for key journeys 3 DOES Find the largest new drop 4 USES A TOOL Split by platform, device and region and checkcrashes and load times 5 CHECKS THE RESULT Is the cause explained? If not: check level and difficulty data for designcauses. Back to step 4. 6 USES A TOOL Draft finding and suggested test 7 YOU APPROVE Team lead decides next steps 8 RESULT Finding logged
Read the steps as a list
  1. Weekly review
  2. Build funnels for key journeys
  3. Find the largest new drop
  4. Split by platform, device and region and check crashes and load times
  5. Is the cause explained?If not: check level and difficulty data for design causes. Back to step 4.
  6. Draft finding and suggested test
  7. Team lead decides next stepsThe agent waits here for your OK.
  8. Finding logged

How it decides

It focuses on the largest new drop and rules out technical causes before design causes.

  • Technical causes first
  • Compare with the previous build
  • One focus drop per week

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Journeys tracked
  • Splits
  • Review day
  • Report recipients

What keeps you in control

It always asks you first

  • Starting tests or fixes

Hard limits

  • Read-only data
  • Never changes live config

It stops when

  • Done: finding logged
  • Stop: telemetry broken

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensAfter the June 3 update, tutorial completion fell from 78% to 64%. The first split by platform did not explain it, so the agent kept digging. By device, the drop was only on Android phones under 4 GB of memory, where step 3 took over 20 seconds to load. It reported a performance cause and suggested lighter textures for that step. The team lead approved the fix for the next patch.

More agents for game designers