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 scrum masters

Team Health Trend Agent

Turn survey scores into a followed-up improvement with checked results

AnalysisIT and developmentProduct development
See how it worksGet access
Team Health Trend Agent: what goes in, what the agent does and what you get

What it does

The team fills in a health survey each sprint, and the results are looked at once and forgotten. After each survey this agent compares scores with earlier rounds and finds dimensions that are falling, such as workload or code quality. It links the changes to sprint events like incidents, scope changes, staff leave and releases. It proposes a topic for the retrospective with the evidence. After the retrospective it records what was agreed and checks the next survey to see whether the score moved. If it did not, it proposes a different angle. The scrum master approves what is raised with the team, since scores may reflect personal matters. Edge case: one low score from a single answer in a small team, so the agent notes anonymity risk.

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
ApprovedYes, continueNo 1 STARTS WHEN Survey results available 2 USES A TOOL Load the new and earlier survey rounds 3 DOES Find dimensions that fell or stayed low 4 USES A TOOL Read the sprint event log for the same periods 5 DOES Link falling scores to events 6 DOES Propose a retrospective topic with evidence 7 YOU APPROVE Scrum master approves what is raised with the team 8 USES A TOOL Record the agreed actions after the retrospective 9 USES A TOOL Read the next survey round 10 CHECKS THE RESULT Did the score for the targeted dimension improve? If not: propose a different angle or a different action.Back to step 6. 11 RESULT Trend report with follow-up status
Read the steps as a list
  1. Survey results available
  2. Load the new and earlier survey rounds
  3. Find dimensions that fell or stayed low
  4. Read the sprint event log for the same periods
  5. Link falling scores to events
  6. Propose a retrospective topic with evidence
  7. Scrum master approves what is raised with the teamThe agent waits here for your OK.
  8. Record the agreed actions after the retrospective
  9. Read the next survey round
  10. Did the score for the targeted dimension improve?If not: propose a different angle or a different action. Back to step 6.
  11. Trend report with follow-up status

How it decides

It flags a dimension that has fallen for two rounds or by 1 point or more and links it to events in the same sprints.

  • Flag a dimension falling in 2 rounds in a row
  • Flag a drop of 1 point or more on a 5 point scale
  • Suppress detail when fewer than 5 respondents
  • Check the effect only after one full sprint

Make it yours

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

  • Survey dimensions
  • Drop alert level (default 1 point)
  • Minimum respondents (default 5)
  • Event sources
  • Retrospective format

What keeps you in control

It always asks you first

  • Scrum master approves the retrospective topic
  • Scrum master approves sharing the trend with the team

Hard limits

  • Never reveal who gave which answer
  • Never raise a topic with the team without the scrum master

It stops when

  • Done: the targeted score improves or an alternate action is chosen
  • Stop: the team is too small to keep responses anonymous

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 happensScores for Workload fell from 4.1 to 3.4 over two rounds. The log showed two incidents and 30% added scope in the last sprint. The agent suggested a retrospective topic on mid-sprint additions. The scrum master approved. The team agreed to a rule for adding work. The next survey showed Workload at 3.5, an increase of only 0.1, so the check failed. The agent proposed a look at on-call load.

More agents for scrum masters

Analysis · Management

Team Retrospective Follow-through Agent

Retrospective actions judged by outcomes, not activity.

8 steps1 check3 jobs
Quality control · Compliance

Acceptance Criteria Test Mapping Agent

Make sure every accepted story has evidence for each of its acceptance criteria

11 steps1 check2 jobs
Risk management · Monitoring

Roadmap Commitment Risk Watch Agent

Warn early about at-risk commitments with options the owner can act on

11 steps1 check5 jobs
Risk management · Monitoring

Mid-Sprint Goal Health Agent

Spot a failing sprint goal while there is still time to act

11 steps2 checks3 jobs