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 service managers

Team Process Bottleneck Agent

The real bottleneck identified with evidence.

Team Process Bottleneck Agent: what goes in, what the agent does and what you get

What it does

Repeated delays often get blamed on the wrong step or the wrong team. When a manager asks why work is slow, this agent calculates time spent in each stage from the workflow records and separates waiting time from active work. It forms a hypothesis about the bottleneck and tests it against specific sample cases. If the evidence does not support it, for example delays track missing inputs rather than staffing, it revises the hypothesis and tests again. It writes an evidence-linked bottleneck review. Staffing decisions and ratings stay with the manager. Edge case: approvals look slow, but most of the time is spent waiting for missing documents.

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, continueNo 1 STARTS WHEN Delay question 2 USES A TOOL Calculate stage timing 3 DOES Form a delay hypothesis 4 USES A TOOL Test it on sample cases 5 CHECKS THE RESULT Does the evidence support it? If not: revise the hypothesis. Back to step 3. 6 DOES Write the bottleneck review 7 RESULT Evidence-linked bottleneck review
Read the steps as a list
  1. Delay question
  2. Calculate stage timing
  3. Form a delay hypothesis
  4. Test it on sample cases
  5. Does the evidence support it?If not: revise the hypothesis. Back to step 3.
  6. Write the bottleneck review
  7. Evidence-linked bottleneck review

How it decides

It tests the leading hypothesis on sample cases and revises when evidence disagrees.

  • Separate waiting time from work time.
  • Test inputs before staffing as a cause.
  • A hypothesis holds only if most sample cases support it.

Make it yours

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

  • Workflow record sources
  • Number of sample cases (default 30)
  • Time window analyzed (default last 90 days)
  • Report format

What keeps you in control

It always asks you first

  • Staffing decisions
  • Performance ratings

Hard limits

  • No blame.

It stops when

  • Done: bottleneck found.

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 happensA manager asked why contract approvals took 18 days on average. The agent found 11 days were waiting time at legal review. Its first hypothesis, too few reviewers, failed on 30 sample cases: delays matched missing information, not reviewer load. It revised the hypothesis and confirmed 22 of 30 cases waited for a missing risk form. The review was delivered on June 6.

More agents for service managers