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 vice president of strategies

Strategy Experiment Coordination Agent

Every strategic experiment reaches a decision at its checkpoint, based on its original rules.

Strategy Experiment Coordination Agent: what goes in, what the agent does and what you get

What it does

Strategic experiments, such as a new pricing test or a pilot market, often run on without a clear decision rule. Teams argue over results that were measured differently. At each checkpoint date this agent checks that measurement is complete against the experiment charter and that the outcome definitions have not changed. If data is missing, it creates a collection task first. If a definition changed mid-way, it flags it and splits the results before any conclusion. It then computes the agreed outcomes against the charter's thresholds and prepares continue, revise or stop options with the history. The strategy director makes the decision. Edge case: a result that passes the threshold only on a partial sample is labeled as not yet decidable.

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 Checkpoint date reached 2 USES A TOOL Check measurement coverage against the charter 3 CHECKS THE RESULT Is measurement complete and the definitionunchanged? If not: create a data task or flag the definitionchange. Back to step 2. 4 USES A TOOL Compute outcomes against thresholds 5 DOES Prepare continue, revise or stop options 6 YOU APPROVE Strategy director decides 7 RESULT Checkpoint decision packet with history
Read the steps as a list
  1. Checkpoint date reached
  2. Check measurement coverage against the charter
  3. Is measurement complete and the definition unchanged?If not: create a data task or flag the definition change. Back to step 2.
  4. Compute outcomes against thresholds
  5. Prepare continue, revise or stop options
  6. Strategy director decidesThe agent waits here for your OK.
  7. Checkpoint decision packet with history

How it decides

It checks completeness before outcomes, and recalculates once missing data arrives.

  • Ready to decide: only with complete data and unchanged definitions.
  • Option framing: continue, revise or stop based on the charter's thresholds.
  • Definition change: split results by period and judge only the consistent part.
  • Partial sample: label the result as not yet decidable.

Make it yours

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

  • Checkpoint schedule per experiment (default as set in the charter)
  • Minimum data coverage before deciding (default 95% of planned measurements)
  • Thresholds for continue, revise and stop
  • Format of the decision packet (default one page plus data appendix)
  • Who decides (default the strategy director)

What keeps you in control

It always asks you first

  • Expanding spend
  • Changing success criteria
  • Ending contractual commitments

Hard limits

  • Never changes success criteria.

It stops when

  • Done: decision packet ready.

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 happensAt the halfway checkpoint of a pricing pilot on June 30, the agent finds 'active customer' was redefined in week 5, so the check fails. It flags the change and splits results into before and after. Only the later period can be judged: conversion is 3.8% against a 3.5% threshold. The agent prepares a continue option with a note. Strategy director Leon Marsh approves continuing.

More agents for vice president of strategies