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 compensation analysts

Geographic Pay Differential Review Agent

Keep location pay tiers aligned with the market at a cost the company can afford

DecisionsAnalysisFinanceHuman resources
See how it worksGet access
Geographic Pay Differential Review Agent: what goes in, what the agent does and what you get

What it does

The company uses three location tiers set four years ago, but the market has moved. This agent compares market pay data by city with the company's tiers and finds cities where the gap is outside tolerance, such as a city now 12 percent above its tier. It models what it would cost to move each outlier city to a better tier, counting headcount and salaries affected. If the total exceeds a cost limit, it proposes phased changes over two cycles, and reruns the cost under the phased plan. It checks that no employee would lose pay and that the change leaves bands consistent. The comp lead approves any tier change. Edge case: a city with fewer than 10 data points is marked low confidence and left alone.

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, continueYes, continueApprovedNoNo 1 STARTS WHEN Annual review begins 2 USES A TOOL Load market data by city and the tier table 3 DOES Compare each city's market pay with its tier 4 CHECKS THE RESULT Does each flagged city have enough data points? If not: Mark low confidence and exclude from changes.Back to step 3. 5 USES A TOOL Model the cost of moving each outlier city 6 CHECKS THE RESULT Is the total cost within the limit? If not: Phase the changes across two cycles and rerunthe cost. Back to step 5. 7 DOES Check that no employee loses pay and bands stayconsistent 8 DOES Draft the recommendation with options and cost 9 YOU APPROVE Comp lead approves any tier change 10 RESULT Tier review report
Read the steps as a list
  1. Annual review begins
  2. Load market data by city and the tier table
  3. Compare each city's market pay with its tier
  4. Does each flagged city have enough data points?If not: Mark low confidence and exclude from changes. Back to step 3.
  5. Model the cost of moving each outlier city
  6. Is the total cost within the limit?If not: Phase the changes across two cycles and rerun the cost. Back to step 5.
  7. Check that no employee loses pay and bands stay consistent
  8. Draft the recommendation with options and cost
  9. Comp lead approves any tier changeThe agent waits here for your OK.
  10. Tier review report

How it decides

It flags a city when market pay differs from its tier by more than 5 percent with enough data. It phases changes when the cost passes the limit.

  • Flag a city 5 percent or more away from its tier
  • Require at least 10 data points per city
  • Phase changes when cost exceeds the limit
  • Never reduce an employee's pay as a result

Make it yours

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

  • Tolerance (default 5 percent)
  • Cost limit (default set by finance)
  • Minimum data points (default 10)
  • Phasing rule (default two cycles)

What keeps you in control

It always asks you first

  • Comp lead approves any tier change

Hard limits

  • Never change a tier or pay on its own
  • Never reduce pay
  • Mark low-confidence data clearly

It stops when

  • Done: Recommendation approved by the comp lead
  • Stop: Market data is not available, so hand to the comp lead

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 happensMarket data shows Austin 12 percent above its Tier 2. 140 employees are affected and moving them costs $610,000, above the $400,000 limit. The agent phases it, with 60 percent this year for $366,000. Check two passes. Denver has 7 data points and is left low confidence. The comp lead approves the Austin change.

More agents for compensation analysts

Research · Decisions

Salary Benchmark Research Agent

Give the client a defensible salary range with the reasons behind it.

9 steps1 check2 jobs
Decisions · Risk management

Pay Equity Check Agent

Pay changes that do not widen unexplained gaps and stay within budget

9 steps2 checks6 jobs
Creating · Executives and strategy

Total Rewards Statement Preparation Agent

Build accurate total rewards statements for every employee that tie to payroll.

10 steps1 check7 jobs
Decisions · Analysis

Compensation Band Maintenance Agent

Propose band updates for lagging roles that fit within the compensation budget.

10 steps1 check6 jobs