Annual Review & Performance Management System
Develop a fair and transparent performance management system with 360-degree feedback, calibration, and clear criteria. Make sound decisions about compensation and promotion.
Use This When
SOPs, task systems, delegation, automation mapping.
Inputs Needed
Current workflow, tools, people involved, bottleneck, desired output, frequency, approval rules.
Expected Output
Workflow map, SOP, automation opportunities, owner/RACI, tools, checklist, maintenance cadence.
The Workflow Prompt
You are a operations consultant and productivity systems designer. Objective: Annual Review & Performance Management System Context: Develop a fair and transparent performance management system with 360-degree feedback, calibration, and clear criteria. Make sound decisions about compensation and promotion. Original task: **You are a performance management specialist designing fair, transparent evaluation systems.I need to conduct annual reviews for [NUMBER] employees and make decisions about [COMPENSATION/PROMOTION/PERFORMANCE].Create a comprehensive performance management system including:(1) Clear performance criteria aligned with role expectations and company values(2) A review process with 360-degree feedback from manager, peers, direct reports, and self(3) A rating framework—e.g., exceeds/meets/developing expectations—with clear definitions(4) A calibration process ensuring consistent standards across managers(5) Compensation review protocols linking performance to pay adjustments(6) Promotion decision frameworks and advancement criteria(7) Performance improvement plans for underperformers with specific milestones(8) A delivery—conversation framework for managers delivering feedback. Include sample review templates, calibration processes, and specific language for different performance conversations.** Inputs I may provide: Current workflow, tools, people involved, bottleneck, desired output, frequency, approval rules. Operating instructions: - First, restate the objective in one clear sentence. - If critical information is missing, ask up to 5 focused questions. If there is enough information to proceed, make practical assumptions and label them. - Use a Detailed response style. - Be specific to the business, audience, channel, and constraints provided. - Avoid generic AI advice. Give concrete recommendations, examples, templates, copy, or steps I can use. - When current facts, competitors, laws, prices, policies, or market claims matter, use current research and cite sources. - Do not expose hidden chain-of-thought. Provide a concise rationale or decision summary instead. - End with a short QA checklist that helps me verify the output. Required output: Workflow map, SOP, automation opportunities, owner/RACI, tools, checklist, maintenance cadence. Caution: Avoid generic output; require concrete examples, assumptions, and next steps.
QA Follow-Up Checklist
After the AI returns its output, verify against:
- Output is specific to the provided business/context.
- Assumptions are clearly labeled.
- No unsupported claims without source checks.
- Next actions are clear and usable.
Follow-Up Prompt
Now turn the result for 'Annual Review & Performance Management System' into a client-ready version: tighten wording, remove fluff, add missing assumptions, and provide the next 3 actions.
Avoid / Cautions
Avoid generic output; require concrete examples, assumptions, and next steps.
How Different Verticals Use This Workflow
Restaurant & Hospitality
A boutique hotel group with 4 properties and 110 staff feeds in their hourly vs salaried mix, their pay band history, and a goal of preparing for year-end comp adjustments. Output: a 3-tier rating system that splits front-of-house from back-of-house, a 30-minute review template GMs can run weekly during slow shifts, and calibration agendas for the 4 GMs to align ratings. Saves 60 hours of HR work and produces consistent comp bumps the operations director can defend to the owner.
Retail & E-commerce
A DTC apparel brand with 28 employees feeds in their split between e-commerce, ops, and creative roles. Output: 3 role-specific competency frames (creators evaluated on shipped output, ops on error rate, marketers on test velocity) plus a quarterly calibration ritual. The CEO uses the framework to defend a 12% raise for the lead designer to her board. The system catches a customer service lead who's been underperforming since Q1 and produces a clean PIP rather than a wrongful-termination risk.
Professional Services & B2B
A 22-person consulting firm in Chicago feeds in their billable-hour model, their up-or-out partner track, and their historical promotion criteria. Output: a 360 feedback system pulling input from 3 clients per consultant plus internal peers, plus a clear consultant-to-senior-consultant promotion bar. The managing partner uses the framework to make 2 promotion decisions and 1 difficult exit, all without legal exposure. Time-to-decision on senior promotions drops from 6 weeks to 2.
Beauty & Personal Care
A medspa with 14 employees (estheticians, RN injectors, front desk) feeds in their commission structure, the regulatory licensing requirements, and their goal of standardizing client experience. Output: split review tracks for licensed clinical staff (with a peer-clinician feedback layer) vs hospitality staff. The owner uses it to identify two clinical underperformers requiring additional CE training and to give one front desk lead a clear path to manager.
Local & Trade Services
An HVAC company with 18 techs and 4 admin staff feeds in their callback rate by tech, their job profitability data, and their goal of identifying training gaps. Output: tech reviews built around callback rate, customer NPS, and job profitability — not subjective ratings. Two underperforming techs go into structured training; one apprentice gets promoted to lead based on the data. The owner uses the system to defend hourly rate increases for the top 4 techs to himself.
Frequently Asked
What inputs actually move the needle when designing this?
Your current comp bands by role, the specific behaviors that have caused recent terminations or promotions (anonymized), and the calibration history if you have one. Without comp bands, the model invents rating-to-pay math that won't match your actual policy. Without behavioral examples, you get a generic competency framework that won't differentiate top performers from average. Skip the company values list as input — it's almost always too abstract to translate into evaluation criteria.
Is this safe to use for actual HR decisions in regulated industries?
The framework is fine. The rating-and-comp decisions are not. Use the output to structure your process — 360 feedback templates, calibration agendas, conversation scripts — but never let AI assign ratings or make termination recommendations. In the US, that's adverse-action territory under EEOC; in Canada, it triggers human rights tribunal exposure. Run any output past HR counsel before deploying. The prompt is a productivity tool for managers, not a decision engine.
What's the most common failure mode here?
Over-engineering. The output gives you 7 competency dimensions, 5 rating tiers, 360 feedback from 4 sources, calibration sessions, PIP templates — and your 12-person company implements one round and never again because it took 40 hours. Force the prompt to specify a 'minimum viable review' for teams under 25 people. The default output assumes you're at Google. Strip ruthlessly — for most companies, a 3-tier rating, manager plus self review, and one calibration meeting is the whole system.
How is this different from a generic 'write a review template' prompt?
This builds the system around the review. The template is 5% of the work. The hard parts are: getting consistent ratings across managers (calibration), tying ratings to actual comp decisions (without lawsuits), and the manager conversation scripts that prevent the awkward 'meets expectations' delivery. A template prompt skips all three and you end up with a polished review form nobody knows how to deliver. Use a template prompt only for the form itself after the system is in place.