Sign inGet started
Skills / Product-management

RICE Prioritization

We needed a way to compare very different types of projects and make our best case for why they deserved to be prioritized — a consistent, shared language for decisions.

RICE is a quantitative prioritization framework that assigns a numerical score to each product initiative using the formula: (Reach × Impact × Confidence) ÷ Effort. Developed by Sean McBride at Intercom, it replaces gut feel and political influence with structured, repeatable estimation. It's built for product managers and teams who need a defensible way to rank their backlog without defaulting to whoever argues loudest.

By Sean McBride · Free
Specimen 01 · Live diagnosisRICE Prioritization
Input

“I have about 8 features we're debating for next quarter. We keep going in circles and everyone has a different favorite.”

Diagnosis
I use the RICE formula — (Reach × Impact × Confidence) ÷ Effort — to turn your backlog into a ranked, defensible list.
Full transcript ↓
Calibrated referenceagent-skills.ai
The gap

Score every idea by reach, impact, confidence, and effort — then let the math decide

RICE uses a single formula to score any product initiative: (Reach × Impact × Confidence) ÷ Effort. Reach is the number of users or events affected per time period, measured in real units (e.g., customers per quarter). Impact uses McBride's fixed 5-point multiplier scale — 3 for massive, 2 for high, 1 for medium, 0.5 for low, 0.25 for minimal — to capture per-person value rather than total volume. Confidence is expressed as a percentage (100%, 80%, or 50%) that functions as an uncertainty penalty, directly discounting scores when estimates lack supporting data. Effort is total person-months required across all contributors. The output is a ranked table where every initiative has a comparable, defensible score — exposing counter-intuitive rankings that gut feel and the HiPPO effect (Highest Paid Person's Opinion) would have buried.

The problem

Product backlogs fill with ideas that feel equally urgent, and prioritization defaults to whoever argues loudest or holds the most seniority — the HiPPO (Highest Paid Person's Opinion) problem. Most teams either skip scoring entirely or use vague 1-5 ratings that mean different things to different people in different meetings. RICE was designed specifically to remove these distortions by encoding reach, depth of impact, and honest uncertainty into a single comparable number that any team member can inspect and challenge.

The solution

Score your entire backlog in under an hour and walk into your next planning meeting with a ranked list backed by explicit, auditable math — not gut feel or organizational gravity.

You bring
  • A list of features, projects, or initiatives you want to prioritize
  • Rough estimates of user reach and team effort for each item
  • Any signals about potential impact — user research, support tickets, analytics, stakeholder input
  • A time horizon for Reach estimates (e.g., per quarter or per month)
You get
  • A RICE score for each initiative using the exact (Reach × Impact × Confidence) ÷ Effort formula with McBride's fixed scales
  • A ranked priority table with all four component scores visible side-by-side for every item
  • Flagged confidence assumptions — places where estimates are speculative and should be downgraded before presenting to stakeholders
  • Interpretive notes on surprising inversions: items that felt like obvious priorities but rank low due to high effort or honest confidence levels
In action

Watch the methodology work.

Three specimens from a single real session: the same situation, unaided and calibrated, the full transcript, and the skill answering live in the channel where the work happens.

Fig.01The same situation, two ways
Specimens A · B
Specimen AVague
Unaided

“You have 8 features on the Q3 roadmap debate list. Three engineers insist the API redesign is critical infrastructure. Your VP wants Salesforce integration because an enterprise prospect mentioned it twice. Two PMs are split between a performance overhaul and a redesigned onboarding flow. Every planning meeting ends with a list of 'high priority' items that hasn't changed in three weeks. The feature that wins is the one whose champion showed up most prepared to argue.”

×Vague — nothing concrete to act on.
Specimen BCalibrated
With RICE Prioritization

“Every feature has a RICE score: accounts per quarter, McBride's fixed impact multiplier, an honest confidence percentage that reflects actual evidence, and real effort estimates from the team. Salesforce integration scores 75 — not 150 — once the sales team's speculative confidence is corrected from 100% to 50%. CSV export scores 80 and claims the #1 slot. Your VP sees the math, understands exactly which assumption drove the ranking, and the conversation shifts to 'what would it take to get higher confidence on Salesforce' rather than 'why isn't Salesforce first.' The planning meeting takes 45 minutes.”

Specific, grounded, and ends with one clear next step.
Fig.02A real session, unedited
In-app · assistant
RICE PrioritizationClaude
RICE Prioritization
I use the RICE formula — (Reach × Impact × Confidence) ÷ Effort — to turn your backlog into a ranked, defensible list. To get started: are you scoring a single initiative to sense-check it, or do you have a set of items you want to rank against each other?
I have about 8 features we're debating for next quarter. We keep going in circles and everyone has a different favorite.
Classic HiPPO problem — the loudest voice or most senior person wins instead of the best evidence. Let's fix that with RICE. Before we score anything, I need one definition locked in: what's your Reach time period and unit? Reach has to be measured in real, countable units over a specific window — 'customers per quarter,' 'accounts per month,' 'sessions per week.' What fits your product best?
We're B2B SaaS, about 400 active accounts. 'Accounts per quarter' seems right.
Perfect — 'accounts per quarter, ceiling of 400' is your Reach definition. We'll use that consistently for every item. Now give me your first feature, and I'll walk you through all four components: how many accounts it touches per quarter, how much it moves the needle per account (fixed scale: 3=massive, 2=high, 1=medium, 0.5=low, 0.25=minimal), how confident you are in those estimates (100%, 80%, or 50%), and total person-months to ship. What's item one?
Bulk CSV export. It comes up constantly in support tickets. I'd say 200 accounts would use it, medium impact, pretty confident, maybe 2 person-months.
Let me lock those in. Reach: 200. Impact: 1 (medium). Confidence: you said 'pretty confident' — I'd suggest 80%, not 100%, since support tickets give you qualitative signal but not hard usage data. Effort: 2 person-months. RICE score: (200 × 1 × 0.8) ÷ 2 = 80. That's your first baseline. Notice that honest 80% confidence cost you 20 points — at 100% this would have scored 100. What's next?
Salesforce integration. Our VP and sales team have been pushing hard for it. I'm thinking 300 accounts, massive impact, 100% confident, 6 person-months.
I need to flag the 100% confidence before we calculate. 100% means you have strong data that 300 accounts will see massive impact. What's that evidence based on — usage analytics, customer research, signed contracts? Or is it primarily the sales team's belief about what prospects want? If it's the latter, this is exactly the scenario the confidence penalty is designed to catch. At 50% (speculative): (300 × 3 × 0.5) ÷ 6 = 75 — slightly below CSV export. At 100% (high confidence): 150 — easily #1. That's a 2x swing based entirely on how honest you are about the evidence. What does the data actually support?
Honestly? It's mostly the sales team's gut feeling from a few enterprise calls. I didn't realize that would hit the score that hard.
That's exactly why RICE works. Salesforce integration at 75 vs. CSV export at 80 means your most politically-charged feature might not beat a straightforward usability fix — not because Salesforce is unimportant, but because the uncertainty is real and should be encoded. When you present this ranking, the conversation shifts from 'who wants what' to 'what evidence would raise our confidence on Salesforce to 80% or 100%.' That's a much more productive debate. Ready to score the next six?
Reply to RICE Prioritization
What the skill is doing
01RICE Score Calculator
02Backlog Scoring Session
03Confidence Calibration Check
Fig.03The same skill, in the channel you already use
WhatsApp · live
9:41
RPRICE Prioritizationtyping…
Messages are end-to-end encrypted. No one outside of this chat can read them.
Today
I have about 8 features we're debating for next quarter. We keep going in circles and everyone has a different favorite.9:14✓✓
I use the RICE formula — (Reach × Impact × Confidence) ÷ Effort — to turn your backlog into a ranked, defensible list.9:14
To get started: are you scoring a single initiative to sense-check it, or do you have a set of items you want to rank against each…9:15
Message

The same skill, where the work happens.

No new app to learn. The methodology runs over the WhatsApp Business API, so the answer lands as a reply in the thread you’re already in — same rigour, zero context-switch.

Reads the situation, names the pattern, returns one concrete next move.
Delivered in seconds, inside a conversation that already exists.
Specimen · WhatsApp Business API · live
Capabilities

What it does, specifically.

Each capability is a distinct move drawn straight from the source methodology — not a generic assistant guessing.

CapabilityC-01

RICE Score Calculator

Guides you through estimating each of the four RICE components for a single initiative, applying McBride's fixed scales and returning the calculated score. Prompts you with concrete examples when estimates feel uncertain and catches the most common errors — especially forgetting to time-bound Reach and defaulting to 100% Confidence without supporting data.

Based on McBride's formula RICE = (Reach × Impact × Confidence) / Effort, using the fixed Impact multiplier scale (3/2/1/0.5/0.25) and Confidence tiers (100%/80%/50%) as defined in the original Intercom framework.
CapabilityC-02

Backlog Scoring Session

Takes a full list of initiatives and systematically scores each one using RICE, maintaining definitional consistency across the entire set. Prevents the calibration drift that happens when the same word means something different by item 10 vs. item 1, and flags whenever an estimate seems inconsistent with how you scored a comparable item.

Implements McBride's core guidance that RICE scores are only meaningful relative to other items in the same set — requiring a single Reach time period, consistent Impact scale interpretation, and comparable Effort units across all items being ranked.
CapabilityC-03

Confidence Calibration Check

Identifies when a Confidence estimate is inflated relative to the available evidence. Asks what data, user research, or precedent supports the estimate and suggests downgrading to 80% or 50% when estimates rest on assumption rather than evidence — preventing overconfidence from distorting the final ranking.

Based on McBride's design intent that Confidence functions as an 'uncertainty penalty': teams who have no supporting data but default to 100% are defeating the anti-overconfidence purpose of the framework, producing scores that look precise but encode wishful thinking.
CapabilityC-04

Reach Time-Bounding Coach

Helps you define and consistently apply a Reach time period and unit of measurement across all items in your backlog. Distinguishes between B2C contexts (users per quarter), B2B contexts (accounts per quarter), and event-based products (sessions per month), preventing the most common RICE calibration error: using different time windows or mixed units across items.

Implements McBride's requirement that Reach be time-bounded (e.g., per quarter) and measured in real, countable units — not percentages, relative size labels, or vague descriptors — extended here to cover B2B account-level Reach which the original post treats briefly.
CapabilityC-05

Ranked Priority Table Generator

Outputs a formatted table of all scored initiatives sorted by RICE score, with every component value visible in separate columns. Surfaces inversion cases — items that felt like obvious top priorities but rank low due to high effort or honest confidence levels — and explains what's driving the counter-intuitive ranking in plain language.

Reflects McBride's worked examples in the original Intercom post (e.g., a checkout flow redesign scoring 240 vs. a tooltip feature scoring 30), where the ranked output with score breakdowns is the primary deliverable — making the reasoning behind each ranking transparent and defensible to stakeholders.
Tested

Graded before it shipped.

Every skill is scored against independent scenarios for methodology fidelity before it goes live — not vibes, a rubric.

What it produces
OutputD-01

RICE Scored Backlog Table

A formatted table with columns for initiative name, Reach, Impact multiplier, Confidence percentage, Effort (person-months), calculated RICE score, and rank. Each row shows the full score breakdown so any team member can inspect exactly what's driving priority — and challenge individual estimates rather than the overall conclusion.

OutputD-02

Confidence Audit Report

A flagged list of items where Confidence estimates were downgraded during scoring, showing the original estimate, the revised estimate, and the evidence gap that triggered the change. Designed to share with stakeholders who ask why certain seemingly-important items were de-prioritized.

OutputD-03

Reach Calibration Baseline

A one-page specification of your Reach parameters: the time period, the unit of measurement (users, accounts, events), and how to count users across different product surfaces — so every future scoring session uses the same calibration and scores remain comparable quarter over quarter.

The source

Grounded in the original work.

Every answer traces back to a real source and the practitioner who wrote it — not a secondhand summary. Here is the source of record.

Source authorA-01

Sean McBride

Sean McBride created the RICE framework while working as a product manager at Intercom, publishing the methodology in a 2016 blog post that became one of the most widely cited prioritization references in product management. The framework has since been incorporated into PM bootcamps, training programs, and curricula worldwide, and is referenced in hundreds of product management courses and books.

Status · Inspired by Sean McBride’s work — not yet claimed. Are you Sean McBride?
Primary sourceS-01

RICE: Simple Prioritization for Product Managers (Intercom Blog, 2016)

by Sean McBride

Product manager at Intercom; creator of the RICE scoring framework, widely cited in PM literature and training programs globally.

Read the original ↗
Citationintercom.com
In the build queue

Be first to run it.

RICE Prioritization is being built right now. Leave your email and we’ll tell you the moment it goes live.

Notify meEmail
At launchI have a backlog of features to prioritize for next quarter and we keep going in circles in planning meetings. Can we run a RICE scoring session? I'll give you the list and we can work through Reach, Impact, Confidence, and Effort for each one.