home / skills / coowoolf / insighthunt-skills / controllable-inputs-framework

controllable-inputs-framework skill

/product-growth/controllable-inputs-framework

This skill helps you apply controllable input metrics to diagnose growth, prioritize actions, and sustain a flywheel without chasing lagging outputs.

npx playbooks add skill coowoolf/insighthunt-skills --skill controllable-inputs-framework

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
4.0 KB
---
name: Controllable Inputs Framework
description: Focus on Input Metrics (selection, price, speed) rather than Output Metrics (revenue, stock price). Inputs are controllable and causal; outputs are lagging. Amazon's flywheel philosophy.
---

# The Controllable Inputs Framework

> "If we served customers well... things like sales, revenue... and share price... would follow. We took it as an article of faith." — Bill Carr

## What It Is

A management focus on **"Input Metrics"** (controllable activities like selection, price, speed) rather than **"Output Metrics"** (lagging indicators like revenue, stock price), often conceptualized as a Flywheel.

## When To Use

- When defining **OKRs**
- Conducting **weekly business reviews (WBR)**
- When **growth stalls** and you need to diagnose
- Avoiding **short-term reactive** decision making

## Inputs vs. Outputs

```
┌─────────────────────────────────────────────────────┐
│  OUTPUT METRICS (Lagging)                           │
│  ❌ Revenue                                         │
│  ❌ Stock price                                     │
│  ❌ Active users                                    │
│  → Results of past actions                          │
│  → Not directly controllable                        │
├─────────────────────────────────────────────────────┤
│  INPUT METRICS (Leading)                            │
│  ✅ Selection (# of products)                       │
│  ✅ Price (% below competition)                     │
│  ✅ Speed (delivery time)                           │
│  → Actions you take today                           │
│  → Directly controllable                            │
└─────────────────────────────────────────────────────┘
```

## The Amazon Flywheel

```
                    ┌─────────────────┐
                    │  Better Customer│
                    │   Experience    │
                    └────────┬────────┘
                             ↓
┌─────────────────┐    ┌─────────────────┐
│  Lower Prices   │←───│  More Traffic   │
└────────┬────────┘    └─────────────────┘
         ↓                     ↑
┌─────────────────┐    ┌─────────────────┐
│  Lower Cost     │    │  More Sellers   │
│  Structure      │───→│  More Selection │
└─────────────────┘    └─────────────────┘
```

## How To Apply

```
STEP 1: Identify Your Flywheel
└── What inputs drive customer experience?
└── How do they compound?

STEP 2: Define Input Metrics
└── Each must be controllable
└── Each must have causal link to outputs

STEP 3: Measure Continuously
└── Weekly Business Reviews (WBRs)
└── Real-time dashboards

STEP 4: Resist Output Obsession
└── When output dips, diagnose inputs
└── Don't panic-optimize the output directly
```

## Common Mistakes

❌ Confusing **outputs** (active users, revenue) with **inputs**

❌ Creating "compound metrics" that **obscure root cause**

❌ Reacting to **output dips** with short-term hacks

## Real-World Example

Amazon focused on "Selection" (number of detail pages) and "Lower Prices" as inputs, believing they would drive the output of "Free Cash Flow" via the Flywheel effect.

---
*Source: Bill Carr, Co-author of "Working Backwards", Lenny's Podcast*

Overview

This skill teaches the Controllable Inputs Framework: focus on leading, controllable input metrics (selection, price, speed) rather than lagging output metrics (revenue, stock price). It frames those inputs as a flywheel that compounds customer experience and long-term results. The aim is to create operational clarity so teams act on things they can control and measure every week.

How this skill works

You identify the core flywheel for your product or business by mapping the inputs that directly drive customer experience. For each input you define simple, controllable metrics with causal links to outputs. Measure those inputs continuously (WBRs, dashboards) and use them to diagnose output changes instead of reacting to outputs directly.

When to use it

  • Setting OKRs or operational goals
  • Running weekly business reviews (WBRs) and dashboards
  • Diagnosing stalled growth or unexpected output drops
  • Designing experiments that change controllable activities
  • Preventing short-term hacks that optimize outputs at the cost of inputs

Best practices

  • Pick a small set (3–6) of true inputs that teams can control and influence
  • Ensure each input has a clear causal path to outputs; discard fuzzy compound metrics
  • Instrument inputs for frequent reporting—weekly is typical for WBRs
  • Use input metrics to design experiments and prioritize interventions
  • When outputs move, trace back to inputs before taking corrective action
  • Treat the flywheel as system-level — optimize interactions between inputs, not just one metric

Example use cases

  • A marketplace measures selection (detail pages), seller count, and price competitiveness to grow GMV over quarters
  • A logistics team focuses on speed (fulfillment time) and on-time rate to reduce churn
  • A consumer product team tracks assortment breadth and in-stock rate to improve conversion
  • A subscription business uses onboarding speed and feature activation as inputs to predict churn
  • Leadership uses WBRs to surface input trends and align cross-functional fixes

FAQ

Why not just optimize outputs like revenue or active users?

Outputs are lagging and often noisy. They reflect many historical decisions and external factors. Optimizing inputs targets actions teams can control and that causally drive outputs over time.

How many input metrics should I track?

Keep it small—typically 3–6. Too many inputs dilute focus; too few can miss important levers. Each should be directly controllable and clearly linked to outcomes.