Continuous Calibration, Continuous Development (CCCD)
by Keith Coleman & Jay Baxter • Product Lead & Founding ML Engineer at Community Notes (X)
Keith Coleman and Jay Baxter lead the Community Notes team at X (formerly Twitter). Keith, a former product leader, and Jay, a machine learning engineer, developed the open-source, crowd-sourced context system that uses bridging algorithms to combat misinformation.
🎙️ Episode Context
Keith Coleman and Jay Baxter discuss the origins, principles, and engineering behind Community Notes. They reveal how a small, 'thermal' team used dynamic goal-setting and a unique bridging-based algorithm to build a decentralized fact-checking system that scales effectively where traditional methods failed. The conversation covers the transition from Birdwatch, the impact of open-sourcing the algorithm, and the operational philosophy of 'Continuous Calibration' that allows them to move rapidly.
Problem It Solves
Prevents the bureaucratic slowdown and misalignment common in large organizations, allowing small teams to ship internet-scale solutions rapidly.
Framework Overview
A dynamic operational model that rejects rigid long-term planning (like quarterly OKRs) in favor of high-frequency goal setting and execution. The team aligns daily via a simple shared document and recalibrates their roadmap as often as bi-weekly based on immediate data feedback.
🔄 Iterative Cycle
When to Use
When operating a small, high-trust team ('Thermal team') tackling ambiguous or rapidly changing problems.
Common Mistakes
Sticking to outdated OKRs despite new data; allowing team focus to fragment across multiple projects.
Real World Example
The Community Notes team scaling from a small pilot to a global feature by adjusting their roadmap weekly based on pilot data, without formal quarterly planning.
We set our goals very dynamically... We might change our roadmap multiple times in two weeks based on what we see.
— Keith Coleman & Jay Baxter