How Datadog built a universal machine tool for Claude Code

ℹ️ EPISODE INFO

Released

May 6, 2026

Duration

30m

Channel

Claude

Watch on YouTube

▶ Open ↗

📝 EPISODE DESCRIPTION

At Datadog, 90% of engineers adopted AI coding tools for production work in the last four months, with Claude Code driving two-thirds of that usage. As sessions grew more ambitious, the reusable tools they produced — for verification, debugging, orchestration — sprawled into unmaintainable one-offs. Sesh Nalla, VP of Engineering, shares how Datadog built Temper: a constrained framework that produces secure, reusable tools that compound across sessions and teams instead.

🧾 EPISODE SUMMARY

In this episode of Claude, How Datadog built a universal machine tool for Claude Code explores Datadog’s Temper: machine-tool discipline for agent-built software factories The speaker traces Datadog’s progression from human-built distributed systems to agent-assisted construction, culminating in a need for industrial-grade repeatability rather than one-off agent improvisation.

🔗 RELATED EPISODES

Memory and dreaming for self-learning agents

Getting started with Claude Cowork

Getting more out of the Claude Platform

Architecting for model step-changes: A fireside with Vercel's Guillermo Rauch

Building AI-native: Inside the stacks powering Cognition, Gamma, and Harvey

Live coding session with Boris Cherny and Jarred Sumner