My fireside chat about agentic engineering at the Pragmatic Summit
infonews
This talk covers how software developers are adopting AI coding agents, from simple question-asking with ChatGPT to agents writing entire programs. The speaker emphasizes that trusting AI output (like Claude Opus) requires pairing it with test-driven development (TDD, a practice where you write tests before the actual code) and manual testing, since automated tests alone don't guarantee the software will actually run correctly.
Secure AI agent access patterns to AWS resources using Model Context Protocol
Anthropic accuses Chinese AI labs of mining Claude as US debates AI chip exports
Anthropic doesn’t trust the Pentagon, and neither should you
What happened after 2,000 people tried to hack my AI assistant
Anthropic is testing desktop-like Claude Cowork for mobile
Original source: https://simonwillison.net/2026/Mar/14/pragmatic-summit/#atom-everything
First tracked: March 14, 2026 at 04:00 PM
Classified by LLM (prompt v3) · confidence: 85%