AI Engineer conference talk, May 2026, newly transcribed. A live-coded build of a minimal agent harness, tool registry, guardrails, a verify step that catches the agent's own false "done" claim, done in front of an audience with the prompt never touched. No new primitive, but a rare worked example of ones this lane already tracks.
In the News: August 11, 2026
Anthropic now permanently watermarks everything Claude writes; plus a runnable reference harness and a first-party Spotify judge-removal case study.
Morning edition
Machine-readable
Download Markdown
Story
Anthropic starts watermarking everything Claude writes
Every Claude model launched on or after August 2, 2026 now weaves an imperceptible watermark into its generated text and attaches signed C2PA provenance metadata to generated files. The marking applies worldwide, including outside the EU,…
Read story →
Story
Anthropic ships runnable reference harness code
The repository supplies three small, standalone hooks: a default-FAIL contract that blocks an agent from marking a results file "passing" until it has opened evidence, a screenshot or console log; a fresh-context evaluator subagent, with no…
Read story →
Story
Spotify removed its PR-verification judge once the models got good enough
Gustavsson describes Honk, Spotify's internal system for automating code changes across a backend monorepo of more than 20 million lines. Honk originally ran every proposed change past an LLM judge, which took its success rate from…
Read story →