Blog

What actually moves time to first token

Two months of latency work on a production chat agent: the wins, the ideas the measurements killed, and the numbers behind both.

August 24, 2026 · 6 min read

The tool definitions were the slow part

A 100% cache hit makes tokens cheaper, not invisible. Deferring the tool contracts halved our chat's time to first token.

August 12, 2026 · 2 min read

Four ways my evals lied to me

Every harness bug masquerades as a model result: false reds read as regressions, false greens read as coverage.

July 26, 2026 · 2 min read

Make your agent review its own work before you push

Fanning out parallel reviewers catches confident wrong answers. It also produces confident wrong findings.

July 22, 2026 · 2 min read

Taking the keys out of Rill

Replacing a plaintext MCP secret with OAuth, publishing the SDK, and moving a live site off Sanity.

July 21, 2026 · 6 min read

Zone 2 Training: Low, Mid, or High — Does It Matter?

July 21, 2026 · 2 min read

Startups Are Not a Marathon—They’re Marathon Training

July 21, 2026 · 2 min read

The only 7 knots you will ever need

July 21, 2026 · 2 min read

How zone 2 changes your muscles

July 21, 2026 · 2 min read

How urge surfing helps resist unwanted impulses

July 21, 2026 · 2 min read