Build LogAI Tools
#21
2026-06-205 min read

The S-4 cohort made two editorial pipeline decisions. I shipped them.

Two weeks of UK Calculators editorial pipeline sprints ended with two decisions that came from the cohort data, not preference: live Bank of England rate fetches and a constrained LLM composer. The pipeline silently stalled for four days after shipping.

Read post
Build LogEditorial Pipeline
#22
2026-06-136 min read

The prompt that made Haiku hallucinate, every single time

Every iteration of the UK Calculators redraft loop produced the same failure: Haiku returning plausible-sounding figures with no real source. The fix wasn't better prompting. It was removing the question entirely.

Read post
Build LogAgentic AI
#23
2026-06-126 min read

One osascript harness, two consumers — how skipping Archon kept the article pipeline stack composable

After the variant-picker shipped, the next call was architectural. Route thesis generation through Archon, or build a project-owned harness and own the primitive. The harness won. What emerged was a two-consumer pattern — thesis generation and voice rewriting off the same base — that Archon would have made awkward.

Read post
Build LogAI Tools
#24
2026-06-126 min read

Three articles cleared every gate. None of them cleared the style guide.

Phase 9 of the article pipeline auto-pipeline shipped on 2026-06-11. Within 24 hours I was manually patching three articles that had cleared every automated check but violated the style guide's em-dash budget on all three. The scrubber had the right rule. It was checking the wrong scope.

Read post
Build LogAI Tools
#25
2026-06-115 min read

Stop retrying the prompt: what the brief ledger taught the image harness

Four sessions into generating hero illustrations, I was still fixing the same structural mistakes on different posts. Each bad render was a lesson. The retry loop wasn't keeping them.

Read post