SEOAI Tools
#06
2026-08-025 min read

161 agents ran the SEO audit. The skeptics killed half the findings before they reached a PR.

An eight-dimension ultracode audit ran 161 agents and roughly 7.7 million tokens against captainrandom.co.uk. The parallelism is a speed feature. The adversarial-verify pass is the quality feature — it killed roughly half the findings before they touched a branch.

Read post
Content PipelineBuild Log
#07
2026-08-015 min read

Thirteen sentences. Ten checked out. Three would have shipped wrong.

A mortgage rate-spike draft cleared ten of thirteen sentence-level checks and failed three. Without a corrective verifier, the three failing claims would have shipped alongside the ten correct ones. The 10/13 split is where LLM content pipelines silently break facts.

Read post
Build LogAI Tools
#08
2026-07-306 min read

Eight chapters, two Workflows: which parts of a course parallelise

Shipping the static-next-cpanel course via two ultracode Workflows revealed a clean partition: chapter bodies fan out to parallel agents without coordination cost; prerequisite ordering and the curriculum through-line do not.

Read post
Build LogAI Tools
#09
2026-07-275 min read

The verifier should gate sentences, not articles. A rescued mortgage draft showed why.

The April mortgage rate-spike draft had been queued for weeks. When the Monday cron finally produced it, 10 of 13 sentences passed verification. The right call was to fix the three that didn’t — not discard the article. That distinction reshapes the pipeline.

Read post
Build LogUK Calculators
#10
2026-07-255 min read

10 of 13 sentences made it. The verifier caught the rest before they reached a pillar page.

The June 30th cron produced a mortgage rate-spike draft grounded in April 2026 data. Ten of thirteen sentences passed. The three that didn't never reached a pillar page — and the next two days showed why that distinction matters at publishing scale.

Read post