Scoping, sequencing and gating a single-model car-price site from a 197-page topical map to a 199-URL launch in about 12 days, and what I chose not to build.
Topic
Content Systems
Projects
The product decisions behind a one-person AI content business: who it serves, where the quality bar sits, what I killed, and the honest numbers.
How I sequenced a CMS rebuild and AI workflows for desk editors in eight languages, kept the publish decision with each editor, and advised against funding an AI debate platform.
Writing
- Killing a content cluster on evidenceA question-page cluster built on a sound theory, then deindexed by Google. When to stop a reasonable bet, what counts as a verdict, and what to keep.
- Hybrid LLM Evaluation: Let Code Count, Let Models JudgeWhich parts of 'good' to give code and which to an LLM judge: per-dimension weights, hard caps, and publish bands as product decisions.
- Language Is Product, Not LocalizationBuilding for India's languages at ShareChat, Lokal, and a multilingual newsroom taught me that language changes the product, not just its strings.
- When Constrained Generation Beats Open GenerationLessons from shipping AI in a multilingual newsroom and running an eval-gated content pipeline: constrain the failure surface, not the model's talent.