The fifteen problems · 01 of 15 · design

The stack was built English-first without anyone deciding that

Embeddings, extraction prompts, hybrid search, source evaluation and the validator were all designed against English. Nobody chose that. The required remedy, a hand-checked Amharic evaluation set, was named and never executed.

Embeddings, extraction prompts, hybrid search, source evaluation and the validator were all designed against English. The operator reframed the benchmark on 2 August 2026 as how well the system supports bilingual editors writing in English and Amharic for the largest possible audience, and the brief that followed recorded the risk in one line: Amharic retrieval quality is unmeasured and is the most likely weak link.

Rich Semitic root-and-pattern morphology degrades keyword matching; embedding quality on lower-resource languages varies unpredictably.

× What it broke

Nothing visibly, which is the danger. The named failure mode is the system quietly degrading into English-only support with Amharic as an output-translation step, and no measurement existed that would have shown it happening.

✓ What it established

The required remedy, never executed: measure retrieval and extraction quality in Amharic against a small hand-checked set before building anything that assumes parity with English. The durable asset is the evaluation set, not any model, because an evaluation set is reusable across model generations and a tuned checkpoint depreciates in months.

user-beadwork/briefs/BRIEF_ethiopia-site-delivery-tiers_2026-08-02.md (retrieval parity section) · 2026-08-02 · retrieved 2026-08-21

Ask your AI about this page

Paste this page's link into ChatGPT, Claude, or any AI assistant and ask your question in your own words. Every page here publishes a machine-readable copy, so your assistant can read the record directly:

https://ethiopia-build.stoagen.com/problems/01/

Published . Last updated . Times come from this page's revision history and can be checked against it.