Enrichment should add a traceable, reviewable interpretation to existing authorized data. It must not fabricate facts or infer sensitive traits. Separate source facts, deterministic derived values, model suggestions, and human-approved fields.

// concept

Define the Enrichment Contract

For a public business-description dataset:

// prompt — copy me5 lines

input: record_id, approved public description, source URL/version
output: category from allowed taxonomy, short summary, evidence span
never infer: owner identity, revenue, religion, ethnicity, political view, creditworthiness
state: SUGGESTED until accepted
retention: source and decision evidence only as required

Deduplicate input records and cache only when tenant, source version, prompt, model, and schema match. A source update invalidates enrichment.

Define reviewer disagreement categories such as wrong taxonomy, insufficient evidence, harmful inference, stale source, or unclear input. Report them by prompt/model/source version with minimum sample sizes. This turns corrections into an evaluation program instead of letting a workflow silently accumulate low-quality labels.

// concept

Build the Pipeline

// prompt — copy me4 lines

trigger → authorization/minimization → deterministic validation
→ AI structured suggestion → schema/policy validation
→ confidence/evidence gate → human review or accepted suggestion
→ write with provenance → metrics

Do not let the model browse arbitrary URLs. Retrieve approved content through a controlled fetcher with destination and size limits.

// worked_example

Worked Example

A Karachi marketplace categorizes seller-supplied public product descriptions into 12 catalog groups. Fifty labelled fixtures include ambiguous and bilingual copy. The model returns category, evidence quote limited to the source, and needs_human.

Unknown products route to review; the model cannot invent material, brand, warranty, or origin. Approved results store source hash, model/prompt/schema version, reviewer, and timestamp. A seller correction replaces the suggestion and triggers reevaluation.

// failure_cases

Failure Cases to Diagnose

6 cases to diagnose

Enrichment overwrites source fact
store separate SUGGESTED field.
No provenance
link input/version/model/reviewer.
Sensitive inference marketed as personalization
prohibit and audit.
Cached result crosses client/updated source
include tenant/version keys.
Model evidence not in input
reject.
Human corrections never feed evaluation
record labelled errors safely.

// pakistan_angle

Pakistan Angle

Test Roman Urdu and local product vocabulary with authorized examples. Do not assume a name, neighborhood, language, or price reveals customer class or protected traits.

For ecommerce, enrichment can suggest category or missing-field questions but cannot certify authenticity, halal status, safety, legal compliance, or warranty without authoritative evidence and qualified review.

// hands_on

Hands-On Exercise

5 steps

Write permitted/prohibited fields.
prepare 30 labelled synthetic/public fixtures.
build structured suggestion pipeline.
add evidence, cache versioning, and human review.
measure errors by category/language.

// completion_rubric

Completion Rubric

6 checks — tick as you verify

0/6

// sources

Sources

3 official sources — check every claim yourself

// check_yourself

Check yourself

4 questions · answers and options are taken word-for-word from this course

0/4

1 / 4 · diagnose
Your work shows this failure mode: “Enrichment overwrites source fact.” What does the lesson tell you to do about it?