§ delta-support-audit
Builder & triager
2026
Next.js 15 / TypeScript
OpenRouter → Claude Sonnet
Upstash Redis + Vector
BGE-large-en-v1.5 embeddings
RAG
Slack + Notion
Builder · RAG Quality System
Delta Support Audit
Nightly RAG audit of support articles for factual drift.
Articles audited
P0 true-positives (trial)
Wall-clock / run
Cost / run
Tab. 1 — key metrics
§ 01
The problem
Support content drifts. Freshdesk articles quietly fall out of step with the product docs and guides that are the real source of truth — and nobody notices until a customer is misled.
The system embeds 344 support articles (1,067 chunks) into a vector store and compares them against the canonical docs for contradictions and coverage gaps.
§ 02
How it works
RAG detectors classify each article for conflicts, contradictions and coverage gaps. P0 issues page a Slack channel; the full report lands in Notion. A Vercel cron runs the whole sweep at 04:00 IST.
On a 100-article trial it caught 14/14 P0 issues (100% true-positive) with a combined P0+P1 false-positive rate of 5–9% — at $2.45 and four minutes per run.
Fig. 2
Delta Support Audit — daily AI audit of Delta India support content with impact metrics
§ colophon
Stack
Next.js 15 / TypeScript · OpenRouter → Claude Sonnet · Upstash Redis + Vector · BGE-large-en-v1.5 embeddings · RAG · Slack + Notion · Vercel Cron