Marketplace Triage Worker
Python worker for filtering marketplace leads before manual review.
Stack
Python, SQLite, JSONL ingestion, CLI worker, IMAP, crawler handoff, LLM triage, Telegram notifications
Proof angle
Shows lead-intake automation that applies deterministic filters before LLM triage and keeps handoff/notification state auditable.
Overview
A Python intake pipeline with SQLite queues, JSONL ingestion, deterministic hard filters, LLM triage, read-only IMAP intake, crawler handoff, CLI commands, audit trail, and Telegram notification boundaries.
Where this is relevant
Relevant for marketplace lead filtering, LLM triage, read-only mailbox intake, crawler handoff, queue state, replayable CLI workers, and human-reviewed automation.
AI / automation relevance
Hard filters run before model judgment so duplicates, bad parses, low-value budgets, blocked locations, and vague spam do not reach the review queue.
What it shows
- lead intake normalization before review
- duplicate checks and hard filters before LLM evaluation
- queue states, audit records, and replayable CLI processing
- mail-link extraction, crawler handoff, and Telegram notification boundaries