Recent work.

A two-sided marketplace was processing hundreds of publisher submissions weekly through manual review and routing. The ops team was the bottleneck for every transaction, and quality was inconsistent across reviewers.

A Zoom → n8n → Claude pipeline that captured intake calls, scored submissions against a structured rubric, routed approved publishers into the right marketplace tier, and flagged edge cases for human review. Eval framework wrapped around it to monitor scoring drift over time.

A multi-team services company knew they were behind on AI but had no internal capability, no roadmap, and no clear first wins. Leadership wanted real production deployments, not a pilot graveyard.

90-day audit and roadmap covering 12 candidate workflows. Prioritized three for immediate build: client deliverable QA, capacity planning, and contract intake. Shipped all three to production with adoption tracking and team training.

A team handling thousands of customer calls per week had no scalable way to monitor quality. Manual QA covered ~5% of calls; the other 95% were a black box.

An automated call scoring system using Claude to evaluate every transcript against a multi-dimensional rubric, surface coaching moments, and flag at-risk accounts in real time. Dashboard for team leads, weekly trend reports for leadership.

Editors at a publisher network were manually triaging briefs across eight properties — reading every submission, tagging it, and assigning it to the right desk. Routing took ~45 minutes per piece and misroutes were a weekly occurrence.

A unified intake form feeding an n8n + Claude pipeline that tags topic, brand fit, and tier, then routes the brief into the right desk's queue with a confidence score. Edge cases get auto-flagged for editor review instead of silently misrouting.

Senior reviewers were spending ~10 hours a week eyeballing decks and docs for brand, structure, and consistency issues before they went to clients. Rework was constant; senior time was the bottleneck on every shipment.

A Claude-based pre-flight QA pass that scores every deliverable against a structured rubric, posts a Slack summary with line-level fixes, and only escalates to a human reviewer when something genuinely needs judgment.