Chris Faulkner
AI-assisted product content & catalog cleanup
New to Contra
Chris is ready for their next project!
Self-initiated sample: I designed this AI-assisted product catalog cleanup workflow to standardize messy product data, rewrite unclear descriptions from source facts, structure attributes, flag missing or unsupported claims, and return a clean owner-reviewable spreadsheet. The goal is to make ecommerce catalogs clearer, more consistent, and easier to maintain without inventing product information.
0
8
Self-initiated sample: I designed this AI content feedback loop to improve AI-generated writing systematically instead of fixing each draft in isolation. The workflow generates a draft, reviews it for accuracy, specificity, voice, structure, and usefulness, classifies the weakness, updates prompts or source context, and re-runs the task. The goal is to turn editorial feedback into reusable system knowledge so future outputs improve over time.
0
8
Self-initiated sample: I designed this AI-assisted executive voice calibration framework to turn generic drafts into specific, credible LinkedIn content. The workflow analyzes source material, builds a reusable voice profile, generates drafts with structured constraints, checks accuracy and originality, and feeds performance insights back into future iterations. The substantive drafting, analysis, comparison, and refinement are AI-assisted.
0
10
Self-initiated sample: I designed this AI-assisted editorial QA workflow to turn rough AI drafts into credible LinkedIn thought-leadership content for C-level audiences. This sample shows how I structure briefing, draft generation, editorial review, feedback loops, and performance analysis to improve clarity, accuracy, consistency, and executive voice. Tools used in this workflow include ChatGPT, Notion, Google Docs, and LinkedIn Analytics. The goal is a repeatable system for producing stronger executive content at scale.
0
11