Result: 40x content throughput. Zero additional headcount.
Before: Property Filter produced one member success story per month, maximum. Every step was manual: interview, writing, editing brief, blog article, social copy. Short-form video: zero. SEO-optimised articles: zero.
What I built: A multi-stage AI production system using Claude. One coordinator types a single command after each member interview. The system generates: a timestamped video editing blueprint for the editor; a full SEO and GEO-optimised blog article using a validated canonical template; a publishing checklist for the web team; platform-specific social copy for 4-5 short-form clips. HubSpot MCP pulls the member's data in automatically. Automated Slack messages route each output to the right person in the right channel.
Not automation replacing humans. An intelligence layer that makes every person in the pipeline perform at a higher level.
After: 10+ stories per week. 4-5 short-form clips per story (previously zero). Substantially better video quality because editing briefs are precise and timestamped. Zero additional headcount.
ChatGPT just added a new sketch feature to its new Images 2.5 model, so I tried it with extremely simple sketches and short prompts to see how well it could understand my intention.
And honestly, I actually like it!
This can be helpful especially when you already have a specific pose or composition in mind and want to quickly turn that rough idea into something more refined.
If you’re curious, I included a quick process video in the comments.
Do you think this new feature could be useful in your workflow?
Absolutely. The ability to translate a rough sketch into a refined visual while preserving the intended pose, composition, and creative direction could make the ideation process much faster. It feels especially useful for designers who want to communicate an idea visually before spending time refining every detail. Definitely a feature worth experimenting with in a real workflow.
ChatGPT just added a new sketch feature to its new Images 2.5 model, so I tried it with extremely simple sketches and short prompts to see how well it could understand my intention.
This is a great experiment! The sketch to refined visual pipeline could seriously speed up early ideation. Curious how it handles more abstract or complex sketches.