PostKonnect
Small teams with something worth sharing still have to rewrite it for every platform, then remember to post it.
A social media desk. You add a story or a photograph, and it drafts a post for each channel. Nothing is published until someone approves it.
- AI integration
- Human approval
- Privacy by design
- Consent management
- Scheduling & dispatch
The problem
I built it for small teams where one person looks after social media on top of their actual job. Some of these teams photograph children, which changes how a picture has to be handled.
What I built
PostKonnect drafts with Gemini, but the drafting is the simple part. Most of the work went into approval and consent. Every draft waits for a person to approve it, and every image carries a record of who agreed to its use.
What it does
- One input becomes a draft for Instagram, Facebook, LinkedIn, TikTok and WhatsApp.
- An approval queue where drafts can be edited before they are scheduled or sent.
- Face detection in the browser, so children’s faces can be blurred before anything is uploaded.
- Consent records linked to the photographs they cover.
- A brand voice that every draft reads before it is written.
- A phone mode for platforms that still have to be posted to by hand.
Under the hood
- Next.js and TypeScript on Supabase.
- MediaPipe face detection runs on the device, not on a server.
- Gemini model names are looked up at runtime, after Google retired the old ones twice in a month.
- Posts go out through Make, with a safeguard against sending the same post twice.
Where it stands
It is live and used daily. The face detection is deliberately cautious. A missed face costs a child’s privacy, while a wrong box costs one tap to remove.
Why it might matter to you
If you want AI in your work, but with a person approving what goes out, this is how I would approach it.
Next case study
Cheche Za Nuru Foundation
A non-profit’s website goes out of date quickly when every update needs a developer.