A 3-week fixed-price build that took one person out of daily content operations entirely — scalable to any number of AI personas, operable by a non-technical VA.

“Design and implement a modular, automation-first AI influencer system capable of generating and posting realistic image content to social media at scale, while minimizing detection risk through controlled content variation, behavioral randomization, and perceptual realism. The system must be: Scalable — easy to add new houses and influencers. VA-friendly — operable by non-technical staff. Future-proof & Modular — supports new image models, formats, and platforms. Risk-aware — optimized for longevity and reach, not overengineering.”
— Jure Erlic, CanadaBefore this build, Jure was running every step manually:
The bottleneck wasn't image generation — that's fast. The bottleneck was creative direction (figuring out what to generate) and mechanical operations (everything between "image done" and "post live"). Producing daily content across multiple AI personas was unsustainable for one person.
Rather than generating images in random environments, I designed each AI persona's world like an actual home. The base has a Houses table and a Rooms table — some rooms are shared across personas (kitchen, living room, balcony) and some are private to each persona (bedroom, dressing room). Every generated image is anchored to a specific room. Followers subconsciously recognize the spaces over time — exactly how real influencer accounts build visual identity.

The pipeline, end to end:


From a small set of keywords per persona, GPT generates high-quality detailed image prompts — handling styling, clothing, pose, lighting, and room context. Eliminates the creative bottleneck entirely.
At a configured time of day per persona, Airtable kicks off the generation run automatically.
Airtable sends the record ID to a Lambda function, which pulls full record details via the Airtable API.
Lambda passes the prompt and persona reference images to Wavespeed (Flux Schnell, Flux Pro, and Google Nano-Banana 2 models).
A second Lambda receives the generated image, runs a Python script to strip all AI metadata, then organizes and uploads the file to AWS S3 in the correct persona/room folder structure.
Only the S3 URL gets stored — not the file itself. Keeping images in S3 and only URLs in Airtable keeps the bill flat regardless of generation volume.
An n8n workflow picks up the ready post and publishes it on schedule. No human involvement past initial configuration.
Shehar is really great to work with. He is excellent at understanding client needs and executing the plan as agreed upon. I highly recommend working with him! I'd love to work together again in the future.
Whether you're running an AI content operation or a marketing agency thinking about offering AI content services — the same backbone applies. Book a free audit call.
Book a free audit →