Skip to content
← All work

GenAI · Content generation

AI content generation platform

An internal product in development: AI features that turn a brief into generated marketing content, grounded in retrieved context.

Internal product / in developmentContent-generation features inside an internal product. Not presented as finished or commercialised.

content-platform / new brief
Illustration

Brief

Announce a new feature to existing customers. Friendly, concise, one clear call to action.

Context retrieved

  • brand-voice
  • product-notes
  • past-campaigns

Draft

Generating

[1] brand-voice[2] product-notes
  1. FastAPI
  2. RAG / LLM
  3. Store
  4. AI services
  5. Output
Illustration of a brief being turned into generated content using retrieved context.

The problem

Generic prompting produces generic content. Useful output needs the right context retrieved and applied consistently, behind a dependable API.

Context

An internal content-generation product, still in development, where a person describes what they need and receives a draft they can review.

My role

I designed and built the generation pipeline: the FastAPI service, retrieval-augmented prompting, persistence, and the extra AI processing applied before a draft is returned.

What I built

Built features

  1. 01Brief intake through a typed API
  2. 02Context retrieval before generation
  3. 03Language-model draft grounded in that context
  4. 04Persistence of application data and results
  5. 05Post-processing of the generated material

Design decisions

  • Retrieve relevant context before calling the language model, instead of sending a bare prompt.
  • Coordinate every step behind one FastAPI service so the flow is explicit and repeatable.
  • Persist application data, retrieved context and results in Supabase and MongoDB.
  • Run additional AI processing on the draft before it is returned, so the caller gets a finished artefact.
  1. 01A FastAPI service receives each request and coordinates the pipeline.
  2. 02Retrieval-augmented generation supplies the language model with relevant context.
  3. 03Supabase and MongoDB persist application data and results.
  4. 04Further AI services process the output before it is returned.

Outcome

Content-generation features are integrated into an internal product that is still in development. This is not presented as a finished or commercialised product.

Architecture

How AI content generation platform fits together.

Each step, in order. Select a node to see what it is responsible for.

  1. A user describes the content they need.

  2. API layer that receives requests and coordinates each step of generation.

    • Python
    • FastAPI

  3. Retrieves relevant context and prompts a language model with it.

    • RAG
    • LLM

  4. Persists application data, context and generated results.

    • Supabase
    • MongoDB

  5. Additional AI services applied to the generated material.

  6. Finished content returned to the user.

Stack

  • Python
  • FastAPI
  • RAG
  • LLMs
  • Supabase
  • MongoDB

Next project

Authentication log analytics

An end-of-studies project: a data pipeline and dashboards that turn raw authentication logs into searchable events and reporting views.