Skip to content
Muhammad Safyan

Wesion (Abundance Movement)

AI matching and recommendations at 5% of the cost

How I built an 11-service AI matching and recommendation platform with OpenAI, LangChain and Pinecone for a UK social learning app — and cut LLM costs by 95%.

lower LLM spend
95%lower LLM spend
AI services in production
11AI services in production
profile dimensions matched
5+profile dimensions matched

The problem

Wesion connects members by goals, strengths and values. It needed matching, video recommendations and conversation summaries that understood meaning — and the first AI prototype was too expensive to run for every member.

What I built

  1. 01Designed and built the NestJS back end from scratch on TypeORM and PostgreSQL, deployed on AWS, with a Python Lambda compressing uploaded images and video on S3.
  2. 02Built 11 AI services — semantic matching, video recommendations, goal suggestions, content analysis and chat summarisation — on OpenAI GPT and LangChain.
  3. 03Stored each member's strengths, weaknesses, interests, values and keywords in separate Pinecone namespaces, so matches compare like with like.
  4. 04Measured cost per feature, moved tasks that did not need a reasoning model from o1-mini to gpt-4o-mini, and set token limits of 300–2,000 per use case — 95% cheaper with output quality held.
  5. 05Added a weekly NestJS cron that summarises each 7-day conversation window into a narrative and action items, with REST endpoints for on-demand digests.

Screens

Wesion community dashboard showing proposals, votes and member balances
Wesion community dashboard showing proposals, votes and member balances

Want results like these on your project?

Tell me what you are building and where it hurts, and I will come back with questions or a plan.