CASE STUDY

Jam

The first fully functional social dApp on Farcaster protocol

Jam brings AI-powered search, reimagined web3 profiles, tailored feeds, curated news, and much more.

WEB3

AI

Jam Hero - True Sparrow
Duration
7 Months
Team size
11
Functions
  • Engineering
  • DevOps
  • UX
  • Android
  • iOS
Scope
Deliver the best-in-class social experience to the Farcaster community.
Airstack brought us on-board to help design, architect, build and host this experience.
Tech Stack
Golang
React Native
React
Weaviate
GraphQL
MongoDB
Product

Web3's decentralized model gives users ownership of their content but to take this to the masses, there is a strong need to create dAaps with better experiences.

Jam serves this purpose by delivering a brilliant and intuitive social experience in the absence of any fully functional dApp on Farcaster. Jam's superpower is being able to smartly search and show the relevant content to the user to engage with.

Jam Product Section
Jam Dev Spotlight - True Sparrow

AI-powered semantic search

The usual keyword-based search is very limiting.

We leveraged OpenAI's vector embeddings (Ada v2 model) along with Weaviate, a vector database, to provide a semantic search. We further factored in engagement metrics and time parameters to deliver relevant results.

Jam Farcaster - True Sparrow
Jam Curated News - True Sparrow

Curated news featured by engagement

Jam surfaces the most trending news on Farcaster by analyzing shared links using an engagement-oriented scoring mechanism that also takes into account their recency. It uses link metadata and a custom data-cleaning process to deliver clear, informative news content.

Discover content & users based on your Twitter activities

The Twitcaster feature uses AI-powered semantic search and Twitter APIs. This helps solve the cold start problem for new Farcaster users by suggesting relevant users and content based on their 50 recent tweets.

Jam AI Powered - True Sparrow
jam Trending Topics - True Sparrow

Trending topics

To show relevant content to the users, we analyze the most recent posts and categorize them into the top 20 topics by using openAI APIs and Davinci-003 Model.

Integrating Farcaster Hubs

As the first adopter of Farcaster Hubs, we worked very closely with the Farcaster protocol team and provided them with early feedback. By integrating hubs, we were able to create a smooth user experience.

We also made use of long casts to surpass the hub's character limits and switched to direct data sync from hubs, adeptly handling design constraints.

Jam Integrating - True Sparrow
Jam Scaling - True Sparrow

Scaling & preview environments

Using Terraform, Kubernetes, Docker, and AWS, our DevOps team facilitated quick product development and scalability. This additionally empowered the developers to create preview environments that enhanced collaboration and innovation.

Impact

1st

Most widely used third-party app on Farcaster

“Just discovered the search on Jam with filter by time. Way easier to find new stuff on jam with this. Great feature.”

-Fran (Farcaster user)

90%

People who try Jam continue to use it at very high rates resulting into 90% wau/mau