Builder Profile: Ismail Pelaseyed

Lena Vu Sawyer

Ismail Pelaseyed is the CTO and co-founder of Superagent, an open-source framework that enables developers to build, manage, and deploy AI Assistants.

Ismail is an experienced developer who is dedicated to building open source software. After many years of running a successful consulting firm with his business partner, Alan Zabihi, they wanted to go back to building projects for themselves, focusing primarily on open source AI and agent frameworks.

Eight years ago, Ismail and Alan built KeyCrunch (now Hyperdrive), which automatically writes marketing copy for users. They continued to expand the function of KeyCrunch into a tool that generates ad materials with the help of AI agents. Their goal was to get mainstream developers without expertise in ML to integrate AI into their applications. The company was eventually acquired by Jetshop, but Ismail and Alan continued to focus on agents and accessible AI dev frameworks in their next project: Superagent.


At Superagent, Ismail’s goal as CTO is first to develop a framework that makes it easy for developers to build with AI agents, then a pipeline for developers to train their models. He’s used Replit for rapid prototyping and has deployed Superagent’s backend API using Autoscale Deployments. Not only has Replit made it easier for Ismail and his team to build Superagent, but it’s also helped them enable developers to find and use their tools.

Ismail and his team started using Replit to spin up quick prototypes of Assistants and Agent definitions before pushing them to production. The earliest prototype he built on Replit was an AI assistant to conduct code reviews on the Superagent open-source repository.

“Superagent devs use Replit internally to prototype new types of Assistants and Agent definitions before pushing them to production. It allows us to rapidly deploy our environment and try out new features and making sure these new features work in production and in our SDKs.”

He also built a proof-of-concept to illustrate how developers could "embed" specific knowledge into a large language model, query that language, and ask specific questions about the data they had embedded.

“Replit has allowed us to create templates and demos showcasing what's possible to build with Superagent. Before deploying Repl, we had to write long posts about each and every step, but now we can just point to a Repl we have set up that the user can run without writing a single line of code. This has helped us drastically reduce the time to onboard new users on our framework.”

Ismail has since deployed NO-7B, “an open source LLM designed to surpass the knowledge cut-off date by leveraging the internet to output real-time and factual responses."

Don’t miss an update from this prolific developer! Check out Ismail’s projects and templates on his profile and follow his work on Twitter/X.

More blog posts