Artificial intelligence continues to dominate the tech world and in Brazil, the Master team wants to help developers master it.
Meistrari offers solutions for companies building products based on other major language models. Rodrigo Bobrow and Henrique Cunha started the company in 2023 after seeing how difficult it was to create artificial intelligence orchestration, specifically direct engineering.
They started with a product called Perfect Profile, which was an AI that when you connected LinkedIn to it, it rewrote your profile to be more search-optimized. While doing this, there were applications that helped develop the front end and back end in a matter of days. However, when it came time to orchestrate the AI, it took weeks because they couldn’t find an easy-to-deploy solution, Bobrow recalls.
So he and Cunha set out to develop a comprehensive, automated system for instant generation and evaluation of results. Prompt is the instruction given to another LLM, which determines the quality of the output, Bobrow explained.
The platform requires no programming knowledge and provides quality control for all applications using language models, such as ChatGPT, Claude and Cohere. This includes everything related to direct management, system testing, evaluating quality results, and monitoring the system in production.
“We have three main experiences: One is being able to create a great prompt. The second is the test suite where we’ll create 100 tests for each of your brands so you can see how well your prompt performs in real-world situations. The third is a rating system that allows you to configure several raters to rate something within your production,” Bobrow said.
For example, you can give a prompt to write something funny in a certain person’s style, and Meistrari will run it through the rater and give it an exit score that will tell you if it’s something you should go ahead with.
Meistrari released its proof of concept, called “Prompts Royale,” on GitHub in 2023. That attracted attention from notable market executives, including the founders of Shopify, Cohere, and OtherSideAI, Bobrow told TechCrunch.
In fact, Shopify co-founder Tobi Lütke specifically sent Meistrari a message requesting a security feature for Shopify to use. This resulted in receiving over 100 GitHub stars on the first day. And several investors to approach.
Although the company is in its early stages — less than five months into its tech development, to be exact — Monashees and Audacious Ventures co-led a $4 million seed round and were joined by a group of angel investors, including Oleg Rogynskyy by People AI, Paul St. John, ex-CRO of GitHub and Hugh Strange, ex-CPO of Nubank.
Much of the new capital will be used to build a team so it can continue to develop AI infrastructure, Bobrow said. He expects to release a minimum viable product in the next two months or so.
“One of our guiding principles is to be a development environment for natural language,” Cunha said in an interview. “We are seeing more and more codebases consisting of English instead of an official language for instructions. At the same time, we see many companies and engineering teams, coding the messages in the code base. We want to help them have a real integrated development environment for natural language itself.”