Scorecard has raised $3.75 million to build an AI evaluation platform.
The San Francisco-based startup lets customers test their AI agents against vetted metrics and deploy them faster. Evaluations involve assessing an AI system’s performance, efficiency, and safety next to industry benchmarks.
The product was created when founder Darius Emrani was building a healthcare app that could transcribe patient notes and let doctors have better patient interactions.
“I really quickly realized that if it messed up, then it could hurt or kill people,” Emrani said. “I realized there’s a need for evals.”
“That’s where Scorecard came up,” the founder said. “So I tried to do something other than evals and came back to evals,” he added, referring to his time at Google-owned Waymo, where he oversaw testing and simulations for self-driving cars for four years before leaving in 2022.
Emrani said that with so many companies launching AI applications, health, finance, and legal tech startups are under pressure to ship quickly.
“They launch and then there’s an ‘Oh crap’ moment where they’re like, it doesn’t work,” he said. “This is happening everywhere in legal. Really prominent companies are literally having failures and lawyers are getting disbarred.”
These startups then use Scorecard’s platform to test how well their AI agents are doing and improve from there.
Scorecard, which is just coming out of stealth, said that it has run millions of tests for customers, including Thomson Reuters, which is using Scorecard to test and deploy CoCounsel, the company’s suite of legal AI agents.
Scorecard has a free tier, and rates are determined based on number of seats and usage.
The $3.75 million seed round was led by Kindred Ventures, with participation from Neo, Inception Studio, and Tekton Ventures. Angel investors included former Meta chief operating officer Sheryl Sandberg and others from OpenAI and Apple.
With the cash injection, Emrani, who leads a team of three other engineers, plans to hire people in engineering and design and a go-to-market person.
“I want to see a world where agents are universally accessible in essential services, things that make a huge impact people’s lives,” Emrani said. “I’m so excited because my customers didn’t exist a year and a half ago. There were no agents. This whole space is so new.”
Check out the pitch deck Scorecard used to secure the funding: