Since the launch of ChatGPT towards the end of the previous year, we have witnessed companies actively developing generative AI tools to enhance customer interactions with their products and services, making these interactions more natural. However, in numerous instances, these providers lack insight into the performance of the underlying large language models or the quality of the responses they generate.
Context.ai, a company that emerged earlier this year, has now secured a $3.5 million seed investment to fully realize its vision of helping organizations gain a better understanding of how users engage with their Large Language Models (LLMs). CEO Henry Scott-Green and his co-founder, CTO Alex Gamble, who both previously worked at Google, identified a critical need for a service that assesses the behavior and effectiveness of these models. They noticed a significant gap in available tools to address these challenges.
Scott-Green explained, “We’ve spoken to hundreds of developers who are building LLMs, and they have a really consistent set of problems. Those problems are that they don’t understand how people are using their model, and they don’t understand how their model is performing. The phrase that I always hear is that ‘my model is a black box.'”
In many ways, this service resembles product analytics tools like Amplitude or Mixpanel, which track user interactions with a product interface, such as clicks or time spent on a page. However, Context’s focus is on delving into the data generated by LLMs and determining if it delivers genuinely useful content that assists users in answering customer inquiries, with the ultimate goal of improving model effectiveness.
Here’s how it works: Customers share chat transcripts with Context through an API. The software then employs Natural Language Processing (NLP) to analyze the data. It categorizes and tags conversations by topic and assesses each conversation to determine customer satisfaction with the responses provided.
Scott-Green emphasized the significance of this shift, stating, “We believe there is a big shift happening [with the rise of LLMs], and there’s going to be a huge number of these chat experiences built over the next few years. And in that new world, where there is a huge amount of textual interface that users are engaging with via text, rather than graphical user interfaces, there is a need for a different set of tools.”
Context.ai initiated its journey by creating an initial prototype and sharing it with early customers and design partners. They have since been continuously iterating and enhancing the product. Scott-Green mentioned that it’s an ongoing process, but they have garnered significant interest and secured paying customers.
Regarding security and privacy concerns, Context.ai takes measures to safeguard data. It removes Personally Identifiable Information (PII) upon ingestion and refrains from using the content for model development or marketing purposes. Data is retained for no more than 180 days before being deleted.
Currently, the company is relatively small, employing six individuals. However, Scott-Green envisions a future with a growing organization and believes it’s never too early to prioritize building a diverse and inclusive workforce.
He stated, “It’s obviously a challenge that the startup ecosystem has, and the tech ecosystem has in general when it comes to building representative, diverse, inclusive teams. It’s something we both believe strongly in, and I think more importantly, it’s something that we’re both acting on as well, and really making efforts to ensure that we have an inclusive representative diversity [in our employee base].”
The recent investment was co-led by GV (Google’s venture arm) and Theory Ventures.
