While building a legal AI tool, the founders discovered that optimizing each component was a complex benchmarking challenge involving trade-offs between accuracy, speed, and cost. They built an internal tool that quickly gained public traction as the number of models exploded.
Related Insights
Startups are increasingly using AI to handle legal and accounting tasks themselves, avoiding high professional fees. This signals a significant market need for tools that formalize and support this DIY approach, especially as startups scale and require more robust solutions for investors.
Recognizing there is no single "best" LLM, AlphaSense built a system to test and deploy various models for different tasks. This allows them to optimize for performance and even stylistic preferences, using different models for their buy-side finance clients versus their corporate users.
The company provides public benchmarks for free to build trust. It monetizes by selling private benchmarking services and subscription-based enterprise reports, ensuring AI labs cannot pay for better public scores and thus maintaining objectivity.
Rather than relying on a single LLM, LexisNexis employs a "planning agent" that decomposes a complex legal query into sub-tasks. It then assigns each task (e.g., deep research, document drafting) to the specific LLM best suited for it, demonstrating a sophisticated, model-agnostic approach for enterprise AI.
The popular AISDK wasn't planned; it originated from an internal 'AI Playground' at Vercel. Building this tool forced the team to normalize the quirky, inconsistent streaming APIs of various model providers. This solution to their own pain point became the core value proposition of the AISDK.
Rather than committing to a single LLM provider like OpenAI or Gemini, Hux uses multiple commercial models. They've found that different models excel at different tasks within their app. This multi-model strategy allows them to optimize for quality and latency on a per-workflow basis, avoiding a one-size-fits-all compromise.
Founders can get objective performance feedback without waiting for a fundraising cycle. AI benchmarking tools can analyze routine documents like monthly investor updates or board packs, providing continuous, low-effort insight into how the company truly stacks up against the market.
The company originated not as a grand vision, but as a practical tool the founders built for themselves while developing a legal AI assistant. They needed a way to benchmark LLMs for their own use case, and the project grew from there into a full-fledged company.
The founders built the tool because they needed independent, comparative data on LLM performance vs. cost for their own legal AI startup. It only became a full-time company after its utility grew with the explosion of new models, demonstrating how solving a personal niche problem can address a wider market need.
The legal profession's core functions—researching case law, drafting contracts, and reviewing documents—are based on a large, structured corpus of text. This makes them ideal use cases for Large Language Models, fueling a massive wave of investment into legal AI companies.
