Context

Legal and PR risks are an under-appreciated motivator for LLM analytics 🦺 Many businesses come to us because they want their legal and PR teams to have more confidence in their LLM products Everyone knows LLM products can be unpredictable - and that they introduce risk when they go wrong 🚨 It’s hard to be happy with that risk as a general counsel or data protection officer 💼 So what's the solution? LLM monitoring tools track risky conversations, frustrated users, and unexpected user behavior This enables you to measure and then manage the level of risk 📉 Businesses can then catch issues before they blow up in the press - as we’ve seen happen so often Get in touch if you’re building an LLM product and you want to help your favorite lawyer sleep better at night 💤 

Thank you CB Insights for featuring Context.ai as a Future Tech Hotshot! 🚀 We're in great company with our friends at MotherDuck and Superlinked too!

Today we’re launching support for custom conversion events 🧾 This addresses one of the biggest challenges in the LLM ecosystem - proving ROI 📈 Context.ai 💬🔬 users can now log custom conversion events with their LLM conversation transcripts, indicating where users completed an action: a purchase, a link click, or even a negative event like an unsubscribe We analyze conversion rates, identifying subgroups of conversations and users where conversion rates are relatively stronger or weaker You can then use Context.ai 💬🔬 to investigate what is driving areas of weaker performance, address those issues, and measure the impact of your improvement This allows you to prove the ROI of your product, as well as the ROI of improvements you make to it over time. It also allows you to see the ROI of Context.ai in clear dollar terms, in a way that has not previously been possible

Fresh batch of customer logos on the website 👨🎨 Who wouldn't want to join this esteemed bunch

The Rise of AI Agent Infrastructure. The blistering pace of GenAI development means few assumptions hold true for long. One key change is the rise of AI agents: autonomous actors that can plan and execute multi-step tasks. Today, AI agents — not direct prompts to the underlying model — are becoming a common interface that end-users encounter and even becoming a core abstraction that developers build upon. This is further accelerating how fast new apps can be built and is creating a new set of opportunities at the platform layer. Apps are now being built in a new way that will impose new requirements on the underlying infrastructure. Those developers are speeding across a half-finished bridge. Their apps won’t achieve their full potential if our industry fails to support them lower in the stack with a new set of AI agent Infrastructure components. So let's get to work. We are pleased to share a view of the emerging AI infrastructure stack as it looks in June 2024. Also sharing some additional thoughts in the blog post linked below. Would love to hear from you if you're building in this area. https://lnkd.in/efs_wJJy

We’re growing! I’m excited to welcome Matt Salisbury to Context.ai Matt joins us as our first salesperson to help scale our GTM motion We’ve seen great results from our engagements with Fortune 500 enterprises, tech unicorns, and exciting startups - and it's time to scale up our small but mighty team! Reach out to Matt if you’re building LLM products and want to better understand how and why people are using them, how well user needs are being met, and where performance can be improved

We now support self-hosted deployment! 🏗️👷♂️ Are you desperate to understand how people are using your LLM product, but don’t want to share your transcripts with a third party for analysis? 🔐 Good news! You can now run the Context.ai product within your own cloud instance, without data leaving your control 💭 We’ve also recently improved transcript categorization to be significantly more accurate, and we support projects to allow separation of multiple LLM products within one team or company

Ready to test GPT-4o? It's now live in Context.ai! Test it in the playground, then perform rigorous evals and get it live to your users!

Today we’re launching the ecosystem’s best support for evaluating multi-call chains 🔎⛓️ This allows you to evaluate multi-stage workflows with many calls to LLMs and functions using Context.ai, and you can evaluate these both end-to-end and across any stage of the chain You can then debug exactly where errors are occurring in the trace using our new visualization  And the best part? It’s fully LangSmith SDK compatible, so it couldn’t be easier to get started Huge numbers of builders are using multi-stage LLM workflows, but evaluating them is a well-known problem We’ve spent a ton of time with customers iterating towards a great trace evaluation experience here - and we couldn’t be more excited to share it with the ecosystem Also this month, we’ve added test case tagging, JSON schema validation evaluators, comparison diff view, many more UX improvements

Context.ai is growing fast! Our LLM evals product is now supporting companies from Fortune 500 enterprises to unicorns and startups – with great feedback, but lots to do To help with this next phase of growth we’re expanding the team and hiring for: 1) A Business Development Rep to scale our GTM motion. This person must have 1+ year of experience as a SaaS BDR or AE 2) A contract Product Designer to improve the design and usability of our product. This person must have several years experience designing products used by software engineers These roles are an opportunity to work at the front of the AI revolution, enabling engineers at the world's most innovative AI organizations to ship higher performing and safer LLM products Know someone great? Interested in learning more? Please reach out to me directly! More information in the job descriptions linked in the comments