Lamini

Thanks DeepLearning.AI for featuring us in The Batch! https://lnkd.in/gzbJ-a-C

CAT Challenge 🐱 Apply to hack with us on your CAT. ~1 hr to get to an extremely high-accuracy LLM agent (eg. 95%, 99%, etc.). https://lnkd.in/gR_Fh3m8 Uses: - LLM-as-judge - Data labeling agent - Tool selection - Intent detection Let's build some CATs together :)

😻 Apply for our CAT Challenge and see if we can get your classification accuracy up to 90+% in ~1 hr! ⏳ Are you struggling to achieve high accuracy with your classification use case? Have you exhausted prompting and RAG? We are offering a limited number of free 1-hour consulting sessions with one of our Solutions Architects. They will: 📊 Review your use case and current performance 🔎 Analyze your training and test datasets 🎁 Walk you through how to use our toolkit to improve classification accuracy and precision. If you’re interested in a free consulting session with one of our experts, just fill out the Google form. Spots are very limited and we’ll be opening up more spots as they become available. https://lnkd.in/gDMKfk7t

Thank you for the warm response to our new Classifier Agent Toolkit 😺 ! Have you seen our technical demo yet? Scott Gay demonstrates how to use our SDK to build a highly accurate Classifier Agent for a customer service chatbot. The agent categorizes customer interactions by intent so it can determine the appropriate response. Scott shows how to run an evaluation against your model and iterate until you get to your desired level of accuracy. Links to our docs and repo: https://lnkd.in/gU3nJDTZ https://lnkd.in/gKyMySET

I'm so excited to launch Lamini's Classifier Agent Toolkit, aka. CAT! 🚀🐱 CAT hunts & tags the important signals 🐭 in a vast amount of data — so devs can easily create *agentic classifiers*. ❌ Manual data labeling ❌ Large, slow general LLM calls that can only handle 20-30 categories with mid accuracy ✅ CAT has helped our customers tag 2,000 pages across 1,000 categories in just 3.6 seconds with 99.9% accuracy. Dev time? A few hours to a few days. Hallucinations? Approaching zero. *Meow*. Some common agentic classifiers with CAT: ◽️ Customer service agents that extract user intent ◽️ Finding high severity tickets, so your teams can prioritize urgent issues ◽️ Triage legacy application code based on importance, to prioritize development ◽️ Analyze sentiment in earnings calls, reviews, posts, surveys, etc. More on it 👉 https://lnkd.in/gh-w97Gb Demo from one of our amazing architects, Scott Gay https://lnkd.in/gSGYKvqG This was a huge effort by the entire Lamini team 🎀 Happy holidays, hope you like our gift 🎁 Reach out anytime to fill our inbox with cheer at [email protected] (we read, we respond!)

🎄 Christmas came early this year for devs and AI/ML engineers working on large-scale classification problems! 🎁 We just launched our new Classifier Agent Toolkit (CAT) — a streamlined way to build LLM classifier agents that you can plug into an agentic workflow. Here are some ways our customers are using this today: ⭐ Triage incoming support tickets so support teams can prioritize urgent issues ⭐ Analyze sentiment of product reviews, social media posts, customer surveys, earnings calls, and more ⭐ Infer user intent to return the correct chatbot response ⭐ Review and categorize legacy application code Works on both AMD and NVIDIA GPUs on any open model like the latest Llama 3.3. 👀 To see how it works, watch our demo here: https://lnkd.in/gU3nJDTZ 🫰 Sign up at https://app.lamini.ai/ and get $300 credit to create your first Classifier project.

🙌 Our new guide to fine-tuning is out! If you want to know the basics of how fine-tuning works, how it compares to prompting and RAG, and what the best use cases are for each method, this is the guide for you.  https://bit.ly/3CKrYvJ

We're #hiring a new Software Engineer, LLM Platform in Menlo Park, California. Apply today or share this post with your network.

If you're heading to Open Data Science Conference (ODSC) today, be sure to check out Sharon Zhou, PhD talk at 11am “Removing Hallucinations by 95% with Memory Tuning: A Technical Deep Dive". Register: https://lnkd.in/e8zWYqW

Thank you for hosting such an inspiring group of women entrepreneurs Leena Nair!