Tool
Streamlit
12 cases from 10 companies use Streamlit in their stack. 1 was checked in an online A/B test; 2 report results in production. Tasks: Evaluate models, Rank search results, Detect anomalies, Predict churn and lifetime value and 3 more. Methods: LLM-as-a-judge, Multi-agent system, Gradient boosting, RAG evaluation, Synthetic data generation (LLM) and 31 more. Companies: Canva, Raiffeisenbank, Walmart, Celsus, Rabota.ru and 5 more.
| Agentic Feature Engineering: How McAfee Drives Personalization With Agent Bricks | general | 2026-06 | |
| How We Are Deploying AI at a University | edtech | 2026-05 | |
Method of Automated Construction of Production Digital Twins Using LLM Agents![]() | ![]() | manufacturing | 2026-05 |
| Measuring Commercial Impact at Scale at Canva | saas-b2b | 2025-06 | |
| From Chaos to Control: Building a Streamlit Tracer for Debugging RAG Systems | general | 2025-05 | |
| How to improve search without looking at queries or results | saas-b2b | 2024-11 | |
| Deploying RAGs in production — Part 2 | retail | 2024-07 | |
Building a Playlist You Will Like![]() | ![]() | media-streaming | 2024-05 |
| ML in Predicting ESP Failures | — | manufacturing | 2024-05 |
Incidents in ML Services and How to Monitor Them![]() | ![]() | healthtech | 2024-05 |
| Salary Horrors and How to Avoid Them | classifieds | 2023-10 | |
Experience in Creating a Design Document When Designing an ML System: A Store Clustering Service![]() | ![]() | retail | 2023-05 |



