Tool
Prometheus
9 cases from 9 companies use Prometheus in their stack. 2 were checked in an online A/B test; 2 report results in production. Tasks: Build a data platform, Retrieve and rank from millions of items, Detect anomalies, Rank search results and 4 more. Methods: Gradient boosting, Probability calibration, Data drift monitoring, Logistic regression, Canary rollout and 28 more. Companies: Yelp, LinkedIn, Rabota.ru, Celsus, Raiffeisenbank and 4 more.
| ML based ranking using Nrtsearch | search-engine | 2026-09 | |
| Building the incremental and online training platform at LinkedIn | social | 2025-10 | |
| HRBert2.0: Improving Vectorization of Vacancies and Resumes | classifieds | 2024-11 | |
Machine Learning Service from Scratch, or Creating Frankenstein![]() | ![]() | general | 2024-11 |
| Experience Building a Data Quality Tool at MTS | telecom | 2024-05 | |
Incidents in ML Services and How to Monitor Them![]() | ![]() | healthtech | 2024-05 |
| Adopting the Vespa search engine for serving personalized second-hand fashion recommendations at Vinted | marketplace | 2023-10 | |
| ML System Design Doc Challenge – Final | banking | 2023-05 | |
| Recommend API: one shared pipeline for many recommendation features at Slack | saas-b2b | 2022-09 |

