Automate ML lifecycle tooling and API scaffolding for AI microservices on OpenShift.
npx skills add https://github.com/fajjarnr/payu --skill ai-engineer-fajjarnr
Please help me install this Agent Skill. Skill: ai-engineer Source: https://github.com/fajjarnr/payu/tree/main/.agent/skills/ai-engineer Command: npx skills add https://github.com/fajjarnr/payu --skill ai-engineer-fajjarnr
This skill equips software engineers to design, build, deploy, and monitor production-grade AI microservices using Python 3.12, FastAPI, and robust MLOps patterns on OpenShift.
Create a production-ready ML microservice scaffold using Python 3.12, FastAPI, and TimescaleDB on OpenShift.
High-intent search queries and answers about installing and using this skill.
Scaffold a production-ready ML microservice by generating FastAPI endpoints and Pydantic v2 API contracts, integrating TimescaleDB for time-series feature storage, and automating MLOps patterns on OpenShift. This approach provides clean API scaffolding and robust typing for scalable AI inferences.
Manage real-time ML features by using TimescaleDB for time-series storage and analytics within your Python 3.12 services. This integration supports high-volume data engineering, enabling real-time feature computation for AI inferences served via FastAPI.
Yes, you can deploy AI microservices on OpenShift using Python 3.12. The skill focuses on building scalable AI services with MLOps patterns specifically designed for the OpenShift platform, ensuring robust deployment and monitoring.
Add guardrails for LLM prompts by implementing generative AI patterns with prompt management and safety checks. This skill provides tooling to integrate LLMs into FastAPI applications while ensuring production prompts are safe and validated.
Yes, the MLOps tooling supports model drift tracking for AI risk scoring services. It enables you to ingest transactions, compute real-time features, serve inferences via REST API, and monitor the deployed models for data drift over time.
BearflowerExtend PostgreSQL with TimescaleDB hypertables and continuous aggregates for time-series analytics.
QuestNova502Deploy ML models with automated monitoring, drift detection, and canary rollouts.
figueroaignacioValidate and coerce Python data using Pydantic models.
apassuelloAutomate end-to-end ML pipelines from data preparation through deployment.
