Ruiming ZhaoAI agents, image model training, and developer tools. I build and inspect AI systems that hold up beyond the demo: agents, retrieval, evaluation, and tool use in real developer workflows. |
uuzzrm USA GitHub Prysai Lab |
The work
I work through the full agent engineering loop: choose the right model and context, connect tools safely, measure quality and failure modes, and turn what works into repeatable workflows.
The standard is simple: fewer impressive demos, more systems that can be tested, understood, and improved.
| AI agents Tool use, retrieval, evaluation, and operational boundaries for dependable workflows. |
Image models Full-quantization training and fine-tuning workflows for image AI models since 2024. |
Delivery systems Documentation, checks, release paths, and infrastructure that make work inspectable. |
Building with Prysai
|
FLAGSHIP / EVIDENCE-LED LEARNING SYSTEM Prysai LLM Playbook A public, six-language learning and practice system for reliable work with LLMs, Codex, Skills, tools, and agent workflows. It pairs concepts with observable labs, acceptance checks, and source boundaries. Repository · Documentation · Hugging Face Space |
Public development candidate: structure and checks are available to inspect; broader learner validation and independent review remain in progress.
Selected open-source contributions
| jupyterlab/jupyter-chat Test reliability Isolated YStore databases for parallel UI tests. |
microsoft/agent-framework Agent runtime Operational warnings and prompt-cache usage preservation. |
| gnt-ai/gnt Agent CLI JSON automation, connectors, documentation, and review output. |
vllm-project/semantic-router Routing and observability Replay attribution, cache consistency, and stable lifecycle checks. |
| livekit/agents Voice AI Explicit Google Speech-to-Text project selection with compatibility preserved. |
oomol-lab/open-connector Product integration Expanded Resend workflows and resilient run-log summaries. |
Build carefully. Measure what matters. Keep the boundary visible.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support