Create personal profile README

README.md

@@ -0,0 +1,81 @@
+---
+tags:
+- ai-agents
+- developer-tools
+- image-models
+- evaluation
+- retrieval
+---
+
+<div align="center">
+  <img src="https://raw.githubusercontent.com/uuzzrm/uuzzrm/main/assets/profile-header.svg" alt="Ruiming Zhao - Prysai AI systems and developer tools" width="100%" />
+</div>
+
+<table>
+  <tr>
+    <td width="68%">
+      <h1>Ruiming Zhao</h1>
+      <p><strong>AI agents, image model training, and developer tools.</strong></p>
+      <p>I build and inspect AI systems that hold up beyond the demo: agents, retrieval, evaluation, and tool use in real developer workflows.</p>
+    </td>
+    <td align="right" valign="top">
+      <strong>uuzzrm</strong><br />
+      USA<br /><br />
+      <a href="https://github.com/uuzzrm">GitHub</a><br />
+      <a href="https://prysai.com/">Prysai Lab</a><br />
+      <a href="https://www.linkedin.com/in/ruiming-zhao">LinkedIn</a>
+    </td>
+  </tr>
+</table>
+
+<hr />
+
+## 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.
+
+<table>
+  <tr>
+    <td width="33%" valign="top"><strong>AI agents</strong><br /><br />Tool use, retrieval, evaluation, and operational boundaries for dependable workflows.</td>
+    <td width="33%" valign="top"><strong>Image models</strong><br /><br />Full-quantization training and fine-tuning workflows for image AI models since 2024.</td>
+    <td width="33%" valign="top"><strong>Delivery systems</strong><br /><br />Documentation, checks, release paths, and infrastructure that make work inspectable.</td>
+  </tr>
+</table>
+
+## Building with Prysai
+
+<table>
+  <tr>
+    <td>
+      <sub>FLAGSHIP / EVIDENCE-LED LEARNING SYSTEM</sub><br />
+      <a href="https://github.com/Prysai/Prysai-LLM-Playbook"><strong>Prysai LLM Playbook</strong></a><br /><br />
+      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.<br /><br />
+      <a href="https://github.com/Prysai/Prysai-LLM-Playbook">Repository</a> &middot;
+      <a href="https://docs.prysai.com/llm-playbook/">Documentation</a> &middot;
+      <a href="https://huggingface.co/spaces/Prysai/Prysai-LLM-Playbook">Hugging Face Space</a>
+    </td>
+  </tr>
+</table>
+
+<p><sub>Public development candidate: structure and checks are available to inspect; broader learner validation and independent review remain in progress.</sub></p>
+
+## Selected open-source contributions
+
+<table>
+  <tr>
+    <td><a href="https://github.com/jupyterlab/jupyter-chat"><strong>jupyterlab/jupyter-chat</strong></a><br /><sub>Test reliability</sub><br />Isolated YStore databases for parallel UI tests.</td>
+    <td><a href="https://github.com/microsoft/agent-framework"><strong>microsoft/agent-framework</strong></a><br /><sub>Agent runtime</sub><br />Operational warnings and prompt-cache usage preservation.</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/gnt-ai/gnt"><strong>gnt-ai/gnt</strong></a><br /><sub>Agent CLI</sub><br />JSON automation, connectors, documentation, and review output.</td>
+    <td><a href="https://github.com/vllm-project/semantic-router"><strong>vllm-project/semantic-router</strong></a><br /><sub>Routing and observability</sub><br />Replay attribution, cache consistency, and stable lifecycle checks.</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/livekit/agents"><strong>livekit/agents</strong></a><br /><sub>Voice AI</sub><br />Explicit Google Speech-to-Text project selection with compatibility preserved.</td>
+    <td><a href="https://github.com/oomol-lab/open-connector"><strong>oomol-lab/open-connector</strong></a><br /><sub>Product integration</sub><br />Expanded Resend workflows and resilient run-log summaries.</td>
+  </tr>
+</table>
+
+<p align="center"><sub>Build carefully. Measure what matters. Keep the boundary visible.</sub></p>