Update README.md

README.md

@@ -41,3 +41,33 @@ thumbnail: >-
 _**We are a team that seeks to connect our people's past with the world's future.**_
 
 At **Navid**, we build Arabic-first and multilingual GenAI solutions across domains, laser-focused on delivering real value for people and organizations.
+
+## What We Do
+
+- **Data pipelines & governance** — automated collection, filtering, and curation  
+- **Synthetic data & augmentation** — domain-balanced recipes for Arabic tasks  
+- **Training & fine-tuning** — SFT, DPO, PPO, RLHF/RLAIF  
+- **Custom LLMs & evals** — Arabic/multilingual models with robust evaluation  
+- **Advanced RAG** — secure retrievers, re-rankers, hybrid search & guardrails  
+- **Agentic workflows** — LangGraph/LangChain multi-agent apps with memory/tools  
+- **Deployment** — on-prem, VPC, or managed GPU with full observability  
+
+🚀 **Highlight:** *Yehia* — one of the top models for its size trained by Navid.  
+
+## Building Agents
+
+- **Planner–Worker patterns** for complex tasks  
+- **Structured tool-use** with safety constraints  
+- **Grounded reasoning** with hallucination grading  
+- **Replayable traces & guardrails** for compliance  
+
+Use cases: knowledge copilots, policy Q&A, analytics, code assistants, and enterprise automation.  
+
+## Open Source
+
+We contribute to the Arabic AI ecosystem with:  
+
+- **First Arabic RAG Leaderboard** — open-sourced for the community  
+- **Arabic/Multilingual Reranker Benchmarks**  
+- **Evaluation recipes** for faithfulness, recall, precision, and similarity  
+- **Data loaders/cleaners** for Arabic PDFs & OCR