All work
AI and LLM apps
Resolve AI
Evaluation-driven AI customer operations agent using tool calling, hybrid RAG, policy guardrails and human-in-the-loop workflows.
- My role
- Designer and developer
- Stack
- Python, RAG, LLMs, Tool calling, AI evaluation
Key features
- Retrieval-augmented generation (hybrid RAG)
- Tool calling for customer operations tasks
- Policy guardrails
- Human-in-the-loop review workflows
- Automated LLM evaluation
Related projects
Next projectHiral International Courier