AI agent engineer at a Hangzhou enterprise software company, building LLM-powered workflow automation with tool-use and memory. Designed the multi-agent orchestration layer that reduced manual data-entry work by 70%.
An architectural deep-dive into choosing between RAG and fine-tuning for enterprise-grade, reliable multi-agent orchestration.
6 August 2026
Build resilient LLM-powered applications with fallback chains that handle API failures, rate limits, and model degradation gracefully — covering circuit breakers, provider routing, response quality detection, and observable failure handling.
17 July 2026
Fine-tuning and retrieval-augmented generation solve different problems, and choosing the wrong one wastes months of engineering effort. This article breaks down the decision criteria, hidden costs, and practical scenarios where each approach wins — and where combining them is the right answer.
16 July 2026