Loading...
Explore our latest articles and insights about AI Engineering.
40 posts in total
How to strip names, roles, and demographics from queries before retrieval to reduce RAG bias. The redaction pipeline and the 3 leakage traps to avoid.
How to filter irrelevant retrieved chunks with a cheap LLM call before the final answer. The prompt, the batch pattern, and the 40 percent noise reduction.
How to combine multiple vector stores in one RAG pipeline. The merge pattern, the deduplication rule, and when multi-source beats a single index.
How Prometheus metrics surface performance bottlenecks in agentic AI. The 3 queries, the alert rules, and the dashboard that finds hot loops fast.
Why linear LangChain chains fall over on real agents and how LangGraph's stateful graphs replace them. The state model, loops, and upgrade path.
How circuit breakers prevent LLM outages from cascading through your agent. The 3 states, the failure window, and the 50-line implementation.
How to survive LLM provider outages with Tenacity retries and fallback models. The retry policy, the fallback chain, and the 60-line pattern.
How to manage context windows in production AI agents. The 4 strategies that keep long sessions bounded without losing critical context.
Why uv replaces pip, pip-tools, and poetry for production agentic AI services. The speed, the lockfile, and the 5-minute migration.
How to wire Langfuse into an agentic AI service for full observability. The trace hierarchy, the decorator pattern, and what to log per span.
How to use sub-graphs in LangGraph to keep complex RAG pipelines sane. The composition pattern, the state isolation rule, and when to split.
How to render a RAG pipeline as a graph with LangGraph StateGraph. The diagram, the state schema, and the debugging workflow that saves hours.