9 min read
Thinking Fast and Failing Slow: Why LLM as a Judge Fails
LLMs excel at routine coding tasks, but evaluating their outputs is a System 2 problem. Sharing lessons learned from failed “LLM-as-a-judge” attempts - and how to build reliable evaluation instead.
September 22nd, 2025
6 min read
A Practical Guide to OpenTelemetry with OpenSearch
OpenSearch OpenTelemetry
August 18th, 2025
6 min read
The Weekly Chunk #9: Production AI with Prompts, Evals & Agent Architecture
Series: Weekly Chunk
August 15th, 2025
8 min read
Mastering Apache Flink in Production: A Guide to Monitoring & Optimization
Apache Flink
August 11th, 2025
6 min read
The Weekly Chunk #8: AI Ops Insights, Agents, Model Health & Silent Errors
Series: Weekly Chunk Gen AI RAG AI Agents
August 10th, 2025
5 min read
When to Use Partitioning in ClickHouse?
Series: ClickHouse Power Tips ClickHouse
August 4th, 2025
6 min read
Weekly Chunk #7 - Rethinking Linked Data for Better RAGs & LAMs
Series: Weekly Chunk RAG Gen AI
July 31st, 2025
8 min read
RAG with OpenSearch: A Practical Guide to Building Production-Ready AI Applications
OpenSearch AWS OpenSearch RAG
July 28th, 2025
5 min read
Weekly Chunk #6 - LLMs, Scaling and Serving Tools
Series: Weekly Chunk LLM
July 27th, 2025
4 min read
ClickHouse Power Tips: Projections
Series: ClickHouse Power Tips ClickHouse
July 21st, 2025
6 min read
The Weekly Chunk #5 - AI at Scale: S3 Vectors, ReAct & Context Engineering
Series: Weekly Chunk Gen AI Vector Search LLM RAG
July 14th, 2025
6 min read