# Writing

Notes on building agent systems, retrieval and the infrastructure that keeps them running. General engineering material, written from practice. New posts also go out by RSS at /rss.xml.

## Posts

- [LLM evaluation: evals that catch regressions, and when to trust LLM-as-a-judge](https://anukumar.site/writing/llm-evaluation-llm-as-a-judge) (2026-10-16): How to build an eval set from real failures, what to check with code first, the known biases of LLM-as-a-judge and how to calibrate it, evaluating agent trajectories, and running evals like tests.
- [Multi-agent systems: when splitting an agent helps and when it just costs more](https://anukumar.site/writing/multi-agent-systems) (2026-10-16): What multiple agents actually buy you, what they cost in tokens and reliability, the patterns that work, how to write handoffs, and why to start with one agent.
- [RAG retrieval: hybrid search, reranking and measuring recall](https://anukumar.site/writing/rag-retrieval-hybrid-search) (2026-10-16): Most wrong RAG answers are retrieval failures. How to measure retrieval on its own, chunk by structure, combine keyword and vector search, rerank, and filter safely.
- [Agentic AI in practice: tool design matters more than the prompt](https://anukumar.site/writing/agentic-ai-tool-design) (2026-10-16): Why most agent failures come from the tools, not the system prompt: naming, granularity, what tools return, error messages that teach, safe retries and hard limits.
- [Human-in-the-loop AI agents: where approval gates belong](https://anukumar.site/writing/human-in-the-loop-ai-agents) (2026-10-16): Why an approval step bolted on after an agent runs doesn't protect anything, where the gate should sit, what a reviewer needs to see, and how to resume safely after a yes.
- [Multi-tenant architecture: shared schema vs database per tenant](https://anukumar.site/writing/multi-tenant-architecture) (2026-10-16): The three ways to separate SaaS customers' data, how each one fails, what database per tenant really costs, and how to choose.

---

Last updated 2026-10-16. Canonical: https://anukumar.site/writing