AI, LLMs, and applied ML.

Senior-engineer field notes on AI, LLMs, agents, and applied machine learning by Ercan Ermis.

All posts

66 posts

Structured Output Beats Clever Parsing

Still regex-parsing JSON out of model text? Stop. Bedrock structured outputs enforce a JSON Schema during decoding, so the response is valid by construction.

Apr 06, 2026 4 min

Prompt Caching on Bedrock: The 90% Discount Most Teams Ignore

Bedrock prompt caching reads a repeated prefix at 90 percent off, but a cache write costs more than not caching. The breakpoint decides which you get.

Apr 02, 2026 5 min

AWS Monthly (Mar '26): Governance Comes for the Agents

March 2026 on AWS: AgentCore Policy and Evaluations reach GA, Elemental Inference ships, and agent governance moves from demo to a production control plane.

Mar 31, 2026 4 min

Streaming Responses Are a UX Decision, Not a Performance One

Streaming model responses is a user-experience choice about time to first token, not a speed fix. Sometimes it makes structured output and tool use worse.

Mar 24, 2026 5 min

Bedrock Agents vs Rolling Your Own Loop

Amazon Bedrock Agents handle orchestration, memory, and tool calls for you. Here is when the managed framework saves you real work and when it quietly owns you.

Mar 18, 2026 5 min

IAM for LLM Apps: Least Privilege When the Caller Is a Model

When the caller is a model, least privilege still applies. Give each agent tool a scoped IAM role and a session policy, not one broad set of admin credentials.

Mar 14, 2026 4 min

Someone Registered antrophic.com and Points It Straight to OpenAI

Someone registered antrophic.com, one letter off the real domain, and pointed it straight at OpenAI. A look at the bait and at AI brand confusion.

Mar 11, 2026 4 min

Stop Fine-Tuning. You Need RAG, a Cache, and Better Prompts

Fine-tuning plus provisioned throughput is the expensive answer to most LLM problems. The cheaper path is retrieval, prompt caching, and better prompts.

Mar 09, 2026 4 min

Knowledge Base Chunking Is Where Your RAG Quality Dies

Most bad RAG answers are a retrieval problem, not a model problem. How fixed, semantic, and hierarchical chunking in Bedrock Knowledge Bases set your quality.

Mar 05, 2026 5 min

Bedrock Guardrails Won't Save You From Prompt Injection

Amazon Bedrock Guardrails filter content, they do not authorize actions. Real prompt injection defense is input isolation, tool allowlists, and IAM scoping.

Mar 03, 2026 5 min

More from Ercan

Two more sites, same author, different ground.