AI, LLMs, and applied ML.

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

All posts

54 posts

Step Functions Is the Most Underrated Agent Orchestrator

Most agent workflows do not need a model to decide control flow. Step Functions gives deterministic orchestration, retries, and human-in-the-loop states.

May 07, 2026 4 min

LLM Gateways: Why Every Platform Team Builds One Eventually

A second team calling a model means ungoverned fan-out. An LLM gateway centralizes auth, quota, routing, and audit. Build vs LiteLLM vs API Gateway.

May 04, 2026 5 min

AWS Monthly (Apr '26): OpenAI Lands on Bedrock

April 2026 on AWS: OpenAI models, Codex, and Managed Agents arrive on Bedrock, and AgentCore adds a managed harness and CLI to shorten the path to an agent.

Apr 30, 2026 4 min

Cross-Region Inference: Cheap Resilience or Residency Trap?

Bedrock cross-region inference smooths throughput and throttling. But a global profile can route your prompt out of its geography. Read residency first.

Apr 26, 2026 4 min

Your LLM Bill Is an Observability Problem

A surprising Bedrock bill is not a pricing problem, it is a visibility one. If you cannot attribute tokens to a feature, tenant, or agent, you cannot manage it.

Apr 21, 2026 4 min

Batch Inference on Bedrock: Half Price If You Can Wait

Amazon Bedrock batch inference runs at 50 percent of on-demand pricing. The only cost is latency. For any job where nobody is waiting, that trade is free money.

Apr 17, 2026 4 min

Multi-Tenant LLM Apps: Isolating Customers on a Shared Model

One shared Bedrock model, many customers. The model is stateless, so isolation is your job: scope the retrieval, cap the quota, carry identity per tenant.

Apr 13, 2026 4 min

Agent Memory Is a Database Problem, Not a Prompt Problem

Stuffing an agent's whole history into the prompt is not memory, it is a growing bill and a token ceiling. Real memory is a database with a retrieval step.

Apr 09, 2026 4 min

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

More from Ercan

Two more sites, same author, different ground.