AI, LLMs, and applied ML.
Senior-engineer field notes on AI, LLMs, agents, and applied machine learning by Ercan Ermis.
All posts
Evals Before Agents: You Can't Ship What You Can't Score
Without an eval harness, every agent change is a vibe check. Build the scoreboard before the agent, and treat the LLM-as-judge as a component that can be wrong.
Semantic Caching: Two Different Questions, One Answer
Semantic caching returns one stored answer for two differently worded questions. It cuts cost and latency, but a false hit serves a confidently wrong reply.
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.
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.
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.
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.
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.
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.
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.
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.
More from Ercan
Two more sites, same author, different ground.
Cloud, AWS, EKS, Terraform, platform engineering.
Field notes from production systems. EKS, IAM, Terraform at organization scale, observability, cost optimization.
Visit ercan.cloud →The hub. About, consulting, contact.
Personal hub for both writing tracks. Who I am, how the consulting works, how to reach me.
Visit ercanermis.com →