AI, LLMs, and applied ML.

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

All posts

66 posts

One Door to the Models, Part 2: Terraform, Bicep, or ARM

Bicep has no state file and cannot touch Entra ID. Part 2 picks the IaC layer for the gateway, and finds the model-version default that upgrades production.

Jul 20, 2026 11 min

One Door to the Models, Part 1: The Case for a Central LLM Gateway

A company runs five GenAI apps and cannot say what any of them cost. Part 1: the scenario, build versus buy on Azure, and the gateway this series builds.

Jul 19, 2026 11 min

Agents on Call, Part 8. Production: Observability, Evals, and the Day It Lies

OTEL traces into CloudWatch, Bedrock invocation logging to S3, an eval harness with a golden incident set, and the day the triage agent lied with confidence.

Jul 16, 2026 12 min

Kiro After the Hype: What AI IDEs Actually Changed

Eight months after Kiro went GA, the spec survived and the IDE mostly did not. What actually changed is where the review happens, not who writes the code.

Jul 15, 2026 6 min

Why Your AI Pilot Died in Procurement

Most AI pilots do not fail on accuracy. They stall in security review and data processing agreements, because nobody scheduled the twelve weeks that follow.

Jul 13, 2026 7 min

Per-App Bedrock Cost Tracking with Inference Profiles

Application inference profiles put cost allocation tags on Bedrock calls, turning one shared bill into per-team lines. The tag design is the hard part.

Jul 10, 2026 6 min

Agents on Call, Part 7. Sizing: Token Math Nobody Does Upfront

The sizing math nobody does upfront: tokens per incident, quota ceilings, when provisioned throughput breaks even, and the platform's monthly bill.

Jul 09, 2026 12 min

EU AI Act, August 2: The Deadline That Didn't Move

The Digital Omnibus deferred the high-risk deadlines to 2027 and 2028. Article 50 transparency still lands on 2 August 2026, and that is the one most teams hit.

Jul 08, 2026 7 min

SageMaker vs Bedrock: An Org Decision, Not a Technical One

The SageMaker or Bedrock question is really about whether your org has a team that owns models. Pick for the team topology you have, not the one on the slide.

Jul 06, 2026 6 min

Prompt Injection via Your Own Docs: The RAG Attack Surface

Your knowledge base is untrusted input. Retrieval hands attacker-authored text to the model, so the control that pays off is scanning at ingestion time.

Jul 04, 2026 6 min

More from Ercan

Two more sites, same author, different ground.