AI, LLMs, and applied ML.

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

All posts

66 posts

M365 Security 101: AI Pilot and Business Impact Reports

Where AI earns its place in security: remediation behind a per-change approval gate, and reports leadership can act on. A 101 with Aether365 as the example.

Jul 03, 2026 6 min

Agents on Call, Part 6. Guardrails: The Part Everyone Skips

Threat model, then guardrails: Bedrock Guardrails in Terraform, why IAM still does the heavy lifting, and the failure modes nobody demos on stage.

Jul 02, 2026 13 min

Trust the Model, Audit the Binary

A coding agent's client is the most privileged binary on your machine. Claude Code's hidden prompt fingerprint shows why you audit it, not trust it.

Jul 02, 2026 7 min

AWS Monthly (June '26): Agents Get a Feedback Loop

June 2026 on AWS: the Summit in New York turned production traces into agent improvement, shipped Continuum for security, and took the AgentCore harness to GA.

Jun 30, 2026 6 min

Agents on Call, Part 5. The Team: Supervisor and Three Specialists

A supervisor delegates to triage, runbook, and cost agents over the network, AgentCore Memory ties their findings together, and when one agent still wins.

Jun 25, 2026 12 min

AWS Built a Sandbox for AI-Generated Code: Lambda MicroVMs

AWS Lambda MicroVMs give AI agents a place to run model-generated code, isolated at the VM level. The missing piece for production agents was the runtime.

Jun 23, 2026 5 min

Your Multi-Agent System's Real Limit Is Tokens Per Minute

Amazon Bedrock now exposes per-model tokens-per-minute quotas in Service Quotas. For agents, TPM is the real scaling ceiling. Plan for it before the 429s start.

Jun 21, 2026 6 min

Estonia Is Giving AI Agents an ID. That Is the Easy Part

Estonia plans to issue AI ID codes to AI agents, a world first. The identity is the easy part: authority, delegation, and accountability are the real work.

Jun 20, 2026 6 min

Le Chaton Fat: The Fattest AI Model That Never Existed

There is no AI model called Le Chaton Fat. No weights, no API, no benchmark. Here is how a Mistral cat joke became the AI community's favourite running gag.

Jun 18, 2026 4 min

Agents on Call, Part 4. Tools and the Gateway: MCP, Allowlists, Read-Only Default

Tools move behind AgentCore Gateway: scoped Lambdas, cross-account read-only roles, and the one gated path that is allowed to change anything.

Jun 18, 2026 14 min

More from Ercan

Two more sites, same author, different ground.