The Engineering Notebook — 334 posts

Notes on building with AI, agents & the modern stack.

Deep dives on AI/ML, RAG systems, agent engineering, and senior-engineer architecture decisions — a new post every week.

a close up of a laptop with a pink screen
● Latest
AI and Machine Learning 10 min read

AI Agent Sandbox Linux VM [2026]: Safe Tool Use, No K8s

If your coding agent can run `git`, `pip`, or a shell, it deserves its own disposable Linux VM. Default-deny egress, snapshot rollback, scoped secrets, and per-run audit bundles. No Kubernetes required.

Recent posts

page 1 / 37
spectrogram audio analysis screen — illustration for article on Deepfake Voice Detection: 7-Step Detector Eval Guide Cybersecurity

Deepfake Voice Detection: 7-Step Detector Eval Guide [2026]

Deepfake voice detection is easy to demo and hard to operationalize. Here’s a repeatable 7-step methodology to evaluate detectors: datasets, telephony transforms, multilingual edge cases, metrics, thresholds, and deployment playbooks.

terminal window code on laptop dark — illustration for article on Debug HTTP/3 QUIC in Production: Frontend and Mobile

Debug HTTP/3 QUIC in Production: 8-Step Playbook [2026]

A Wireshark-free workflow to prove HTTP/3 is actually negotiated, diagnose silent fallback to HTTP/2, and measure real perf impact using DevTools, curl, and logs.

postgres psql terminal linux server — illustration for article on Transparent Huge Pages + Postgres: Stop Cloud and DevOps

Transparent Huge Pages + Postgres: Stop P99 Latency Cliffs [2026]

THP isn’t “free performance” for Postgres. Here are the exact Linux settings to avoid p99 latency cliffs, plus a validation loop and Kubernetes guardrails.

A close-up of a stack of papers. AI and Machine Learning

Data Privacy in RAG Redaction and Retention [2026 Playbook]

A practical engineering playbook for data privacy in RAG: what to redact, where privacy leaks happen, default retention periods, and audit trails you can defend in an audit without wrecking debugging.

a person typing on a laptop keyboard on a desk AI and Machine Learning

AI Engineering Evals: Regression Gates for Prompts, Tools, RAG [2026]

Stop letting prompt tweaks and model upgrades silently break production. Here’s a CI-style regression gate system for prompts, tool calling, and RAG with golden sets, schemas, shadow evals, and failure budgets.

terminal logs laptop screen code dark — illustration for article on AI Agent Observability Logging Schema AI and Machine Learning

AI Agent Observability Logging Schema [2026]: OTel + Redaction

A copy‑paste JSON logging contract for agent runs (spans, tool I/O, cost, retries) plus a minimal OpenTelemetry mapping you can implement in a weekend—without leaking secrets.

A pair of black headphones sitting on top of a table Cybersecurity

Deepfake Voice Detection for Call Centers [2026]: Deploy It Right

A practical 2026 runbook for deploying deepfake voice detection in call centers: where to tap RTP audio, what survives VoIP codecs, latency budgets, and how to handle false positives with an appeals workflow.

stock market chart displayed on laptop screen AI and Machine Learning

LLM Latency Benchmark Methodology: Streaming UX Metrics [2026]

A UX-first LLM latency benchmark methodology for streaming chat and agent apps: measure chunk cadence, jitter, tool-call stall time, and end-to-end time-to-usable—not just TTFT.

terminal window laptop screen developer — illustration for article on Reproducible Terminal Dev Environment: direnv + Developer Tools

Reproducible Terminal Dev Environment: direnv + mise [2026]

A repo-first, cross-shell setup for a reproducible terminal dev environment using direnv + mise on macOS, Linux, and WSL—plus secrets patterns and troubleshooting.