The Engineering Notebook — page 6 of 32
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.
Cloud and DevOps Cloudflare Workers AI Agents + Durable Objects: What Runs Where [2026]
Cloudflare OS reframes Workers as an agent runtime. Here’s the practical architecture map: what belongs in stateless Workers vs Durable Objects vs Queues vs Workflows, plus the concurrency and retry traps that bite in production.
Developer Tools 7 Metrics to Measure AI Coding Impact on Engineering Metrics [2026]
Stop justifying AI coding tools with “felt faster.” Here’s a team-level measurement framework for PR throughput, rework, defect escape, and code review load—with guardrails and rollout thresholds.
Developer Tools TypeScript 7 Native Compiler Benchmark: My TS6 vs TS7 Recipe [2026]
A reproducible TypeScript 7 native compiler benchmark harness (clean vs incremental, emit vs noEmit) plus a migration checklist for monorepos, path aliases, and CI caching.
Frontend and Mobile CSS Popover API Examples + Accessibility Patterns [2026]
Production-ready Popover API recipes for menus, tooltips, and non-modal UI in 2026. Focus rules, screen reader traps, Anchor Positioning, nesting, and fallbacks—without pulling in a floating UI library by default.
Cybersecurity Prevent Sensitive Data Leakage in RAG: The 2026 Playbook
RAG leaks rarely happen in the model. They happen in logs, traces, and vector stores. Here’s a practical 2026 playbook to ship redaction, least-context retrieval, and auditable controls end-to-end.
AI and Machine Learning Agent Evaluation Harness [2026]: Replay, Rubrics, CI Gates
Most agent failures aren’t “bad prompts”. They’re multi-step tool cascades. Here’s how I build an agent evaluation harness that actually prevents regressions.
Technology Docker Compose vs Kubernetes for AI/ML [2026]: Use Which?
A practical 2026 decision guide for AI teams: when Docker Compose is enough for a single GPU box, when Kubernetes is mandatory, and the cleanest migration triggers for serving and training.
![claude code terminal laptop screen — illustration for article on Claude Code Security [2026]: Risks, Safe](https://img.kunalganglani.com/images/vzekdneq/production/ae489a760c8efd343421ac3a5e4b1f9b048acc2c-1200x675.webp?auto=format&fit=max&q=75&w=600)
Technology Claude Code Security [2026]: Risks, Safe Setup, Team Policy
Claude Code is safe only if you treat it like a junior engineer with terminal access. Here’s the 2026 playbook: permissions, sandboxing, egress controls, MCP allowlists, retention settings, and incident response.
AI and Machine Learning LangGraph vs CrewAI vs AutoGen vs PydanticAI [2026 Matrix]
A 2026 decision matrix for picking an agent framework based on use-case, failure modes, and the hidden production tax: tracing, retries, state, evals, and governance.
AI and Machine Learning AI Agent Control Flow Patterns [2026]: Retries, HITL, Checkpoints
A practical catalog of ai agent control flow patterns that actually ship: bounded retries, idempotent tools, durable checkpoints, human approvals, and debuggable replays.
AI and Machine Learning 9 Picks for the Best Local Model for Agentic Coding [2026]
A practical decision tree for agentic coding: pick local models by repo size and VRAM tier (16GB/24GB/48GB+/CPU), with context, tool-calling reliability, and quantization rules that actually hold up.
Technology Local LLM Benchmark Methodology [2026]: TTFT vs tok/s Done Right
Stop screenshot-benchmarking. Here’s a reproducible local LLM benchmark methodology for 2026 that separates TTFT from throughput and reports rerunnable results.