Writing archive · Page 8 of 9
More tutorials.
Same standard.
More entries from a 110-piece collection of tested, source-checked engineering notes.
- Evidence
- Working code, observable results, and primary sources.
- Judgment
- Tradeoffs, failure modes, and when not to use the technique.
- Freshness
- Every tutorial shows when it was reviewed—and a tested date only when its example was run.
Page 8 of 9
More from the archive.
Showing 85–96 of 107 archive entries.
- Read the tutorial
Sandboxing · WebAssembly · Containers
Sandbox Untrusted Agent Code: Containers vs. WebAssembly
Choose and harden an isolation boundary for generated code using explicit filesystem, network, process, syscall, resource, and output controls.
- Read the tutorial
AI agents · Secrets management · Security
Secrets Management for AI Agents Without Putting Secrets in Context
Give agent tools short-lived credential handles while keeping passwords, tokens, keys, and connection strings out of prompts, memory, traces, and results.
- Read the tutorial
Browser agents · Playwright · AI security
Secure Browser Agents with Playwright: Isolation, Network Policy, and Approval
Build a browser-worker boundary that treats webpages as hostile, isolates credentials, blocks unapproved network destinations, and requires approval for consequential actions.
- Read the tutorial
Next.js · AI security · Server Actions
Secure Next.js Server Actions for AI Agent Operations
Authenticate, authorize, validate, rate-limit, and make high-risk agent mutations idempotent in Next.js 16.
- Read the tutorial
vLLM · Tool calling · Open models
Serve a Tool-Calling Model with vLLM
Configure vLLM's OpenAI-compatible server, model-specific parser, strict schemas, and a safe execution loop for local tool calling.
- Read the tutorial
LoRA · vLLM · Model serving
Serve Multiple LoRA Adapters with vLLM
Share one pinned base model across reviewed LoRA adapters while preserving lineage, tenant routing, cache isolation, memory limits, and measurable quality.
- Read the tutorial
AI agent evaluation · Shadow testing · Production reliability
Shadow Testing AI Agents in Production
Compare a candidate agent on representative production inputs while suppressing side effects, protecting user data, and avoiding misleading metrics.
- Read the tutorial
AI agent evaluation · Statistics · Experiment design
Statistical Confidence for AI Agent Evaluations
Choose estimands, experimental units, paired comparisons, confidence intervals, power, and release thresholds that match stochastic agent evaluations.
- Read the tutorial
AI agents · Multi-agent systems · Evaluation
Supervisor vs. Handoffs vs. Agent Graphs: A Reproducible Comparison
Choose a multi-agent topology using a benchmark protocol that measures task success, coordination cost, latency, and unsafe actions.
- Read the tutorial
OpenTelemetry · AI observability · Privacy
Tail Sampling and Redaction for AI Agent Traces
A privacy-first OpenTelemetry Collector pipeline for retaining useful agent traces without exporting sensitive prompts by default.
- Read the tutorial
Retrieval-augmented generation · PostgreSQL · Data modeling
Temporal RAG: Answer Questions Using the Correct Historical Version
Build version-aware retrieval with valid-time ranges, immutable sources, time-filtered ranking, and citations that preserve what was known when.
- Read the tutorial
AI agents · Threat modeling · Security
Threat Model an AI Agent System from First Principles
Turn an agent architecture into a data-flow model, identify attacker paths across tools and memory, and convert the highest risks into testable controls.