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.

More from the archive.

Showing 8596 of 107 archive entries.

  1. 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.

    7 min read
    Read the tutorial
  2. 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.

    6 min read
    Read the tutorial
  3. 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.

    7 min read
    Read the tutorial
  4. 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.

    6 min read
    Read the tutorial
  5. 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.

    6 min read
    Read the tutorial
  6. 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.

    7 min read
    Read the tutorial
  7. 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.

    5 min read
    Read the tutorial
  8. 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.

    6 min read
    Read the tutorial
  9. 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.

    6 min read
    Read the tutorial
  10. 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.

    6 min read
    Read the tutorial
  11. 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.

    4 min read
    Read the tutorial
  12. 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.

    5 min read
    Read the tutorial