Writing archive · Page 7 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 7 of 9
More from the archive.
Showing 73–84 of 107 archive entries.
- Read the tutorial
Coding agents · AI agents · Software architecture
Migrate Coding-Agent Frameworks Without Losing Behavioral Guarantees
Move a coding agent to a new framework through contract inventory, compatibility tests, dual runs, staged rollout, and a defined rollback.
- Read the tutorial
AI agents · Model routing · Evaluation
Multi-Model Routing for AI Agents: Design and Evaluate a Router
Route agent calls by capability, quality, latency, cost, privacy, and availability using an evaluated policy with safe fallbacks.
- Read the tutorial
PostgreSQL · Retrieval-augmented generation · Security
Multi-Tenant RAG with PostgreSQL Row-Level Security
Enforce tenant isolation across documents, chunks, vector retrieval, citations, caches, background jobs, and database roles.
- Read the tutorial
Next.js · AI applications · Caching
Next.js 16 Cache Components for AI Applications
Adopt Cache Components without leaking sessions, serving stale agent state, or invalidating more data than necessary.
- Read the tutorial
Model Context Protocol · OAuth · Security
OAuth for Remote MCP Servers: Discovery, Scopes, and Token Validation
Implement the MCP 2025-11-25 authorization boundary for an HTTP server without token passthrough, audience confusion, or excessive scopes.
- Read the tutorial
AI agents · Multi-agent systems · Reliability
Prevent Runaway Agent Delegation
Control delegation depth, fan-out, duplicate work, cycles, authority propagation, and result synthesis in multi-agent systems.
- Read the tutorial
AI agents · SSRF · Security
Prevent SSRF in AI Agent Tools
Build an outbound-request broker that stops agents from reaching internal services, cloud metadata, redirected targets, and DNS-rebinding destinations.
- Read the tutorial
Privacy · Multimodal AI · AI security
Privacy-Aware Multimodal Agents: Minimize Audio, Images, Documents, and Traces
Map multimodal data flows, collect only necessary regions and intervals, redact before model access, constrain retention, and verify deletion.
- Read the tutorial
Prompt injection · AI agents · Security
Prompt Injection Defense in Depth for Tool-Using Agents
Contain direct and indirect prompt injection with provenance, privilege separation, constrained tools, output validation, egress controls, and bound approvals.
- Read the tutorial
Retrieval-augmented generation · Evaluation · Information retrieval
RAG Chunking Strategies: How to Compare Fixed, Structural, Semantic, and Parent-Child Retrieval
Choose a RAG chunking strategy with a held-out benchmark that measures retrieval, answer evidence, citation quality, latency, and index cost.
- Read the tutorial
AI agent security · Red teaming · Prompt injection
Red-Team an AI Agent with Adversarial Tool Results
Test whether malicious search, document, email, and tool outputs can trigger unauthorized actions, memory poisoning, or data exfiltration.
- Read the tutorial
Coding agents · Git · Multi-agent systems
Run Parallel Coding Agents Safely with Git Worktrees
Give each coding agent an isolated branch and working directory, then integrate changes through explicit ownership, verification, and cleanup.