Writing archive · Page 6 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 6 of 9
More from the archive.
Showing 61–72 of 107 archive entries.
- Read the tutorial
AI agents · Human oversight · Security
Human Approval for AI Agents: Bind Approval to the Exact Action
Design approval previews, cryptographic action binding, expiry, authorization, execution, and audit trails for consequential agent actions.
- Read the tutorial
PostgreSQL · pgvector · Retrieval-augmented generation
Hybrid Search with PostgreSQL and pgvector: Full Text, Vectors, and Rank Fusion
Combine PostgreSQL lexical search with pgvector semantic retrieval using reproducible ranking, tenant-safe filters, and measured relevance.
- Read the tutorial
LLM as a judge · AI agent evaluation · Human evaluation
LLM-as-a-Judge: How to Calibrate It Against Humans
Calibrate a model grader with blinded human labels, bias probes, agreement diagnostics, and explicit rules for when automation must abstain.
- Read the tutorial
Multi-agent systems · Performance · TypeScript
Make Agent Swarms Faster and Cheaper with Bounded Parallelism
Use dependency graphs, a tested worker pool, cancellation, deduplication, and budgets to reduce multi-agent latency without creating rate-limit and cost failures.
- Read the tutorial
Model Context Protocol · User experience · Security
MCP Elicitation: Ask Users for Input Without Asking for Secrets
Implement form- and URL-mode MCP elicitation with explicit navigation approval, schema validation, identity binding, and safe resume behavior.
- Read the tutorial
Model Context Protocol · AI agents · Security
MCP Sampling with Tools: Build a Bounded Server-Initiated Model Loop
Let an MCP server request model work through its client while enforcing tool capability checks, iteration budgets, approvals, and message balance.
- Read the tutorial
Model Context Protocol · Performance · Distributed systems
MCP stdio vs. Streamable HTTP: How to Choose and Benchmark the Transport
Compare MCP's two standard transports and run a fair benchmark covering startup, latency, concurrency, streaming, recovery, and security.
- Read the tutorial
Model Context Protocol · API design · AI agents
MCP Tools vs. Resources vs. Prompts: A Practical Decision Guide
Choose the right MCP primitive for actions, application-selected context, and user-invoked workflows, then design each contract safely.
- Read the tutorial
Model Context Protocol · Agent2Agent · AI architecture
MCP vs. A2A: Which Agent Protocol Do You Need?
A practical architecture guide to using MCP for tools and context, A2A for peer-agent work, and both without collapsing their trust boundaries.
- Read the tutorial
Voice agents · Performance · Observability
Measure Voice-Agent Latency Correctly: From Speech End to Audible Response
Instrument a voice agent with one clock model, turn-level milestones, WebRTC media statistics, and latency budgets that expose the real bottleneck.
- Read the tutorial
AI agent memory · AI agents · Retrieval-augmented generation
Memory Consolidation for Long-Running AI Agents
Turn raw agent events into reviewable memories with provenance, deduplication, contradiction handling, decay, and safe forgetting.
- Read the tutorial
TypeScript · Monorepos · AI engineering
Migrate an AI Monorepo to TypeScript 6 Without Hiding Breakage
A package-by-package migration plan for TypeScript 6 defaults, deprecations, type environments, project references, and the TypeScript 7 transition.