Writing archive · Page 2 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 2 of 9
More from the archive.
Showing 13–24 of 107 archive entries.
- Read the tutorial
Retrieval-augmented generation · AI safety · Evaluation
Build a Citation-First RAG System That Rejects Unsupported Claims
Represent evidence at span level, require citations for verifiable claims, and abstain when retrieval cannot support a grounded answer.
- Read the tutorial
Coding agents · AI agents · Security
Build a Coding-Agent Harness with Hard Execution Boundaries
Wrap any coding model in a reproducible harness that controls workspaces, commands, credentials, budgets, evidence, and verification.
- Read the tutorial
GPU capacity planning · LLM inference · vLLM
Build a GPU Capacity Planner for LLM Inference
Estimate weights, KV cache, runtime overhead, context concurrency, and replica demand—then replace assumptions with measured service curves.
- Read the tutorial
Model Context Protocol · Multi-tenancy · Security
Build a Multi-Tenant MCP Gateway Without Collapsing Trust Boundaries
Route remote MCP traffic by authenticated tenant while isolating tokens, sessions, discovery, quotas, results, and audit records.
- Read the tutorial
AI agents · Architecture · TypeScript
Build a Plan–Execute–Review Agent Without Infinite Loops
Implement an agent loop with typed plans, evidence-based review, bounded revision, explicit stop states, and safe tool execution.
- Read the tutorial
Retrieval-augmented generation · Data engineering · AI agents
Build a Production RAG Ingestion Pipeline: Parse, Version, Embed, and Delete Correctly
Design a restartable RAG ingestion pipeline that preserves provenance, detects changes, avoids duplicate work, and removes stale chunks from retrieval.
- Read the tutorial
Voice agents · WebRTC · Real-time applications
Build a Real-Time Voice Agent over WebRTC
Design a reconnectable browser voice agent with explicit signaling, ephemeral authorization, audio lifecycle, interruption, and observable session state.
- Read the tutorial
AI agent testing · Simulation · Test environments
Build a Simulated World for AI Agent Testing
Create resettable, observable email, calendar, browser, and database environments that test agent effects without touching real systems.
- Read the tutorial
RAG · vLLM · pgvector
Build a Single-GPU RAG Stack
Reserve one GPU for generation, run embeddings and retrieval on CPU, store cited chunks in Postgres with pgvector, and evaluate retrieval before answers.
- Read the tutorial
Computer-use agents · Evaluation · Browser automation
Build a Visual Browser-Agent Benchmark That Measures Real Task Success
Create resettable visual web tasks with programmatic outcome validators, layout perturbations, safety checks, and reproducible multimodal traces.
- Read the tutorial
WebAssembly · AI agents · Sandboxing
Build AI Agent Tools as WebAssembly Components
Define typed WIT contracts, explicit capabilities, resource limits, provenance, and conformance tests for portable agent tools.
- Read the tutorial
Coding agents · Code review · AI agents
Build an Evidence-First Code Review Agent
Design a review agent that reports reproducible defects with precise evidence instead of producing noisy summaries and style opinions.