Writing archive · Page 9 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 9 of 9
More from the archive.
Showing 97–107 of 107 archive entries.
- Read the tutorial
OpenTelemetry · AI observability · Multi-agent systems
Trace AI Agents with OpenTelemetry: Spans, Tokens, Tools, and Redaction
Instrument agent, model, retrieval, and tool work in one trace using current OpenTelemetry GenAI conventions without exporting prompts or secrets by accident.
- Read the tutorial
AI agent evaluation · Tool-using agents · Trajectory evaluation
Trajectory Evaluation for Tool-Using AI Agents
Evaluate agent tool selection, arguments, ordering, evidence, side effects, and efficiency without requiring one brittle golden path.
- Read the tutorial
pgvector · PostgreSQL · Vector search
Tune pgvector HNSW for Recall, Latency, Filtering, and Memory
Use an exact-search baseline and a repeatable benchmark to tune pgvector HNSW construction, query, filtering, and memory parameters.
- Read the tutorial
Voice agents · Speech interfaces · Evaluation
Turn-Taking for Voice Agents: Endpointing, Interruption, and Backchannels
Design and evaluate voice-agent turn taking without treating every silence as completion or every sound as an interruption.
- Read the tutorial
AI agents · JSON Schema · TypeScript
Typed Agent Artifacts with JSON Schema and TypeScript
Create versioned plans, reports, patches, and decisions that are validated at runtime instead of trusting model-generated prose.
- Read the tutorial
Coding agents · PostgreSQL · Database migrations
Use Coding Agents Safely for Database Schema Changes
Have coding agents plan and verify expand-migrate-contract changes without granting them unsupervised production database access.
- Read the tutorial
PostgreSQL · AI agents · Event sourcing
Use PostgreSQL 18 UUIDv7 for AI Agent Event IDs
Design time-ordered, idempotent agent-event tables with PostgreSQL 18 uuidv7 without confusing identity, time, and sequence.
- Read the tutorial
React · AI agents · Interface architecture
Use React 19.2 Activity for Multi-Session Agent Interfaces
Preserve agent-session UI state across tabs while correctly stopping effects, controlling memory, and protecting sensitive sessions.
- Read the tutorial
Model Context Protocol · API design · Testing
Version an MCP Server Without Breaking Clients
Evolve tools, resources, prompts, transports, and experimental features using protocol negotiation, additive contracts, compatibility tests, and staged removal.
- Read the tutorial
AI agents · Human oversight · Safety
When Should an AI Agent Ask for Help?
Implement escalation rules for ambiguity, missing authority, weak evidence, uncertain side effects, and high-impact decisions.
- Read the tutorial
Coding agents · AGENTS.md · Developer experience
Write an AGENTS.md File That Actually Helps Coding Agents
Create concise repository instructions that expose non-obvious commands, boundaries, architecture, and verification without duplicating discoverable documentation.