Notes from the work

Build the thing.
Explain the hard part.

Practical field notes about AI agents and modern software systems—tested against real constraints, written so you can make a better next decision.

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 last reviewed and tested.

Useful past the quickstart.

10 pieces, built to get you from promising demo to dependable system.

  1. AI agents · Multi-agent systems · Architecture

    Agent Swarms: When Multiple AI Agents Help—and When They Make Things Worse

    A practical decision framework for choosing a multi-agent architecture, plus a minimal coordinator that keeps concurrency, budgets, and failure handling explicit.

    10 min read
    Read the field note
  2. 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.

    7 min readTested Jul 18, 2026
    Read the field note
  3. AI agent evaluation · Continuous integration · AI testing

    AI Agent Evals in CI: A Release Gate for Prompts, Models, and Tools

    Build a provider-neutral agent evaluation suite with deterministic checks, repeated trials, safety cases, uncertainty, and a CI policy that catches regressions.

    5 min read
    Read the field note
  4. AI agent memory · PostgreSQL · pgvector

    AI Agent Memory with Postgres and pgvector: Schema, Retrieval, and Forgetting

    Design tenant-safe agent memory with provenance, hybrid search, retention, deletion, and pgvector indexing that does not mistake every transcript for knowledge.

    7 min read
    Read the field note
  5. Model Context Protocol · TypeScript · AI agents

    Build an MCP Client in TypeScript: Discovery, Tool Calls, and Trust Boundaries

    Connect to a local MCP server, verify capability discovery, call a typed tool, and handle remote transports without confusing discovery with authorization.

    6 min readTested Jul 18, 2026
    Read the field note
  6. Model Context Protocol · TypeScript · AI agents

    Build a Safe MCP Server in TypeScript: Tools, Validation, and Transports

    Build and test a real MCP stdio server, then make the transport, validation, error, and authorization decisions required for a remote deployment.

    6 min readTested Jul 18, 2026
    Read the field note
  7. Durable execution · AI agents · Workflow orchestration

    Durable AI Agents: Retries, Idempotency, Human Approval, and Resume

    Design long-running agent workflows that survive crashes, retry only safe work, bind approvals to exact actions, and reconcile ambiguous side effects.

    6 min read
    Read the field note
  8. 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.

    7 min read
    Read the field note
  9. 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 field note
  10. 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.

    7 min read
    Read the field note