Field Notes
Notes on event-driven Java, Spring Boot, Kafka, and secure systems for regulated banking.
The multi-part series and running themes, rather than one long pile.
Learning Embabel by building with it, in order — planning, testing without a model, tools, human-in-the-loop, tracing, exposing it over MCP.
Build it, attack it, extend it — the Ask Zakaria concierge from first prompt through prompt-injection red-teaming to matching a job description.
Instrument it, learn to query it, then point it at something that thinks.
An agent as a collaborator rather than an autocomplete — design systems, durable knowledge, automation ladders, subagent fleets on my own source, and now in CI.
Secrets delivery, response headers, a cookie banner that sets no cookies — and what happens when you attack your own features.
Shipping and operating my own product in public — one jar serving two hosts, making it findable, dropping experiments into it, shipping a free CV builder off the side.
Building agents on the JVM with Embabel · Part 7
My agent refused to run a single action. The @Condition gate was FALSE and nothing in the agent could ever make it TRUE, because Embabel builds an action's effects from what you declare, not from what your condition reads.
Claude Code keeps a usage ledger nobody reads. After 511 sessions I opened mine: 73 skills invoked, 31 of them exactly once, three still on disk. The survivors all have one thing in common.
I ran /install-github-app on my own repo and ten minutes later a README PR was merged. The timings are the least interesting part — the write path, the commit attribution and whose rules the CI agent followed are better.
Building agents on the JVM with Embabel · Part 6
Turning my JVM agents into MCP tools took one dependency and one annotation. It also took three silent failures -- a starter that suppresses the web server, a shell that eats your CLI flags, and an annotation default that publishes exactly zero tools without telling you.
Building agents on the JVM with Embabel · Part 5
I pointed my Embabel agents at a local Grafana LGTM stack and saw nothing. Three configuration gotchas later, every GOAP planning step, LLM call and tool loop shows up as a span in Tempo. Here is the full walkthrough, with screenshots.
Building agents on the JVM with Embabel · Part 4
In regulated work the dangerous agent is the one that acts without asking. Here's how I made an Embabel agent pause for human approval before moving money -- with the approval built into the type graph, not an if-check.
Building agents on the JVM with Embabel · Part 3
An LLM cannot know a live account balance, and in banking a confidently hallucinated number is a disaster. The fix is a tool. Here's how @LlmTool works in Embabel on the JVM, plus the one API gotcha that cost me a compile.
Building agents on the JVM with Embabel · Part 2
The non-deterministic part of an agent is the LLM. Box it out and the rest is ordinary, deterministic code you can test. Here's how I test Embabel agents on the JVM without spending a single token.
Building agents on the JVM with Embabel · Part 1
My first afternoon with Embabel, the JVM agent framework. I added one action too many, the planner quietly stopped early, and a cryptic get(...) must not be null taught me how GOAP, goals, and AgentInvocation actually fit together.
I pointed the new claude-security plugin at this very site. It spawned 82 agents, proposed 10 vulnerabilities, and then argued itself out of 9 of them. The one that survived was real — and it shipped to prod the same afternoon.