Context Is a Budget: What Changed in Our Team's Process When We Started Using AI Coding Agents
A practical, tool-agnostic workflow for specs, tests, review loops, worktrees, and team-owned configuration when coding agents join …
Viktoria Evdokimova
7 articles
2,773 views
Green Build, Wrong Task: A Working Agreement for Java Teams Using AI Coding Agents
Three ways AI coding agents waste a Java team's afternoon, and the spec, locked tests and capped review loop that stop it. Webinar notes, …
Can You Explain the Diff Your AI Agent Just Wrote?
Every Java developer has been in a code review where the question is simple: What does this method do? The answer used to tell you …
One Base URL, Many Coding Agents: What an OpenAI-Compatible Gateway Looks Like From java.net.http
Somewhere in every coding agent there is an HTTP client. Claude Code, Codex, Cursor, Cline, OpenCode: strip away the terminal UI or the …
Debugging Is Invariant Discovery: What One Kafka Session Taught Us About AI Agents
Every Java team has a sentence like this one somewhere: Any operation on a TID must go through the single asynchronous path and must not let …
“Commit created” — but it isn’t: why the agent’s word needs external verification, and what the mistake costs
A detailed report reads like proof. The agent lists the files it touched, names the branch, quotes a commit hash, adds a test count and …
Did Your AI Agent Ever Run a Debugger? One JVM Bug, Two Agent Runs
Java developers reach for the debugger without thinking about it. Set a breakpoint, run the failing test, look at the variables, then decide …