markpollack/acp-java-tutorial
Progressive tutorial for learning the ACP Java SDK
Progressive tutorial for learning the ACP Java SDK
Judge framework for evaluating AI agent outputs
A systematic approach to growing AI agents — run, judge, read the journal, fix, repeat
Autonomous CLI agent integrations for the Spring AI ecosystem with Claude Code, Gemini CLI, and secure sandbox execution
Progressive tutorial modules for learning Agent Judge evaluation
Loop-driven interactive coding agent CLI — MiniAgent + tui4j + forge lifecycle
Execution ledger — Experiment/Run tracking for agent workflows
Purpose-built Java experiment driver for AI agent evaluation — orchestrates git reset, pre-processing, agent invocation, judging, scoring, tracking, comparison, and Langfuse export.
Foundation library implementing agentic loop patterns with judge-based evaluation
Open benchmarking suite for Java-centric AI developer agents with isolated sandboxes and comprehensive evaluation
Sandbox abstraction for secure code execution in AI agent applications
Tutorial examples for the Claude Agent SDK for Java
Standard agent experiment project template with pre-wired experiment loop
Runnable examples for Agent Workflow DSL — validated with real LLM calls
Reusable GitHub Actions workflows for Maven Central publishing
Data Exploration for GitHub PRs
Progressive memory management for Spring AI
Spring Initializr for agent experiments — creates runnable experiment projects from a brief
Agent Client tutorial — progressive examples from first task to multi-provider
Code coverage experiment v3: partial knowledge paradox — existing tests vs skills
ACP implementation for Java
Code coverage improvement agent experiment — scaffolded by forge
Project Management Agent for Spring AI
Giscus comment discussions for blog.pollack.ai