Skip to main content
Pollack AI Lab
Agent Infrastructure · Experiments
Helping you build agents that demonstrably work. A growing ecosystem of projects — usable together or individually — for composing, evaluating, and understanding agent behavior. Experiments that prove the approach works, with published data and reproducible results. By Mark Pollack, creator of Spring AI.

​
Highlights

What’s genuinely new and cool across the lab right now.

Run a workflow step in Anthropic's cloud

ManagedAgentStep hands one step of your workflow to Claude Managed Agents — a full hosted sandbox with bash, files, and web. Same graph; swap a single step between local JVM, Temporal, or Anthropic’s cloud.

Speak the latest Agent Client Protocol

Tracks ACP 0.14.0 — elicitation (agents ask you for structured input), session fork & resume, and provider config — dropping a Java agent straight into Zed, JetBrains, and VS Code.

Evaluate any agent, any framework

Agent Judge scores output from Spring AI, LangChain4j, Koog, or any CLI agent through one judge / jury layer — LLM and RAG judges (faithfulness, hallucination), plus tooling to evaluate the evaluators. Read the deep dive →

Provably CVE-clean dependencies

The AgentWorks BOM ships only behind a 9/9 convergence gate (plain / Boot 3.5 / Boot 4) — every consumer gets one coherent, vulnerability-free dependency set, verified in CI, not by hand.

Trace Claude and Gemini in one format

Agent Journal captures Claude and Gemini CLI runs into one portable trace + cost schema — one analysis layer across runtimes, no per-vendor lock-in. New in 1.5.0.

​
Active release train

The whole suite ships as one coordinated train, pinned by the AgentWorks BOM — currently 1.15.0, spanning a dozen libraries all shipped within the last month.

​
Core Projects

ACP Java SDK

Agent Client Protocol — build and consume agents for Zed, JetBrains, VS Code

Agent Workflow

Multi-step agentic pipelines with typed context, quality gates, and portable runtimes

Agent Judge

Evaluation with deterministic, command, and LLM judges

Loopy

Interactive coding agent CLI for Java developers

Agent Client

Claude, Gemini, Codex, Amazon Q as unified Spring services

Agent Journal

Behavioral trace capture for analysis and observability

Agent Bench

Benchmarking on real enterprise Java tasks

​
Latest Experiments

Code Coverage v3 — The Exemplar Effect
When existing tests use older patterns, skills can’t override them — the codebase is the agent’s primary teacher. 2 variants on Spring PetClinic.
Apr 2026 · Complete · Details →
Code Coverage v2 — Skills vs Knowledge Bases
Do structured skills beat flat knowledge injection? Skills + pre-analysis cut steps 31% with no quality loss. 7 variants.
Mar 2026 · Complete · Details →
Code Coverage v1 — Knowledge Injection Baseline
9 variants testing progressive knowledge injection on Spring Boot test generation.
Feb 2026 · Complete · Details →