Skip to content

jakemeany523/judgment-engineering

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Judgment Engineering

A framework for AI evaluation that generates, judges, and learns.

Evaluation can't be a static test suite anymore. Models change weekly. Agents execute multi-step traces. Output-level testing misses failures that happen inside the reasoning chain. Judgment Engineering is the methodology for evaluation that keeps up.

License: MIT

The Problem

Traditional LLM evaluation is stuck in two modes:

Benchmarks provide shared standards, but they hit a saturation wall. Top models cluster above 90% on MMLU. Differences are statistically meaningless. Contamination is real. Scaffold gaming means the same model scores 62% with one setup and 70% with another.

Eval Engineering formalized evaluation as a discipline (a good step), but it still only scores outputs. It doesn't generate new tests. It doesn't improve itself. It can't see inside agent execution traces.

Neither mode handles what's actually happening in production: multi-agent systems that make autonomous decisions, accumulate errors across steps, and fail in ways that look fine from the outside.

The Three Stages

Stage 1: Benchmarks         Stage 2: Eval Engineering     Stage 3: Judgment Engineering
-----------------------     -------------------------     ----------------------------
Static test suites          Custom eval pipelines         Adaptive test generation
Public leaderboards         Domain-specific criteria      Agentic judges (trace-level)
One-time scoring            Continuous loops              Self-improving judge calibration
Output-level only           Output-level only             Full execution trace analysis

Judgment Engineering doesn't replace the first two stages. It builds on them.

Core Principles

1. Generate

Evaluation should create its own test cases. Not just run existing ones.

  • Adaptive test scenarios generated from production failures
  • Adversarial inputs targeting known model weaknesses
  • Each evaluation cycle produces new tests, not just new scores

2. Judge

Evaluation should read the full story, not just the final answer.

  • Agent-as-Judge: Judges that read execution traces, retrieve supporting files, and test code. >90% agreement with human experts (vs. ~70% for standard LLM-as-Judge).
  • Multi-model panels: Multiple judges reduce individual model bias. Position bias, verbosity bias, and self-enhancement bias are documented problems.
  • Natural language criteria: Evaluation rules written in plain language, not hard-coded logic. Domain experts define what "good" means without writing code.
  • Evidence chains: Every verdict comes with reasoning and cited evidence from the trace.

3. Learn

Evaluation should get better over time without human intervention.

  • Judge optimization (GEPA) closes the human-judge agreement gap by 10% average (up to 19% on specific tasks)
  • Each cycle feeds back into test generation and judge calibration
  • Judges calibrate against human expert decisions on high-stakes verdicts
  • The evaluation system improves itself as a byproduct of doing its job

Why Trace-Level Matters

The refund agent example: A customer requests a refund. The agent retrieves the return policy, identifies three policy violations, then approves the refund anyway. The final output looks correct ("Refund approved"). Output-level testing would pass this. Trace-level evaluation catches the reasoning failure.

Multi-agent failures (from "Agents of Chaos" research):

  • 124 internal emails containing SSNs and bank details disclosed to unauthorized agents
  • Circular messaging loops burning 60,000+ tokens with no progress
  • Agents reported tasks as complete while system state contradicted their reports

These failures are invisible to output-level evaluation. You can only catch them by reading the execution trace.

The Routing Architecture

Not every evaluation needs a full agentic judge. The cost-effective approach routes by complexity:

80%  Cheap deterministic checks
     Format validation, keyword matching, length constraints
     Cost: ~$0

15%  Calibrated LLM judges
     Semantic quality, domain accuracy, style compliance
     Cost: ~$0.01-0.05 per evaluation

5%   Full Agent-as-Judge
     Complex traces, high-stakes decisions, anomaly investigation
     Cost: ~$0.10-0.50 per evaluation

Total: ~$47 per 1,000 evaluations (multi-model panels) vs. $312 for human experts.

Five Questions

Use these to assess whether an evaluation system qualifies as Judgment Engineering:

  1. Can it think? Does it generate adaptive tests, optimize its own judges, define criteria in natural language, and produce structured verdicts with evidence?

  2. Can it see everything? Does it evaluate across vendors (no lock-in), use multi-model judge panels, and handle multiple modalities (text, image, code, voice)?

  3. Does it keep watching? Is evaluation continuous and tied to model release cycles, not human schedules? Can it gate releases?

  4. Does it work on your reality? Can it run custom datasets in private environments with domain-specific scoring? Public benchmarks cover maybe 10% of real use cases.

  5. Who reviews the verdicts? Do humans adjudicate high-risk verdicts, recalibrate judges, and define escalation thresholds?

Evidence

Claim Source
Traditional LLM-as-Judge: ~70% agreement with human experts Judging LLM-as-a-Judge, 2023
Agent-as-Judge: >90% agreement with human experts Agent-as-Judge, 2024
Judge optimization (GEPA): +10% average improvement GEPA, 2025
64% of companies over $1B revenue lost >$1M to AI failures Industry surveys, 2025
Only 11% have agentic AI in production; 94% fail to scale past 25 systems Enterprise AI deployment data, 2025
EU AI Act enforcement: August 2026 (penalties up to 3% of global annual turnover) EU regulation

Getting Started

Read the Manifesto

The full thesis with evidence, examples, and methodology:

manifesto/the-rise-of-judgment-engineering.md

Run an Example

Basic evaluation using the Stratix SDK:

from layerlens import PublicClient

client = PublicClient(api_key="your-api-key")

# List available benchmarks
benchmarks = client.list_benchmarks()

# Get evaluation results for a specific model
results = client.get_evaluation_results(
    model_id="claude-opus-4-6",
    benchmark_id="swe-bench-lite"
)

# Compare models across benchmarks
comparison = client.compare_models(
    model_ids=["claude-opus-4-6", "gpt-4.1", "gemini-2.5-pro"],
    benchmark_ids=["swe-bench-lite", "livecodebench", "arc-agi-2"]
)

More examples in examples/.

Project Structure

judgment-engineering/
  manifesto/
    the-rise-of-judgment-engineering.md    # Full thesis
  methodology/
    getting-started.md                     # How to apply JE principles
    principles.md                          # Core principles expanded
  examples/
    basic-evaluation.py                    # Simple Stratix SDK usage
    judge-pipeline.py                      # Multi-judge evaluation pipeline
    trace-evaluation.py                    # Trace-level agent evaluation
  README.md

Related Projects

Built by Jake Meany at LayerLens:

License

MIT

About

A framework for AI evaluation that generates, judges, and learns. Methodology, manifesto, and examples.

Resources

License

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors