Topic

Agent Evaluation

7 pieces in this thread.

  1. A World Worth Learning From

    Before an agent can learn from experience, its environment has to produce experience worth learning from. A sixteen-run engineering study tested what survives after the agent commits.

    harness-engineeringagent-evaluationaec-benchtask-worlds
  2. The Attacker Moves Second. So Did I.

    My benchmark optimiser found the same seam an adversary would: it rewrote the world its own grader consumed. A design note on provenance ledgers—agent memory where authority comes from evidence, not persuasion.

    harness-engineeringagent-evaluationaec-benchagent-security
  3. Fluent, But Unsafe

    How 150 supposedly finished tasks and perfect model scores hid a weak engineering benchmark—and how auditable reviews exposed what the numbers missed.

    harness-engineeringagent-evaluationaec-benchtask-worlds
  4. Plausible Answers, Failed Workflows

    An AEC-Bench release evaluation read as workflow reliability, not prose quality. Chapter by chapter: why a model can produce a plausible answer and still fail the durable record a project has to audit.

    harness-engineeringagentic-aiai-in-aecai-benchmarks
  5. Making aec-bench Trainable with Prime Lab

    How aec-bench and Prime Intellect's Lab turn engineering benchmarks into verifier-backed RL environments, adapter training runs, and inspectable traces.

    aec-benchprime-labreinforcement-learningagent-evaluation
  6. What If the Harness Could Improve Itself?

    Applying the autoresearch pattern to self-improve an engineering agent harness. Automated prompt optimisation across HVAC audit tasks on Claude and GPT-4.1-mini, showing how harness engineering compounds when the improvement loop runs itself.

    harness-engineeringautoresearchagentic-aiai-in-aec
  7. Benchmarking Agents on Real Engineering Work Is Already Teaching Us Something Important

    Benchmarking AI agents on real HVAC engineering tasks across Claude and GPT models. Results on harness-dependent capability, agent evaluation design, and why AEC-domain benchmarks reveal what general benchmarks miss.

    harness-engineeringagentic-aiai-in-aecai-benchmarks