#ai-in-aec
Posts in this topic thread.
Why domain-specific agent harnesses, not bigger models, are what close the AI performance gap on real engineering tasks — and why the AEC industry needs proper benchmarks to prove it.
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.
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.
In AEC and domain-specific engineering, AI agent capability lives not in the model alone but in harness engineering — the tools, verifiers, orchestration, and process design that make agentic work reliable.