Topic

AI in AEC

Bring agents into architecture, engineering and construction with room to experiment and clear limits on authority.

Start here

  1. Broad Creation, Narrow Authority

    An open-ended approach to AI-enabled software: let practitioners explore, embed controls in the platform, and govern the moment an experiment acquires organisational consequence.

  2. Mediation, Not Intermediation

    Why the 'fix your foundations before AI' message has it backwards: agentic workflows are the way out of legacy data, and governance worth having is co-designed from practice, not committees.

  3. The Distance to the Edge

    Why organisational AI capability is nonlinear and why the edge is better understood as a learning regime than a position on a maturity ladder.

More in this topic

  1. 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.

    agent-evaluationaec-benchtask-worldsai-in-aec
  2. 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.

    agent-evaluationaec-benchai-in-aecharness-engineering
  3. 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-benchreinforcement-learningagent-evaluationai-in-aec
  4. Executable Standards

    Better tools and verifiers are not enough. The next harness boundary is the clause itself — turning standards, briefs, and codes into versioned predicates and replayable certificates.

    harness-engineeringformal-methodsai-in-aec
  5. 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-engineeringautoresearchagent-evaluationai-in-aec
  6. What HVAC Benchmarks Reveal About Agent Reliability

    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-engineeringagent-evaluationai-in-aecaec-bench
  7. Where Capability Actually Lives in Agentic Engineering

    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.

    harness-engineeringagentic-aiai-in-aec