Visual guide · AI basics for AEC

Useful AI is more than a model.

A simple technical guide to the data, context, harness, workflows, review, and traceability required to make AI dependable inside an architecture or engineering firm.

Download Instagram animation

The 15-second version

Watch the system assemble.

The social animation uses the same semantics as the technical diagrams: orange shows active intelligence, green shows professional review, and every output retains a route back to evidence.

The four-part system

The pieces behind useful AI.

Start with the difference between general intelligence and the governed system that puts it to work on real project evidence.

01 · AI basics

Useful AI is a system, not just a model.

01Firm data

Models · drawings · email

02Project context

Relevant, permissioned evidence

03Foundation model

Claude · GPT · Gemini

04AI harness

Tools · rules · checks

05Professional review

Approve · revise · reject

Approved project output with evidence attached

The foundation model supplies general reasoning. Firm data, project context, controls, and professional review make that reasoning useful for project work.

02 · AI basics

The model reasons. The harness controls.

InstructionsProject contextTyped toolsPermissionsGuardrailsTrace + evaluations

Replaceable intelligenceFoundation model

Professional review before consequential action

The harness is the governed software around the model. It determines what context the model sees, which tools it may use, how results are checked, and when a person must decide.

03 · AI basics

A conversation answers. A workflow completes a bounded task.

Chatbot

QuestionResponse

Useful for research, explanation, and drafting.

Governed workflow

RFI receivedRetrieve evidenceDraft responseArchitect review

Useful for repeatable project work with defined controls and outcomes.

Agentic does not mean uncontrolled. A production workflow has a goal, evidence, tools, stop conditions, a visible trace, and an approval gate before material action.

04 · AI basics

Personal AI workspace versus firm AI operating layer.

Claude DesktopPerson ↔ general AI workspace

ConversationsFilesConnected tools

Designed primarily for individual knowledge work.

AEC HubFirm systems → governed project workflows

Project contextModel choiceReview + trace

Designed for repeatable, permissioned AEC work across projects.

Claude can be one of the foundation models used inside AEC Hub.

Claude Desktop helps an individual work with AI. AEC Hub coordinates models, project evidence, permissions, workflow controls, review, and traceability across the firm.

The technical takeaway

Models are components

Claude, GPT, Gemini, and future models provide reasoning. They do not provide firm context, permissions, or accountability by themselves.

The harness creates control

The software around the model selects context, exposes typed tools, enforces permissions, records traces, and stops for review.

Agentic means bounded execution

A dependable workflow has a goal, evidence, tools, stop conditions, evaluations, and an explicit approval transition.

Firm context is the durable layer

Models can change while project evidence, firm methods, workflow definitions, and approved learning remain owned by the firm.

Go deeper

See how the governed learning loop works.

Explore the platform architecture