Training course · AI Agents · Construction & Architecture

AI Agents for Construction and Architecture

Agentic AI for business teams: understand AI agents, automate workflows safely and keep control with human-in-the-loop and governance.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

This course connects AI Agents with the everyday processes of Construction & Architecture. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

AI agents go a step beyond conventional chat assistants: they plan sub-tasks, use tools such as search, files or business applications and complete multi-step work largely on their own. Over two days you will learn how agents are built, how they differ from chatbots and traditional automation, and which tasks genuinely justify their use. Widely used platforms serve as practical examples, including Microsoft Copilot Studio, custom GPTs and Claude with projects and tool connections.

In the hands-on sessions you design agent workflows for tasks from your own area of work, from triaging requests through research and drafting to handing results over to business systems. You decide where a person reviews and approves, which permissions an agent receives and how errors are detected. A dedicated block covers governance, data protection and accountability, so that your agents not only work but remain controllable, traceable and defensible within your organisation.

Construction projects generate vast amounts of documentation: tenders, bills of quantities, specifications, minutes, snagging lists, variations, correspondence with authorities and standards. Architecture practices, engineering consultancies, contractors and clients spend a great deal of time on writing work that generative AI can speed up considerably. AI assistants help draft specification clauses, turn voice notes into site meeting minutes, structure variation claims, write competition and design statements and review extensive contract documents. Image-generating AI supports early design and visualisation stages. Professional and legal liability remains with designers and contractors – AI is a tool, not a substitute for knowledge of standards, structural engineering or site management.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Architects
  • Civil and building services engineers
  • Site managers and project managers
  • Estimators and planners at contractors
  • Client representatives and public works departments

Typical challenges we address

  • Heavy documentation workload on site and in the office
  • Extensive bills of quantities, contracts and standards
  • Contentious variations, defects and delay notices
  • Skills shortages alongside rising design and sustainability requirements

What you will be able to do

  • You can explain how AI agents are structured and clearly distinguish them from chatbots and classic automation.
  • You can select a suitable agent platform for your requirements using transparent criteria.
  • You can design an agent workflow for a real process in your area and build a working prototype.
  • You can define human-in-the-loop checkpoints, test cases and escalation rules.
  • Produce minutes, specifications and correspondence more efficiently with AI.
  • Analyse contract and project documents with AI in a structured way and spot risks earlier.
  • Use AI responsibly with due regard to liability, standards and confidentiality.

Course outline

Day 1

Module 1 What makes an AI agent
  • Agent building blocks: language model, instructions, knowledge, tools and memory
  • How agents differ from chatbots, macros and classic workflow automation
  • Levels of autonomy: from suggestion-making assistants to agents that act independently
  • Realistically judging which tasks suit agents and which do not
Module 2 Platform overview: Copilot Studio, GPTs and Claude
  • Microsoft Copilot Studio: agents grounded in company data and connected to Microsoft 365
  • Custom GPTs: configuring instructions, knowledge files and actions
  • Claude with projects, knowledge bases and tool access via the Model Context Protocol
  • Selection criteria: data access, integrations, administration and licensing
Module 3 Designing and building agent workflows
  • Breaking tasks into steps and defining hand-offs between agent and human
  • Writing system instructions, examples and knowledge sources for consistent output
  • Connecting tools: search, documents, email, spreadsheets and business applications
  • Building a prototype agent for a real process from your own area
Module 4 Human-in-the-loop, quality and error handling
  • Setting approval steps, escalation rules and thresholds for human review
  • Test cases, evaluation criteria and spot checks for quality assurance
  • Common failure modes: wrong tool choice, endless loops and fabricated facts
  • Using structured user feedback to improve the agent over time

Day 2

Module 5 Governance, security and roll-out
  • Roles and responsibilities across business units, IT, data protection and works council
  • Least-privilege permissions, logging and protection against prompt injection
  • Positioning under the EU AI Act and GDPR: transparency, documentation and data flows
  • From pilot agent to production: operation, maintenance and measuring success
Module 6 Practice lab: Construction & Architecture
  • Drafting specifications
  • Site meeting minutes
  • Variations and correspondence
  • Reviewing contract documents
  • Competition and design statements
  • Defects management
Module 7 Data protection, quality & transfer to daily work
  • Professional and legal liability for design, tendering and site supervision remains with the designer or contractor; AI output must be checked against standards, building regulations and contract terms. Public contracts are subject to procurement law and tender confidentiality, and copyright in designs must be respected.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Drafting specifications

AI helps write clear and complete item descriptions for bills of quantities, spot gaps and contradictions and structure preliminaries – reviewed by the designer. Gaps are flagged for the designer.

Site meeting minutes

Voice notes and bullet points from site meetings or inspections become structured minutes with findings, responsibilities and deadlines, circulated to all parties. Photos are linked to each item.

Variations and correspondence

Delay notices, variation quotes, notices of concern and replies are prepared objectively and in line with the contract, with reference to the relevant contractual provisions.

Reviewing contract documents

Building contracts, special conditions and specifications are summarised for deadlines, liquidated damages, warranties and departures from standard terms, as a basis for legal review. Differences between contract versions are highlighted too.

Competition and design statements

Design concepts, sustainability strategies and project descriptions for competitions, planning applications or presentations are written concisely and tailored to different audiences. Length limits in competition briefs are respected.

Defects management

Defect reports are classified by trade and location, descriptions standardised and letters requesting remedial work with deadlines prepared. Progress stays transparent for site management and client alike.

Prerequisites

You should already use an AI assistant such as ChatGPT, Copilot or Claude on a regular basis. No programming skills are required. Professional experience in design, construction or project management; no programming skills required.

Technical requirements

You will need a laptop with an up-to-date browser. Ideally you have access to at least one agent platform such as Copilot Studio, ChatGPT with GPTs or Claude; practice accounts can be provided if needed.

Data protection & compliance

Professional and legal liability for design, tendering and site supervision remains with the designer or contractor; AI output must be checked against standards, building regulations and contract terms. Public contracts are subject to procurement law and tender confidentiality, and copyright in designs must be respected.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Thu, 10 December 2026 – Fri, 11 December 2026 Bremen Request
  • Thu, 14 January 2027 – Fri, 15 January 2027 Online Request
  • Tue, 19 January 2027 – Wed, 20 January 2027 Salzburg Request
  • Tue, 26 January 2027 – Wed, 27 January 2027 Online Request
  • Tue, 9 February 2027 – Wed, 10 February 2027 Kaiserslautern Request

Frequently asked questions

Do I need programming skills to build AI agents?

No. The platforms used on the course rely on visual interfaces, plain-language instructions and ready-made connectors. You learn to specify agents precisely from a business perspective, connect tools and test workflows. Where deeper technical integration would be needed, you will know which requirements to put to your IT team.

Which platform will we use during the course?

The course is vendor-neutral and uses Microsoft Copilot Studio, custom GPTs and Claude as examples. You build your prototype on the platform that is available or planned in your organisation. The principles of workflow design, control and governance you learn carry over to other agent solutions as well.

How do I stop an agent from acting without control?

Through deliberate design: agents receive only the minimum permissions they need, critical actions such as sending, booking or deleting require human approval, and every step is logged. In addition, you define test cases and escalation rules. These are exactly the control mechanisms you develop for your own use case during the course.

Can AI produce a bill of quantities?

AI can draft item descriptions, suggest structures and highlight gaps. Quantities, technical requirements and alignment with standards and design remain the responsibility of the designer, who is also liable. In the course you practise using AI as a drafting aid and reviewing results systematically.

Can drawings and plans be uploaded to AI tools?

Only if confidentiality agreements, copyright and your firm's policies allow it and the tool is approved. Strict requirements apply especially for security-sensitive buildings or public clients. The course shows how to work with approved solutions and sanitised documents. Project names and addresses can be removed beforehand.

How much does “AI Agents for Construction and Architecture” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Construction and Architecture

More AI Agents courses

All 45 AI Agents courses

AI Agents · MunichAI Agents · SalzburgAI Agents · BerlinAI Agents · AugsburgAI Agents · HanoverAI Agents · BremenAI Agents · StuttgartAI Agents · KaiserslauternAI Agents · Online