Claude in the design office

Key information

The extended option combines core Claude skills (Day 1) with advanced workshops covering four to five design office processes, integration with a project management system, and a module on automatic meeting minutes from client meetings and controlling the Chrome browser (Day 2). The exercises are based on examples prepared by the trainer, set in the realities of design office work: quotations, cost estimates, documentation and client correspondence. Each module ends with a concrete result that participants can adapt to their daily work.

During the training, participants will learn, among other things:

• How to tell Claude Cowork apart from Claude Chat and other AI applications, and when to use which
• How to analyse quotation documents, cost estimates in Excel and concept presentations in PowerPoint with the help of Claude
• How to connect Microsoft 365 to Claude and work on project files through the connector
• How to create and use Claude projects as dedicated workspaces for individual commissions
• How to build your own Claude “skills” that automate the preparation and updating of quotations
• How to build three advanced skills that support further design office processes (on the second day)
• How to use Claude to compare and tabulate quotations and search them by criteria (floor area, budget, type of building, scope of author’s supervision)
• How to configure Fireflies for automatic transcription of client meetings and site visits
• How to connect Claude with Fireflies to search the archive of meetings and client agreements with a single question
• How to have Claude perform actions in the browser, e.g. searching for building standards and material specifications
• How to use Claude subagents to delegate complex tasks to several agents in parallel
• How to work safely with project data and client data in an AI environment

Objective

The objective of the training is to familiarise participants with the possibilities of Claude AI in the daily work of a design office at two levels. Day 1 covers core skills: working with Office documents, integration with Microsoft 365, and building projects and simple skills that automate repetitive tasks, such as preparing quotations. Day 2 introduces advanced uses: building further skills on real cases from the office’s work, integration with a project management system, automatic minutes from client meetings using Fireflies, and controlling the Chrome browser from within Claude. The training emphasises practical exercises based on examples set in the work of a design office.

Day 1: The basics of working with Claude AI

Module 1: Differences between Claude Cowork and other AI applications

• An introduction to the Claude ecosystem: Claude Chat, Claude Cowork, Claude Code
• Projects: a way to create dedicated workspaces in Claude
• “Skills”: saved sets of rules that let Claude carry out a specific type of work
• Claude’s agentic features: working with Microsoft Office files and email messages
• Examples of using Claude in design offices and architectural practices

Module 2: Connectors, integrations and document analysis

• Connecting Microsoft 365 to Claude
• Analysing cost estimates and summaries in Excel
• Working with project documentation and quotations in Word
• Preparing and editing concept presentations for the client in PowerPoint with the help of Claude
• Handling client correspondence in Microsoft Outlook
• Two ways of working with files

Module 3: Skills: creating your own automations in Claude

• What a “skill” is in Claude and when it activates
• The three elements of a skill: instructions (the SKILL.md file), resources (templates, quotation models) and references (model output files)
• When an instruction file alone is enough and when additional elements are needed
• Demonstration: building a skill together with Claude through conversation, using the example of a skill that prepares a quotation based on a client enquiry and a quotation template
• Workshop: each participant creates their own skill that automates a specific design office process (e.g. preparing a quotation based on an enquiry and a template, recalculating a cost estimate from floor area and a price list, preparing a message summarising a client meeting)
• Updating and refining an existing skill based on observations from daily work

Module 4: Claude projects as permanent workspaces for a commission

• What a project in Claude is and how it differs from a single conversation
• The two elements of a project: standing instructions and a knowledge base
• Writing effective project instructions with the KREDO model
• Building the project knowledge base: which documents to upload (price lists, quotation templates, materials documentation, project delivery terms, history of correspondence with the client)
• Sharing projects within a team and permission levels (viewer, editor, owner)
• Scaling a project: what happens when the knowledge base grows (RAG mode)
• Workshop: each participant creates their own project to handle a chosen commission or category of tasks (with instructions and a knowledge base)

Day 2: Advanced uses of Claude in the design office

Module 5: Skills: advanced workshops

In the practical workshop we work through three further workflows, chosen together with participants before the training. Example workflows:

• Handling a request for quotation: from receiving the request, through pricing based on floor area and scope, to a ready draft quotation in Word
• Making changes to an existing quotation based on client comments and recalculating the price
• Compiling and comparing several quotations in one table (client, floor area, scope of work, price)
• Searching for quotations in the archive by criteria (type of building, budget, scope of author’s supervision)
• Other workflows agreed in advance with the client

Claude subagents: delegating complex tasks to several agents in parallel, so that long design office processes finish within a short break.

Module 6: Fireflies: automatic meeting minutes

• Transcribing client meetings and site visits using the live recording function in the mobile and desktop app
• Configuring a Fireflies account connected to your current calendar, so that the bot joins scheduled meetings automatically
• Choosing the right Fireflies licence, with a comparison of the free and paid plans in terms of archive length, integrations and transcription limits
• Automatically sending minutes to clients at specified email addresses right after a meeting or site visit ends, without retyping notes by hand
• Connecting Claude with Fireflies, so that with a single question you can search the entire archive of conversations for client agreements and guidelines
• Workshop: recording a conversation with a client and practising running a meeting without a second person taking notes

Module 7: Claude in the browser: automating actions in Chrome

• What the Claude browser extension is and how it works
• Actions Claude can perform in the browser: searching for building standards and material specifications, monitoring supplier price changes, extracting data from industry portals
• Demonstration: assigning a task in the browser from within Claude
• Security: when to assign Claude work in the browser and when not to (sensitive data, logins, transactions)
• Practical workshops on agreed use cases

Prerequisites

• A completed AI basics course that includes the fundamentals of prompt engineering (particularly valuable if participants know the KREDO method, but not required)
• An active Claude Pro subscription for each participant
• The Claude Desktop application installed on each participant’s laptop
• An active Microsoft 365 account (Business or Enterprise) for each participant
• Login to Claude and Microsoft 365 checked in advance on the device the participant will work on
• An active free Fireflies account for each participant (https://fireflies.ai/pricing)

Organisational tip: we recommend that 3 hours before the start of each training day, every participant sends Claude any command (e.g. “test”). This opens the 5-hour usage window of a Pro account and avoids interruptions to work during the workshops. If the limit is used up during the training, it is possible to top up tokens: if necessary, the trainer will give the organiser instructions on how to do this before the training.

Organisational requirements on the client’s side

• One workstation per person: a laptop for each participant, not shared
• Stable Wi-Fi in the room, sufficient for a training group working at the same time in the Claude Desktop application and the browser
• A projector or large screen for the trainer’s presentation
• A room suitable for workshop-style work (tables, space for notes)
• A flipchart or whiteboard with markers

To be confirmed before the training

Licences and access

• Does every participant have an active Claude Pro subscription?
• Does every participant have their own Claude account, or do they share one?
• Does the organisation restrict the use of Claude connectors to Microsoft 365? (some organisations block OAuth to external tools)
• Have free Fireflies accounts been set up for all participants?
• Does the office use a project management system or CRM that is worth checking for integration with Claude (e.g. a system with an available API)?

Participants’ technical readiness

• Every participant arrives with the Claude Desktop application installed and an account already signed in: we do not set up accounts in the training room
• Test one week before the training: each participant opens Claude Desktop and verifies that they can ask a question and receive an answer
• A test one week before the training: an IT person checks, on one of the accounts, whether a connector to the Office suite tools can be set up (this can be checked together with the trainer online)
• If any participant does not have access: please let us know in advance and we will prepare an alternative way of working

Infrastructure

• Stable Wi-Fi tested under load (a training group working at the same time in the Claude Desktop application and the browser)

Trainer

Franciszek Kołpanowicz: entrepreneur and certified AI trainer who helps leaders and teams become more effective through intelligent technologies. He has been published in Rzeczpospolita, among other places. He has more than 2,000 hours of work with generative AI behind him and shares his knowledge at public events, including the “Manager in the Age of AI” training organised by Rzeczpospolita, as well as at the UKEN and PASE conferences.

His background in philosophy (Jagiellonian University) and his experience in IT quality control allow him to combine analytical thinking with asking the right questions. His own practical journey with AI showed him how this technology can become a real lever for growth.

Drawing on hands-on experience, he shows leaders and their teams how to use AI not only to work more efficiently but also to think more clearly and make faster business decisions. His AI training has, among other results, cut the time needed for routine analysis of multi-page legal documentation by 80%.

In his training sessions he pays particular attention to the participants themselves, drawing on their experience and needs as the work progresses. As a result, his sessions are not repetitive routine but an enriching and individual experience.

His mission is to make artificial intelligence a practical tool for development: business, intellectual and cultural.