Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
- Day 1: Understanding Claude and integrating it into daily workflows
- Orientation and defining objectives
- Reviewing each participant’s current setup and available licenses
- Participants bring one specific use case to develop over the two days
- Overview of Claude’s current capabilities and their limitations
- Exercise: Document the personal use case on a card, outlining the goal, input materials, and desired outcome
- Fundamentals of language models
- Understanding tokens and context windows—how much text a model processes simultaneously
- Explaining why identical queries can yield varying responses
- Understanding model hallucinations and strategies to mitigate them
- Comparing the Haiku, Sonnet, and Opus models based on quality, speed, and usage constraints
- Determining when Claude, Copilot, or ChatGPT is the most suitable choice
- Exercise: Complete the same task using two different models and compare the outputs in terms of quality and speed
- Effective prompting and context management
- Key components of high-quality prompts: role, task, context, examples, format, and constraints
- Encouraging Claude to ask clarifying questions before initiating tasks
- Summarizing and comparing lengthy documents and requesting specific supporting excerpts
- Incorporating verification steps directly into instructions
- Exercise: Refine a weak prompt from daily work through three iterations and compare the versions side by side
- Projects as a shared knowledge base
- Logical separation of project instructions and knowledge files
- Centralizing company style guides, product knowledge, and templates
- Distinct separation of team and personal spaces, keeping sensitive data isolated
- Reviewing, correcting, or disabling memory as needed
- Exercise: Build a project for the personal use case, including instructions and three knowledge files
- Artifacts, file handling, and analysis
- Creating reports, tables, charts, and presentation drafts using artifacts
- Interrogating and comparing data from Excel, PDF, and Word files
- Using the analysis tool to compute figures and performing spot checks
- Exporting, publishing, and sharing artifacts within the team
- Exercise: Generate an analysis including a chart and brief commentary from an anonymized Excel dataset
- Outcome: Each participant will have a configured project for their use case, two refined templates, and an initial artifact created from actual data
- Orientation and defining objectives
- Day 2: Extending Claude with skills, connectors, Cowork, and routines
- Overview of the ecosystem
- Identifying where different features operate: chat, desktop app, Claude in Chrome, Cowork, and Claude Code
- Defining skills, connectors, MCP, and routines
- Simple explanation of agents: workflows combining AI and tools
- Live demonstration from concept to completed skill
- Exercise: Map the personal use case to the appropriate layer and justify the selection
- Developing the first custom skill
- Structuring skills with descriptions, applicability conditions, workflows, examples, and templates
- Iteratively writing and improving skills with Claude’s assistance
- Testing skills against three real-world scenarios
- Sharing and maintaining skills across the team
- Exercise: Each participant builds a skill for their specific use case, such as generating replies in the company style or producing review reports
- Connectors and service integration
- Linking Microsoft 365 or Google Workspace, file storage, and calendar systems
- Maintaining minimal and intentional permission scopes
- Identifying hidden instructions in emails and documents (prompt injection risks)
- Exercise: Connect a service and complete a task spanning email and calendar, such as preparing for the next meeting
- Claude Cowork and automated routines
- Delegating tasks rather than chatting, with access to authorized folders
- Monitoring plans, tracking progress, and reviewing interim results
- Scheduling recurring tasks, such as morning briefings or weekly reports
- Implementing approval gates before sending or deleting content
- Exercise: Configure a routine for a daily summary and evaluate the initial run together
- Team protocols and the next 30 days
- Defining acceptable upload policies and prohibited data types
- Maintaining shared skills and projects, including assignment of responsibilities
- Distributing the model matrix and reference sheets as handouts
- Exercise: Draft a personal 30-day plan containing three specific action items
- Outcome: Participants will exit the course with a functional skill, an active connector, a configured routine, and a strategy for the next 30 days
- Overview of the ecosystem
Requirements
- A laptop equipped with a modern browser, a Claude account (Pro, Team, or Enterprise), the Claude desktop app (recommended), and a specific use case from daily operations
- No programming knowledge is required
Audience
- Professionals in administration, finance, procurement, HR, project management, and process management who are currently using or onboarding Claude and wish to extend their capabilities beyond basic chat interactions
Testimonials (3)
Comprehensiveness about the backround; how to do a prompt.
Olaf Kannt - Helios Klinikum Krefeld
Course - Generative AI and Prompt Engineering in Healthcare
the tips and recommended prompts that we can take away from this training
Lee Mei Lin - ST Engineering IHQ Pte Ltd
Course - InVideo AI: Creating Engaging Short-Form Videos
use of proper and effective prompt
