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: Mastering Claude for Daily Operational Work
- Onboarding and Setting Objectives
- Assessing each participant’s current status and available license tiers.
- Each participant identifies a specific use case to be addressed throughout the two days.
- Overview of Claude’s current capabilities and its inherent limitations.
- Exercise: Document your specific use case on a card, detailing the objective, input materials, and desired outcome.
- Fundamentals of Language Models
- Understanding tokens and context windows, specifically how much text a model processes simultaneously.
- Explaining why identical queries may yield varying responses.
- Addressing model hallucinations (inventing details) and strategies to mitigate them.
- Comparing the Haiku, Sonnet and Opus models based on quality, speed and usage limits.
- Determining when Claude, Copilot or ChatGPT is the superior choice for a task.
- Exercise: Execute the same task using two different models and compare the results in terms of quality and speed.
- Effective Instruction and Context Management
- Key components of effective prompting: role, task, context, examples, format and constraints.
- Enabling Claude to ask clarifying questions before commencing a task.
- Summarizing and comparing lengthy documents, and retrieving specific supporting passages.
- Integrating review steps directly into the initial instructions.
- Exercise: Refine a weak prompt from your daily work over three iterations and compare the versions side-by-side.
- Projects as Shared Memory
- Logical separation of project instructions and knowledge files.
- Centralized storage for house style, product knowledge and templates.
- Distinguishing between team and private areas, and safeguarding sensitive content.
- Reviewing, correcting and disabling memory when necessary.
- Exercise: Create a project for your specific use case, including custom instructions and three knowledge files.
- Artifacts, File Handling and Analysis
- Generating reports, tables, charts and presentation drafts as artifacts.
- Querying and comparing data within Excel, PDF and Word documents.
- Using analysis tools to calculate figures and verifying their accuracy.
- Exporting, publishing and sharing artifacts within your team.
- Exercise: Create an analysis including a chart and a brief commentary based on an anonymized Excel dataset.
- Day 1 Outcome: Each participant will have a configured project for their use case, two improved templates, and a first artifact built from real material.
- Onboarding and Setting Objectives
- Day 2: Expanding Claude’s Capabilities with Skills, Connectors, Cowork and Routines
- Overview of the Claude Ecosystem
- Platforms and interfaces: Chat, Desktop App, Claude in Chrome, Cowork and Claude Code.
- Definitions and distinctions between skills, connectors, MCP and routines.
- Simple explanation of agents as workflows integrating AI and tools.
- Live demonstration: From concept to finished skill.
- Exercise: Map your use case to the appropriate ecosystem layer and justify your selection.
- Developing Custom Skills
- Structuring skills with descriptions, applicable scenarios, workflows, examples and templates.
- Iterative writing and refinement of skills in collaboration with Claude.
- Testing skills against three real-world scenarios.
- Strategies for sharing and maintaining skills within the team.
- Exercise: Each participant will build a skill for their use case, such as drafting replies in house style or generating review reports.
- Connectors and Integrated Services
- Linking Microsoft 365 or Google Workspace, file storage and calendars.
- Principle of least privilege: Keeping permissions deliberately minimal.
- Identifying prompt injection risks in emails and documents.
- Exercise: Connect a service and perform a task spanning mailbox and calendar, such as preparing for an upcoming meeting.
- Claude Cowork and Automated Routines
- Delegating tasks with access to authorized folders, moving beyond conversational interactions.
- Monitoring plans, tracking progress and reviewing intermediate results.
- Scheduling tasks, such as morning overviews or weekly reports.
- Implementing approval checkpoints before data is sent or deleted.
- Exercise: Configure a routine for a daily overview and evaluate the initial run together.
- Team Protocols and the Next 30 Days
- Guidelines on what data can and cannot be uploaded.
- Maintaining shared skills and projects, and assigning clear responsibilities.
- Distribution of the model matrix and reference sheets as takeaways.
- Exercise: Draft a personal 30-day plan incorporating three concrete action steps.
- Day 2 Outcome: Each participant will leave the course with a working skill, a connected connector, a configured routine, and a plan for the next 30 days.
- Overview of the Claude Ecosystem
Requirements
- A laptop equipped with a current web browser, a valid Claude account (Pro, Team, or Enterprise tier), the Claude desktop app (recommended), and a specific use case from your daily workflow.
- No prior programming experience is required.
Target Audience
- Professionals in administration, finance, procurement, HR, project and process management who are using or onboarding Claude in their organization and wish to explore 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
