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
- Introduction and Goal Setting
- Reviewing the current status of each participant and available licensing
- Participants select one specific use case to develop throughout the two-day course
- Overview of Claude's current capabilities and inherent limitations
- Exercise: Define your use case on a card, specifying the objective, input materials, and desired outcome.
- Foundations of Large Language Models
- Understanding tokens and context windows, defining the volume of text a model processes simultaneously
- Analyzing why identical queries may yield varied responses
- Mitigating hallucinations and managing model-generated details
- Comparing the Haiku, Sonnet, and Opus models based on quality, speed, and usage constraints
- Determining when Claude, Copilot, or ChatGPT is the most suitable tool
- Exercise: Execute the same task using two different models and evaluate the results based on quality and performance.
- Effective Prompting and Context Management
- Core components of robust prompts: role definition, task description, context, examples, format requirements, and constraints
- Enabling Claude to ask clarifying questions before processing
- Summarizing and comparing extensive documents, including extracting relevant passages
- Embedding review steps directly into instructions
- Exercise: Refine a suboptimal prompt from daily work through three iterations and compare the versions side by side.
- Projects as a Shared Knowledge Base
- Optimally structuring project instructions and knowledge files
- Centralizing storage for brand style, product expertise, and templates
- Segregating team-wide and private areas to maintain data confidentiality
- Monitoring, correcting, and disabling memory functions when necessary
- Exercise: Establish a project for your use case, including specific instructions and three knowledge files.
- Artifacts, File Analysis, and Visualizations
- Generating reports, tables, charts, and presentation drafts as artifacts
- Querying and comparing data from Excel, PDF, and Word documents
- Utilizing analysis tools for calculations and verifying accuracy through spot-checks
- Exporting, publishing, and sharing artifacts within the team
- Exercise: Create an analysis with a chart and commentary using an anonymized Excel dataset.
- Outcome: Participants will possess a configured project for their use case, two enhanced templates, and a primary artifact built from real data.
- Introduction and Goal Setting
- Day 2: Enhancing Capabilities with Skills, Connectors, Cowork, and Routines
- Overview of the Ecosystem
- Operational platforms: chat interface, desktop app, Claude for Chrome, Cowork, and Claude Code
- Defining skills, connectors, MCP, and routines
- Understanding agents as AI-driven workflows utilizing various tools
- Live demonstration from conceptualization to completed skill implementation
- Exercise: Map your use case to the appropriate ecosystem layer and justify the selection.
- Developing the First Custom Skill
- Structuring skills with descriptions, applicability criteria, workflows, examples, and templates
- Collaboratively writing and refining skills with Claude
- Testing the skill across three real-world scenarios
- Sharing and maintaining skills at the team level
- Exercise: Build a skill for your specific use case, such as generating style-compliant replies or review reports.
- Connectors and Service Integration
- Integrating Microsoft 365, Google Workspace, file storage, and calendar services
- Maintaining minimal and intentional permission sets
- Identifying prompt injection risks in emails and documents
- Exercise: Connect a service and execute a cross-platform task, such as preparing for an upcoming appointment.
- Claude Cowork and Automated Routines
- Delegating tasks via Cowork with access to designated folders
- Monitoring plans, tracking progress, and reviewing interim outputs
- Scheduling tasks like morning overviews or weekly reports
- Implementing approval gates before execution of sensitive actions like sending or deleting
- Exercise: Configure a routine for daily overviews and assess the initial execution collectively.
- Team Governance and 30-Day Action Plan
- Defining permissible data uploads and restrictions
- Maintaining shared skills and projects, including role assignment
- Distributing the model matrix and reference sheets as handouts
- Exercise: Draft a personal 30-day plan outlining three concrete next steps.
- Outcome: Participants will depart with a functional skill, an active connector, a configured routine, and a 30-day strategic plan.
- Overview of the Ecosystem
Requirements
- A laptop equipped with an up-to-date browser, a Claude account (Pro, Team, or Enterprise), the Claude desktop application (recommended), and a specific use case from daily operations.
- No programming knowledge is required.
Target Audience
- Professionals in administration, finance, procurement, HR, project management, and process management who are using or implementing Claude in their organization and aim to leverage capabilities beyond basic chat.
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
