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: Grasping Claude and Integrating It into Daily Operations
- Introduction and Objective Setting
- Assessing each participant’s current status and available licenses.
- Participants bring one specific use case to develop over the two-day period.
- Overview of Claude’s current capabilities and limitations.
- Exercise: Draft a use case card detailing the goal, input materials, and desired outcome.
- Foundations of Language Models
- Understanding tokens and context windows, or the amount of text a model processes simultaneously.
- Why identical queries may yield varying responses.
- Mitigating model hallucinations (invented details).
- Comparing Haiku, Sonnet, and Opus models based on quality, speed, and usage limits.
- Determining when Claude, Copilot, or ChatGPT is the preferred tool.
- Execute a task using two different models and evaluate the results for quality and speed.
- Effective Prompting and Context Management
- Key components of a robust prompt: role, task, context, examples, format, and constraints.
- Encouraging Claude to ask clarifying questions before initiating a task.
- Summarizing and comparing lengthy documents while retrieving specific supporting passages.
- Embedding review steps directly into instructions.
- Exercise: Refine a weak prompt from daily work over three iterations and compare versions side-by-side.
- Projects as Shared Memory
- Optimizing the division between project instructions and knowledge files.
- Centralizing storage for brand guidelines, product knowledge, and templates.
- Segmenting team versus private areas to isolate sensitive content.
- Verifying, correcting, and disabling memory if necessary.
- Exercise: Create a project for your use case, including one instruction set and three knowledge files.
- Artifacts, Files, and Data Analysis
- Generating reports, tables, charts, and presentation drafts as artifacts.
- Querying and comparing Excel, PDF, and Word documents.
- Using analysis tools to compute figures and performing spot checks.
- Exporting, publishing, and sharing artifacts with teams.
- Exercise: Generate an analysis with a chart and brief commentary from an anonymized Excel dataset.
- Outcome: Participants will have a configured project for their use case, two refined templates, and an initial artifact created from actual materials.
- Introduction and Objective Setting
- Day 2: Expanding Claude with Skills, Connectors, Cowork, and Routines
- Overview of the Ecosystem
- Platforms for execution: chat, desktop app, Claude in Chrome, Cowork, and Claude Code.
- Definitions of skills, connectors, MCP, and routines.
- Simplified explanation of agents: AI-driven workflows with tool integration.
- Live demonstration from concept to completed skill.
- Exercise: Map your use case to the appropriate layer and justify the selection.
- Developing the First Custom Skill
- Structuring a skill: description, application criteria, workflow, examples, and templates.
- Co-authoring and refining skills with Claude.
- Testing against three real-world scenarios.
- Sharing and maintaining skills across the team.
- Exercise: Build a skill for your use case, such as generating replies in a specific house style or creating review reports.
- Connectors and Integrated Services
- Linking Microsoft 365 or Google Workspace, file storage, and calendars.
- Maintaining minimal and intentional permission scopes.
- Identifying hidden instructions in emails or documents (prompt injection).
- Exercise: Connect a service and perform a task spanning mail and calendar, such as preparing for an upcoming meeting.
- Claude Cowork and Automation Routines
- Delegating tasks with access to designated folders instead of conversational interaction.
- Monitoring plans, tracking progress, and reviewing intermediate outputs.
- Scheduling tasks, such as daily morning summaries or weekly reports.
- Implementing approval checkpoints before sending or deleting data.
- Exercise: Configure a daily summary routine and jointly evaluate its initial execution.
- Team Protocols and the Next 30 Days
- Defining acceptable data uploads and restrictions.
- Maintaining shared skills and projects while assigning responsibilities.
- Distributing the model matrix and reference sheet as handouts.
- Exercise: Draft a personal 30-day plan with three specific action steps.
- Outcome: Participants will conclude the course with a functional skill, an active connector, a configured routine, and a 30-day action plan.
- Overview of the Ecosystem
Requirements
- A laptop with an up-to-date web browser, an active Claude account (Pro, Team, or Enterprise tier), the Claude desktop application (recommended), and a practical use case from daily operations.
- No programming expertise is required.
Target Audience
- Professionals in administration, finance, procurement, HR, and project or process management who are utilizing or introducing Claude within their organization and seek to extend their usage 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
