Obrigado por enviar sua consulta! Um dos membros da nossa equipe entrará em contato com você em breve.
Obrigado por enviar sua reserva! Um dos membros da nossa equipe entrará em contato com você em breve.
Duração 14 horas
Programa do Curso
- Day 1: Understanding Claude and integrating it into daily operations
- Onboarding and defining objectives
- Assessing each participant's current status and available licenses
- Participants bring a specific use case to focus on throughout the two days
- Overview of Claude's current capabilities and limitations
- Exercise: Document your personal use case on a card, outlining the goal, input materials, and desired outcome.
- Foundations of language models
- Understanding tokens and context windows, i.e., the amount of text a model processes simultaneously
- Explaining why identical questions may yield different answers
- Mitigating hallucinations: why models invent details and how to constrain them
- Comparison of Haiku, Sonnet, and Opus models based on quality, speed, and usage limits
- Determining when Claude, Copilot, or ChatGPT is the optimal choice
- Execute: Perform the same task with two different models and compare results in terms of quality and speed.
- Crafting effective instructions and context
- Core components of a strong prompt: role, task, context, examples, format, and constraints
- Enabling Claude to ask clarifying questions before execution
- Summarizing and comparing long documents, and requesting specific supporting passages
- Incorporating review steps directly into the instruction set
- Exercise: Refine a weak prompt from your daily work through three iterations, comparing versions side by side.
- Projects as shared organizational memory
- Optimally separating project instructions from knowledge files
- Centralizing house styles, product knowledge, and templates
- Segregating team versus private areas to keep sensitive content isolated
- Verifying, correcting, and disabling memory where necessary
- Exercise: Create a project for your use case, including a main instruction and three knowledge files.
- Artifacts, file handling, and analysis
- Generating reports, tables, charts, and presentation drafts as artifacts
- Querying and comparing Excel, PDF, and Word documents
- Using the analysis tool to calculate figures and conducting spot checks
- Exporting, publishing, and sharing artifacts within the team
- Exercise: Build an analysis featuring a chart and brief commentary from an anonymized Excel list.
- Outcome: Each participant will have a configured project for their use case, two refined templates, and an initial artifact created from real data.
- Onboarding and defining objectives
- Day 2: Expanding Claude's capabilities with skills, connectors, Cowork, and routines
- Overview of the ecosystem
- Deployment points: chat interface, desktop app, Claude in Chrome, Cowork, and Claude Code
- Defining skills, connectors, MCP, and routines
- Simplified explanation of agents: workflows combining AI and tools
- Live demonstration: From concept to a finished skill
- Exercise: Map your use case to the appropriate layer and justify your selection.
- Developing the first custom skill
- Structuring a skill: description, applicability, 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: Each participant develops a skill for their use case, such as composing replies in the house style or generating a review report.
- Connectors and integrated services
- Linking Microsoft 365 or Google Workspace, file storage, and calendars
- Maintaining minimal necessary permissions
- Identifying hidden instructions in emails and documents (prompt injection risks)
- Exercise: Configure a connector to resolve a task spanning mailbox and calendar, such as preparing the next meeting.
- Claude Cowork and automated routines
- Delegating tasks rather than just chatting, with access to designated folders
- Reviewing plans, tracking progress, and assessing interim results
- Scheduling tasks, such as daily overviews or weekly reports
- Establishing approval checkpoints before sending or deleting content
- Exercise: Set up a routine for a daily overview and evaluate the initial run collectively.
- Team guidelines and the 30-day roadmap
- Defining upload permissions: what is allowed and what is not
- Maintaining shared skills and projects, and assigning ownership
- Distributing the model matrix and reference sheet as a handout
- Exercise: Draft a personal 30-day plan including three concrete steps.
- Outcome: Participants will depart with a functional skill, a connected connector, a configured routine, and a 30-day action plan.
- Overview of the ecosystem
Requisitos
- A laptop with an up-to-date browser, a Claude account (Pro, Team, or Enterprise), the Claude desktop app (recommended), and a real-world use case from daily operations.
- No programming experience is required.
Target Audience
- Employees in administration, finance, purchasing, HR, project, and process management who are currently using or introducing Claude in their organization and aim to leverage features beyond basic chat interactions.
Treinamento Corporativo Personalizado
Soluções de treinamento projetadas exclusivamente para empresas.
- Conteúdo Personalizado: Adaptamos o programa e os exercícios práticos aos objetivos e necessidades reais do seu projeto.
- Horário Flexível: Datas e horários adaptados à agenda da sua equipe.
- Formato: Online (ao vivo), In-Company (em suas instalações) ou Híbrido.
Preço por grupo privado, treinamento online ao vivo, a partir de 2600 € + VAT*
Entre em contato conosco para obter um orçamento preciso e conhecer nossas promoções mais recentes
Testemunhos de Clientes (3)
Abrangência sobre o contexto; como criar um prompt.
Olaf Kannt - Helios Klinikum Krefeld
Curso - Generative AI and Prompt Engineering in Healthcare
Máquina Traduzida
as dicas e os prompts recomendados que podemos levar desta formação
Lee Mei Lin - ST Engineering IHQ Pte Ltd
Curso - InVideo AI: Creating Engaging Short-Form Videos
Máquina Traduzida
utilização de prompts adequados e eficazes
Marses Pacaldo
Curso - Generative AI and Prompt Engineering for Corporate Professionals
Máquina Traduzida
