Merci d'avoir envoyé votre demande ! Un membre de notre équipe vous contactera sous peu.
Merci d'avoir envoyé votre réservation ! Un membre de notre équipe vous contactera sous peu.
Durée 14 heures
Plan du cours
- Day 1: Chat, assistants and knowledge
- Langdock at a glance
- Interface, navigation and settings
- Models from Anthropic, OpenAI, Google and Mistral in one interface
- Why one central tool instead of individual licenses
- Exercise: Solve an office task with two models and justify which is better.
- Working productively in chat
- Texts, summaries and tables
- Working with files directly in the chat
- Creating prompt templates for recurring tasks
- Exercise: Create an own template for a common task and test it on two cases.
- Knowledge folders and projects
- Folder structure, sources and document types
- Answers based on own documents with source references
- Limits such as context gaps and invented details
- Exercise: Create a knowledge folder with three documents and ask ten test questions.
- Building assistants
- Instructions, knowledge, model choice and conversation starters
- Sharing assistants in the team, permissions and visibility
- Ideas for use such as quotation texts, report templates and an internal FAQ
- Exercise: Build and share an assistant for a common request in the own area.
- Outcome: Each participant has a template, a knowledge folder and a shared assistant for their own area.
- Langdock at a glance
- Day 2: Integrations, workflows and operation
- Integrations
- SharePoint, OneDrive and Teams as a data source
- Further integrations such as Confluence, Google Drive or CRM
- Checking access and permissions
- Exercise: Connect a released file storage and let an assistant access it.
- Workflows
- From chat to a repeatable workflow
- Structure from trigger, logic, action and control
- Human approval, termination criteria and retries
- Exercise: Build a workflow that categorizes incoming requests and generates a reply draft.
- Data protection and governance
- Data storage, encryption and no use for model training
- What may be uploaded and what may not
- Roles, workspaces and approval processes
- Exercise: Draft a page of usage rules for the own area.
- Tool choice and rollout
- Langdock, Claude and Copilot compared
- From pilot to team to standard
- Top use cases and a plan for 30 to 60 days
- Exercise: Prioritize three use cases for the own area and define next steps.
- Outcome: Each participant has a running workflow with approval, a connected knowledge source and a plan for the next 30 to 60 days.
- Integrations
Pré requis
- Langdock account or test environment, laptop, one or two anonymized sample documents from daily work.
- No programming skills required.
Audience
- Departments and key users in companies that use or are introducing Langdock as a central AI platform.
Nos clients témoignent (2)
les conseils et les suggestions de prompts à retenir de cette formation
Lee Mei Lin - ST Engineering IHQ Pte Ltd
Formation - InVideo AI: Creating Engaging Short-Form Videos
Traduction automatique
Le contenu, les échanges et le fait de travailler sur des sujets qui nous concernaient dans notre quotidien
