Agentic Work with Claude Desktop & Cowork

Run agentic knowledge work through Claude Desktop and Cowork without writing code. Claude Desktop and its extension ecosystem cover quick-launch entry points, persistent memory, model selection per...

Read More
By Request
8781  Reviews star_rate star_rate star_rate star_rate star_half
$1,665USD
Duration 2 days
Course Code AI-CLD-2001
Available Formats Classroom

Overview

Course Description

Run agentic knowledge work through Claude Desktop and Cowork without writing code. Claude Desktop and its extension ecosystem cover quick-launch entry points, persistent memory, model selection per task, and the security model around desktop extensions and local MCP servers. Cowork as the agentic mode covers how it plans, how task progress is surfaced, where human intervention fits, and how to produce polished deliverables including reports, spreadsheets, and presentations through connectors and browser/computer use. Scaling Cowork covers persistent projects, scheduled tasks for repeatable outputs, and plugins that bundle skills and sub-agents into reusable instruction sets. Staying in control covers setting and widening trust boundaries deliberately, intervening during long-running tasks, reviewing before acting on Cowork output, and recognizing when Cowork is the wrong tool. Hands-on labs produce a configured Claude Desktop workspace with extensions, a Cowork project, scheduled workflows, and a trust-boundary checklist tied to the participant’s own work. The course is designed for knowledge workers comfortable with Claude Chat or AI-CLD-1001 who want to delegate work without writing code.

Skills Gained

By the end of this course, participants will be able to:

  • Describe how Claude Desktop and Cowork differ from Claude Chat
  • Configure Claude Desktop with extensions and local MCP servers
  • Delegate multi-step tasks to Cowork with appropriate supervision
  • Design repeatable workflows using projects, scheduled tasks, and plugins
  • Evaluate when Cowork is and is not the right tool for a given task

Who Can Benefit

This course is designed for:

  • Anyone interested in using Claude Desktop and Cowork for agentic knowledge work

Prerequisites

Participants should enter this course with:

  • Familiarity using Claude Chat, or AI-CLD-1001

Organizational Objectives

This course assists organizations to:

  • Reduce turnaround on multi-step deliverables by delegating execution to Cowork
  • Build organization-wide fluency in agentic AI work in two days
  • Lower governance risk through trained intervention and trust-boundary discipline
  • Standardize repeatable workflows via plugins, projects, and scheduled tasks

Software

All attendees must have a modern web browser and an Internet connection.

Read Less

Course Details

Course Details

Module 1 - Your Desktop AI Workspace

By the end of this module, you will be able to configure Claude Desktop for daily knowledge work — reaching it from any application, retaining context across conversations, picking the right model per task, and extending its capabilities through desktop extensions and local MCP servers within an admin-aware security model.

  • How Claude Desktop differs from claude.ai and quick-launch entry points
  • Persistent memory across conversations and choosing the right model
  • Desktop extensions for connecting to local resources
  • Local MCP servers and manual configuration
  • Extension security, allowlists, and admin controls
  • Hands-on Lab: Configure Claude Desktop with at least one local MCP server and one desktop extension, then verify the security and allowlist behavior.

Module 2 - Delegating Work to Cowork

By the end of this module, you will be able to choose between Chat, Cowork, and Claude Code for a given task, hand off multi-step work to Cowork, supervise its progress, and produce polished deliverables through connectors and browser or computer use.

  • Chat vs. Cowork vs. Claude Code: choosing the right mode
  • How Cowork plans and executes multi-step tasks
  • Task progress visibility and human intervention
  • Working with local files and producing reports, spreadsheets, and presentations
  • Connectors for Google Drive, Gmail, Slack, and other services
  • Browser use and computer use
  • Hands-on Lab: Delegate a realistic multi-step deliverable to Cowork end-to-end, intervene at one planned checkpoint, and review the produced artifact before acting on it.

Module 3 - Scaling Your Cowork Workflows

By the end of this module, you will be able to organize ongoing Cowork work into persistent projects, automate repeatable outputs through scheduled tasks, and assemble plugins and skills into reusable instruction sets tailored to your role.

  • Cowork Projects as persistent workspaces (and how they differ from Claude Projects)
  • Scheduled tasks for repeatable outputs
  • Local vs. cloud scheduling and their tradeoffs
  • Plugins: bundled skills, connectors, and sub-agents
  • Skills as reusable instruction sets
  • Customizing Cowork for role and workflow
  • Hands-on Lab: Build a Cowork project containing a scheduled task and at least one custom skill, then verify the project produces a repeatable deliverable.

Module 4 - Staying in Control

By the end of this module, you will be able to set trust boundaries for Cowork, intervene during running tasks, review output before acting, choose the safest execution path, and recognize the situations where Cowork is the wrong tool or where compliance limits its use.

  • Setting trust boundaries and growing autonomy as capabilities prove out
  • When and how to intervene during a running task
  • Reviewing before acting on Cowork output
  • Choosing the safest execution path
  • When Cowork should not be used
  • Audit log and compliance limitations
  • Hands-on Lab: Define a trust-boundary policy for one Cowork workflow and exercise the intervention path on a deliberately ambiguous task.

Schedule

Upcoming Course Dates

There are currently no scheduled dates for this course. If you are interested in this course, contact us with the form below.

Contact Information

FAQ

Does the course schedule include a Lunchbreak?

Classes typically include a 1-hour lunch break around midday. However, the exact break times and duration can vary depending on the specific class. Your instructor will provide detailed information at the start of the course.

What languages are used to deliver training?

Most courses are conducted in English, unless otherwise specified. Some courses will have the word "FRENCH" marked in red beside the scheduled date(s) indicating the language of instruction.

What does GTR stand for?

GTR stands for Guaranteed to Run; if you see a course with this status, it means this event is confirmed to run. View our GTR page to see our full list of Guaranteed to Run courses.

Does Ascendient Learning deliver group training?

Yes, we provide training for groups, individuals and private on sites. View our group training page for more information.

What does vendor-authorized training mean?

As a vendor-authorized training partner, we offer a curriculum that our partners have vetted. We use the same course materials and facilitate the same labs as our vendor-delivered training. These courses are considered the gold standard and, as such, are priced accordingly.

Is the training too basic, or will you go deep into technology?

It depends on your requirements, your role in your company, and your depth of knowledge. The good news about many of our learning paths, you can start from the fundamentals to highly specialized training.

How up-to-date are your courses and support materials?

We continuously work with our vendors to evaluate and refresh course material to reflect the latest training courses and best practices.

Are your instructors seasoned trainers who have deep knowledge of the training topic?

Ascendient Learning instructors have an average of 27 years of practical IT experience and have also served as consultants for an average of 15 years. To stay current, instructors spend at least 25 percent of their time learning new, emerging technologies and courses.

Do you provide hands-on training and exercises in an actual lab environment?

Lab access is dependent on the vendor and the type of training you sign up for. However, many of our top vendors will provide lab access to students to test and practice. The course description will specify lab access.

Will you customize the training for our company’s specific needs and goals?

We will work with you to identify training needs and areas of growth.  We offer a variety of training methods, such as private group training, on-site of your choice, and virtually. We provide courses and certifications that are aligned with your business goals.

How do I get started with certification?

Getting started on a certification pathway depends on your goals and the vendor you choose to get certified in. Many vendors offer entry-level IT certification to advanced IT certification that can boost your career. To get access to certification vouchers and discounts, please contact info@ascendientlearning.com.

Will I get access to content after I complete a course?

You will get access to the PDF of course books and guides, but access to the recording and slides will depend on the vendor and type of training you receive.

How do I request a W9 for Ascendient Learning?

View our filing status and how to request a W9.

Reviews

You get detailed labs to guide you through the technical material giving you a hands on method of learning otherwise difficult material.

I think the platform is very good and look forward to taking my next course in early October.

Very good couse and again we would like to see more videos on removing FRUs

They were very good. They made sure everyone was able to get into the training and got all of the material needed for class.

The format of the class was concise. I learned new skills to use at my workplace.