A live workshop demonstrated how marketers can move beyond single-task chatbot prompts and build automated workflows that handle multistep marketing operations with limited human direction. The second installment of the AI Edge series, hosted by Brandon Z. Hoff, chief AI officer of Responsible Use of Digital Intelligence (RUDI AI), showed participants how to use Anthropic's Claude Cowork environment to research a company, develop brand guidelines, and generate campaign materials in sequence.
What automated workflows actually do
Hoff said decision-makers are placing greater emphasis on agentic workflows, which allow AI systems to complete sequences of tasks with less human intervention. A workflow gives the AI a defined process to follow. It can include instructions, tools, files, quality checks, and specific outputs.
The approach differs from a traditional chatbot interaction. Unlike a chatbot that responds to an individual request, an automated workflow can work through several steps to reach a defined outcome. For marketers, a workflow could include researching a target audience, reviewing a company's website, identifying competitors, and creating campaign materials.
Clean data and the CRAFT framework
Hoff emphasized that the quality of the information provided determines the effectiveness of prompts and workflows. Common file formats can contain formatting information that creates unnecessary noise for an AI model. He recommended using cleaner, machine-readable formats such as Markdown, JSON, CSV, and HTML when building workflows. For those looking to develop these skills, AI Automation Courses cover the fundamentals of structuring data for AI systems.
He introduced participants to a five-part instruction model called the CRAFT Framework, which stands for context, role, actions, format, and testing. Users begin each prompt by providing context and background information about an organization, project, or objective. They then assign a role that tells the AI who it should think and act as - such as a marketing analyst or executive persona. After setting the persona, users outline actions by listing precise, numbered steps. The following step specifies the exact deliverable format. The final step is testing: users establish quality controls and boundaries before the workflow begins.
Giving AI access to tools
Hoff explained that setting up successful workflows requires sharing direct access to workplace tools and local computer systems. Connections expand what the AI can do and allow a workflow to function more like a digital worker operating within defined boundaries. Based on what is shared, capabilities can expand to include sorting information from emails, organizing files, or conducting deep research. The system can connect with tools such as Gmail, Slack, Chrome, and Google Drive. With browser access, it can also visit websites and collect information from public sources.
A live simulation from research to output
Hoff put the framework into practice during the workshop. Participants received a Marketing Operations Starter Kit with brand guidelines, campaign strategy, and content planning objectives. Hoff submitted a master onboarding prompt based on the CRAFT Framework, instructing Claude to assume the role of a marketing operations executor.
Claude then used the Claude in Chrome extension to inspect a target website. The system identified information about the organization and its audiences, analyzed the site's visual system, extracted CSS information, and identified color codes. The workflow used that information to establish elements of a brand identity system, then generated marketing copy, messaging pillars, and prompts for image-generation tools. For marketers working directly with Anthropic's tools, Claude AI Training resources can help bridge the gap between basic prompting and workflow automation.
Why this matters for marketers
Once a workflow is built, users can change the inputs without rebuilding the entire system. Hoff encouraged participants to centralize these workflows in shared environments such as Google Drive, giving teams access to the same AI processes and reducing redundant work. Instead of using AI to complete isolated tasks, marketing teams can build systems that manage entire processes from research to execution - and replicate those systems across different campaigns or clients.
Your membership also unlocks:
