Beyond Chatbots: Build an AI Agent for Corporate Content Compliance

AI agents make decisions and take actions on their own to achieve specific goals. Since GenAI takes natural language as input, it's natural that most of the use cases developed in this initial wave are chatbots. But an agent can be triggered into action by more than “just” a chat interface.

In this article we want to show how you you can use visual workflows to build:

• An Editorial Review agent that ensures content complies with corporate guidelines and is triggered into action by a scheduled scan of a website and by email
• An Editorial Guidelines agent that updates your corporate guidelines according to your email

Here’s how it works:

• A scheduled scan of the corporate website for new content triggers the agent into action.
• The Editorial Review agent evaluates the new content for style and tonality mishaps based on different rules and guidelines
• The agent sends the author of the new content an email summarizing any issues and suggests improvements
• You can email the second agent, requesting updates to the style and tonality guide, triggering new action by the agent.
• The agent receives the email with your update requests, reviews them, and decides which rules and guidelines need to be updated.
• After the agent has updated the relevant rules and guidelines, it emails you back, explaining what action it’s taken – which rules and guidelines it’s updated and how.

Agents reach out to tools, AI workflows, and other agents, which perform specific tasks for them. 

• Tools perform specific tasks. These tasks could be anything from retrieving and processing data, to classifying images, to predicting outcomes, and more.
• Intelligent tools add GenAI to enable capabilities like summarization, translation, or text generation.
• AI workflows combine multiple tools in sequence to accomplish more complex tasks. An example might be retrieving data, summarizing it, and sending it via an email.
• Agents go one step further and dynamically decide themselves which tools and AI workflows to use. Agents can be interacted with directly by users (in agentic applications) or can operate in the background, being called as REST services (agentic services).

For our example, we built different tools and AI workflows — the building blocks our agents will use to accomplish its tasks to check for style and tonality mishaps, and make updates to corporate style and tonality guidelines.

Below, you can see the tools used by the two agents in spaces on KNIME Hub.

This space contains the Editorial Guidelines Agent and the Editorial Review Agent, as well as the checker tools and updater tools they use to do their review and updates.

Here you can see the tools in the checker tools folder, used by the Editorial Review agent.

Here you can see the tools in the updater tools folder, used by the Editorial Guidelines agent.

When the scheduled scan of the website detects new content, our agent is triggered into action. It uses three tools, all built with KNIME workflows:

• Terminology Checker: A tool that compares the new content against a predefined list of forbidden terms
• Tonality Checker: An intelligent tool that identifies tone inconsistencies based on an internal set of style guidelines, combines the results from the Terminology checker tool, uses an LLM to produce a list of the issues, and sends this to a Send Email tool.
• Send Email: A tool that notifies you when content doesn’t comply with your corporate tone and terminology guidelines.

This tool accesses a list of terms in a spreadsheet on the KNIME Hub, checks whether any of the words in the spreadsheet are in the webpage, and produces a list of hits.

The Tonality Checker accesses the KNIME Hub, where it finds our corporate style guidelines in a spreadsheet. The workflow connects with an LLM and asks it to check the content against the guidelines in the spreadsheet. It then takes the results from the Terminology checker tool, uses an LLM to produce a list of the guideline and terminology issues. It summarizes the issues and suggests improvements, and then sends this to a Send Email tool.

It receives a list of the forbidden words caught by the Terminology Checker and a summary of the tone-related issues caught by the Tonality Checker. It formats the issues into a readable message and sends an email to the user.

The agent sends you the results of the compliance check, plus suggestions for how to improve the content, in an email.

In our example, the agent follows a predefined sequence of checks. It becomes agentic when it dynamically decides which tools to use based on the specific task in hand.

At this point, the agent transitions from an automated compliance checker to an interactive system when you email the agent to request it to modify the style guidelines.

Your email triggers an agentic service that evaluates your email, decides which guidelines need to be updated, calls the relevant tools, makes the adjustments, and then sends you an email explaining what it’s done.

The Editorial Guidelines Agent uses three tools, the Terminology Updater and the Tonality Updater, autonomously choosing which one to use based on the type of update it needs to do. It uses the Send Email tool to email you about the updates it’s made to the guidelines.

The agent reads and evaluates your email about the required update and decides which guidelines need to be updated, and calls the respective Tonality or Terminology Tool (listed in the Tools Repository) to make the updates.

You can expand the capabilities of your agent by building additional tools and agents. For example, you could build a tool that checks whether any images included in the new content comply with your brand guidelines.

You can store all the tools, AI workflows, and agents in a space on KNIME Hub. Here, they can be shared with colleagues and other agents.

The agent in this example is a quick, reliable observer of new content on your website. As an agent with memory, it is able to adapt to all new information that’s added to its memory and improve its decision-making. Our agent is always learning.
This type of agent can take over repetitive, but extremely necessary work from domain experts so they can focus on other, more valuable tasks.  The corporate content compliance checker we’ve built here can take over a task that, on a daily basis, takes up many hours of marketing time.