Following my previous article “Agentic AI in Action”, my team recently released a new feature as part of our multi-model, multi-modal Generative AI framework for business.

We call this feature “Builder”, which allows for self-contained applications to be generated from a single prompt or as part of an Agentic AI workflow.

These self-contained applications can leverage previously defined framing or ingested context from structured or unstructured data. They are also built following pre-defined standards, using an approved technology stack, ensuring they are supportable, secure, private, and compliant (avoiding technical debt).

The power of this feature lies in producing a “rich” user experience, featuring interactive elements that can further enhance how teams automate business processes and interact with data.

For example, the screenshot below is an interactive dashboard, produced from business financial data. Elements can be selected to unlock further insights, providing different views, etc.

Agentic AI - Builder

Previously, a dashboard of this type would have been created in Power BI or Tableau, likely requiring an individual (or team) with the relevant skills to identify, integrate, build, test, and verify before being made available to the target stakeholder group.

By comparison, this dashboard could be generated in real-time, by anyone with the relevant access to the information, requiring no specialist skill set. The prompt can even be iterated upon, rapidly adding or modifying the content, appearance, or features.

Finally, the self-contained application generated by Builder can be securely and privately shared.

Dashboards are just one very simple example as to how Builder could be used to create value. In testing, we have generated full stack applications, which could be deployed to support specific business use cases.

At the time of writing, we are limiting the ability to generate some of these more advanced use cases, providing the required time to establish the appropriate governance (avoiding application sprawl).

However, the potential is extremely exciting, further enhancing the value proposition of Generative AI and Agentic AI capabilities within a business.

enterprise architecture ea enterprise_architecture artificial_intelligence ai machine_learning ml generative_ai agentic_ai large_language_model llm natural_language_processing nlp transformer data prompt_engineering model_context_protocol mcp openai chatgpt gpt o1 microsoft google gemini gemini_pro imagen imagen_2 imagen_3 ai_studio project_mariner bard progressive_web_app pwa lifeinwork