Part 1: The Creation of Lisa – How an AI Coworker was designed
The story of Lisa starts with a central concept: AI Coworkers require an AI Brain to operate quickly, reliably, and intelligently in real-world work environments. But what exactly is an “AI Coworker”—and why is it so promising for supporting people and organizations?
1. Multimodal Communication: Interacting Naturally and Effortlessly
A core requirement in developing an AI Brain is ensuring the AI isn’t limited to just one form of interaction (e.g., only chat or only voice). Today, people communicate through a wide variety of channels: from WhatsApp and emails to video calls and project management tools. An AI agent like Lisa needs to:
- Handle speech, emails, and chats equally well,
- Integrate with multiple platforms and formats,
- Adapt to changing contexts (smartphone, web interface, ERP system).
Why This Matters
The more naturally and seamlessly the AI can interact, the faster users will accept it as a “colleague on equal footing.” Only an AI that works smoothly within existing communication channels can truly reduce the daily workload and accelerate business processes.
2. Executing Complex Workflows in Collaboration with Humans
An AI coworker is not just about automating individual tasks; it’s about understanding and orchestrating entire workflows. This is especially important in areas like supply chain management or material planning, where multiple interdependent processes must align perfectly.
Crucial capabilities include:
- Coordinating sub-tasks (e.g., demand planning, supplier management, inventory control),
- Transparent communication—the AI should clearly explain why it recommends specific decisions,
- Role awareness—the AI acts as a team member, complementing human expertise rather than replacing it.
Why This Matters
When an AI understands the bigger picture, it can detect potential issues early on, make informed suggestions, and provide valuable decision support. In doing so, AI moves beyond being a simple automation tool to become a trusted collaborator.
3. Learning Naturally from Humans
One of the defining traits in Lisa’s development was determining how the AI should learn. Traditional machine-learning models are often trained offline and stay relatively static until the next update. In contrast, an AI coworker approach:
- Learns from every interaction—every email, chat, and piece of feedback refines its performance,
- Adapts to the context—incorporating company-specific processes, best practices, and cultural norms,
- Enables mutual communication—employees offer feedback, which the AI integrates into its model, continuously expanding its “knowledge base.”
Why This Matters
A self-learning AI that adapts to real-world work processes can embed itself more smoothly into teams and continuously improve. This creates an evolving relationship between humans and AI, ensuring the agent remains relevant and up-to-date over time.
4. Access to Real-Time Knowledge & Decision-Making Relevance
For Lisa to excel, it needs a constant feed of current data to understand what’s happening across various workflows. Whether it’s inventory levels, supplier updates, or customer feedback, the AI must be able to process information quickly, prioritize what matters, and factor it into its decisions.
Key features include:
- Relevance-focused decisions—the AI discerns what requires immediate attention,
- Condensed information—prioritizing essential data for swift processing within its context window,
- Automated logging—each decision and process update is recorded, enriching the system’s knowledge over time.
Why This Matters
Any modern AI is only as powerful as the data it ingests. By filtering and contextualizing information effectively, the AI provides highly targeted, real-time recommendations that align with the specific workflow at hand.
Inspired by Neurophysiology: Learning from the Human Brain
Interestingly, the creation of an AI Brain also draws inspiration from the human brain. While our understanding of neurophysiology continues to grow, some principles translate well into AI:
- Parallel processing—like the brain, AI should handle multiple data streams at once,
- Focus vs. noise filtering—humans tune out irrelevant details; AI similarly needs efficient filtering to prioritize critical tasks,
- Cognitive context—people apply contextual knowledge to everything they see, hear, or read; likewise, AI must manage “context windows” for accurate, situation-aware responses.
Why This Matters
AI systems that align with neurophysiological insights can prioritize more effectively, act more intuitively, and adapt to rapidly changing environments.
Why Lisa Became an AI Material Planner
Once the fundamental architecture for AI coworkers was in place, our passion for supply chain management took center stage. We had already envisioned countless applications for AI in supply chain operations, and the capabilities we discussed—multimodal communication, intelligent workflow management, continuous learning, and real-time process awareness—proved an ideal match for the complexities of supply chain management. Why?
- Many interaction points—suppliers, logistics providers, and internal departments must all stay in sync,
- Strong automation potential—repetitive tasks (orders, follow-ups, planning) can be efficiently handled by an AI coworker,
- High impact—even small gains in demand forecasting or logistics optimization can yield sizable savings in cost and time.
Thus, Lisa was born as an AI material planner—a role that involves monitoring inventory levels, keeping an eye on supplier performance, and proactively managing order proposals. Over time, Lisa continuously learns how to optimize background processes for even greater efficiency.
Conclusion: An AI Agent with Human-Like Traits for Better Efficiency & Innovation
The personification of AI—assigning it a name and role—is far more than a marketing tactic. It’s the key to developing an agent that thinks and operates holistically.
By constructing an AI Brain inspired by neurophysiological processes and grounded in multimodal communication, advanced workflow management, continual learning, and context-sensitive decision-making, an AI coworker truly evolves into a “digital colleague.”
Only through this broader lens can we appreciate how and why an AI like Lisa can excel in supply chain management—and eventually, in numerous other fields. This technical foundation enables authentic interactions, which in turn drive more effective collaboration and generate long-term value for organizations.
