Question 1

How are AI agents different from RPA (robotic process automation)?

Accepted Answer

_Agents add reasoning where RPA's rule engine stops._

RPA is a rule engine. It automates structured, low-skilled tasks where every decision is essentially zero or one, which is why UiPath and Automation Anywhere built real businesses but hit a ceiling: a script either breaks or runs, and it cannot handle uncertainty or unstructured data. Agents add a language model on top, so they can read an email's style, cope with ambiguity, and self-correct. Cherry's portfolio company Octomind does this for front-end testing with a self-healing loop that notices when a test goes wrong and tries another path, something a rule engine cannot do. The catch: you still have to give an agent clear boundaries, or it goes rogue.

— [The Edge: “AI Agents: The Future of Work?”](https://www.lutzfinger.com/transcript/2024-12-12-ai-agents-the-future-of-work/) · _Podcast_

Question 2

How can AI support frontline workers who aren't sitting at computers all day?

Accepted Answer

_Think voice-first interfaces and knowledge retrieval, not just desktop tools._

Frontline workers move around and might not have time to sit at a laptop, but they could have a quick second to speak or type a question. You could support them with an AI interface that answers questions in their language, translates into technical knowledge, and searches knowledge databases. The key is making sure answers are right. Don't just put ChatGPT on your FAQs. You need human in the loop at the beginning, testing a lot to ensure frontline workers are happy with the output before rolling it out widely.

— [You asked, we answered](https://www.lutzfinger.com/transcript/2023-07-28-you-asked-we-answered/) · _The Edge_

Question 3

How do venture firms use AI in their own operations?

Accepted Answer

_AI in sourcing, diligence, portfolio construction, and founder support._

> AI — it's who controls the data and who builds products that businesses and people actually use.

— [Stargate: The $500 Billion Message To China — The Future Of AI Regulation](https://www.forbes.com/sites/lutzfinger/2025/01/22/stargate-the-500b-message-to-china---the-future-of-ai-regulation/) · _Forbes_

Question 4

How does Catalog ensure certain workflows always follow the same steps when using LLMs?

Accepted Answer

_A rules engine ensures critical workflows always execute consistently._

We built a workflow engine underneath our LLMs. The LLM generates a workflow on the fly every time, but users can design deterministic journeys inside our system using workflows (like Zapier but internal). If a request matches a workflow definition, it triggers that workflow every time instead of a dynamically generated journey. It's no code, so users can do it themselves. First, the LLM does a workflow lookup to see if there's something you always want to do, then for the rest it goes into free flow logic.

— [Large Language Models: one interface to rule them all?](https://www.lutzfinger.com/transcript/2023-08-15-large-language-models-one-interface-to-rule-them-all/) · _The Edge_

Question 5

How does Catalog use large language models to simplify enterprise software access?

Accepted Answer

_One interface to access all your enterprise tools at once._

Catalog uses LLMs to create a unified interface for all enterprise software. Instead of navigating multiple systems, employees enter a single prompt. The LLM understands the query, identifies which data repository holds the answer (like Workday for payslips), converts the request into an API call, performs deterministic retrieval, and returns the result. We don't use LLMs for data retrieval itself, only for reasoning and synthesis. This compresses workflows from multiple surfaces and ten to fifteen clicks down to one query and two or three clicks.

— [Large Language Models: one interface to rule them all?](https://www.lutzfinger.com/transcript/2023-08-15-large-language-models-one-interface-to-rule-them-all/) · _The Edge_

Question 6

What does 'AI as an operating model' mean?

Accepted Answer

_Why the winners redesign work around AI rather than just adopting tools._

> AI — it's who controls the data and who builds products that businesses and people actually use.

— [Stargate: The $500 Billion Message To China — The Future Of AI Regulation](https://www.forbes.com/sites/lutzfinger/2025/01/22/stargate-the-500b-message-to-china---the-future-of-ai-regulation/) · _Forbes_

Question 7

What is an AI agent, really?

Accepted Answer

_Not a sci-fi character, a workflow that chains steps._

An agent is not a sci-fi character and it is not one giant model. It is a piece of code that takes a defined task, breaks it into steps, and lets you act on software through language. The core idea is chaining: instead of asking a model to "improve revenue," you break the goal into step one, step two, step three, exactly the way a manager hands work to a junior employee. Tools like LangChain popularized this. So an agent is less a breakthrough model than a workflow that combines models, tools, and sometimes plain deterministic code, each doing one step.

— [The Edge: “AI Agents: The Future of Work?”](https://www.lutzfinger.com/transcript/2024-12-12-ai-agents-the-future-of-work/) · _Podcast_

Question 8

What makes autonomous AI agents different from traditional automation tools like RPA?

Accepted Answer

_How AI agents differ from traditional automation like RPA_

Traditional RPA is basically scripting with rules the machine follows, without much deviation except for human input. It's a structural, human-made approach. Autonomous agents are different because they use large language models as an interface that understands human language instead of requiring rigid API calls or workflows. This means I don't need to design specific engineering interfaces. The language model can interact with tools like calculators, internet searches, or order engines using natural language, breaking down tasks iteratively rather than following predetermined scripts.

— [Connecting LLMs to the world: The possibilities of the feedback loop](https://www.lutzfinger.com/transcript/2023-05-02-connecting-llms-to-the-world-the-possibilities-of-the-feedback-loop/) · _The Edge_

Question 9

What patterns make a workflow 'agentic' rather than just a wrapper around an LLM?

Accepted Answer

_Reflection, self-correction, knowledge expansion, coordination._

A few recurring patterns. Reflection: the system plans, asks "is this approach good, does this make sense, can you double-check," and only then executes, the way a reasoning model breaks a request into several approaches, picks one, and verifies the answer. Self-correction: it looks at the result, notices it went wrong, and tries a different route. Knowledge expansion: when the answer is not in its memory, it searches the web for current information. Coordination: it splits a job into sub-tasks and routes each to the right tool, for example handing a math question to a calculator instead of guessing. Wrapping a chat box around an LLM is none of these.

— [The Edge: “AI Agents: The Future of Work?”](https://www.lutzfinger.com/transcript/2024-12-12-ai-agents-the-future-of-work/) · _Podcast_

Question 10

What practical business use cases exist for language model chaining beyond autonomous agents?

Accepted Answer

_Real business applications from databases to booking to summarization_

There are many business cases beyond the autonomous agent hype. Question answering over a database is one: use a language interface to access the database, figure out the information, distill it, and report back. Chatbots interacting with booking systems need to understand how to access the system and remember personal preferences. Document summarization is another: if I take all seven Harry Potter books, I can't paste them into OpenAI because it's a finite machine. Instead, summarize page by page, store that in memory, then do iterative summarization to get the final result. These applications are very practical.

— [Connecting LLMs to the world: The possibilities of the feedback loop](https://www.lutzfinger.com/transcript/2023-05-02-connecting-llms-to-the-world-the-possibilities-of-the-feedback-loop/) · _The Edge_

Question 11

What problem did transformers solve for Ultimate AI's multi-language support?

Accepted Answer

_One transformer model replaced 100 language-specific models per customer_

Before transformers, we had different models for different languages. Supporting 100 languages meant running 100 different models per customer, which was painful for model operations. When we switched to transformers like BART about three and a half years ago, we could use one polyglot model for all languages. You could train the bot in English and ask questions in Finnish, and it worked reasonably well. It also helped our clustering pipeline show customers all their questions across languages semantically grouped together. You could see Finnish, Spanish, German, and English examples all meaning the same thing without worrying about the language.

— [How Ultimate evolved from hundreds of supervised models to UltimateGPT](https://www.lutzfinger.com/transcript/2023-05-12-how-ultimate-evolved-from-hundreds-of-supervised-models-to-ultimategpt/) · _The Edge_

Question 12

What was Ultimate AI's key insight that made customer onboarding faster than competitors?

Accepted Answer

_Automated clustering replaced manual training data creation for faster setup_

We couldn't afford AI trainers manually creating training data, so we built a clustering pipeline that analyzed historical customer conversations already sitting in CRMs like Salesforce. This let us automatically find the 100 or 200 most common questions and show customers all 30,000 actual ways users asked questions like where's my order. Competitors were using FAQ pages and having people manually write 50 to 100 variations, which didn't reflect real customer language. Our approach gave faster time to value because we used actual conversation data instead of imagined variations, and customers could see their real top questions before even talking to us.

— [How Ultimate evolved from hundreds of supervised models to UltimateGPT](https://www.lutzfinger.com/transcript/2023-05-12-how-ultimate-evolved-from-hundreds-of-supervised-models-to-ultimategpt/) · _The Edge_

Question 13

Why are AI workflows the real moat?

Accepted Answer

_How redesigning work around AI beats model upgrades._

> SaaS can build the new AI-driven workflows on top of its user data and customer surfaces. But workflows are brittle. One new prompt, one model update, and the whole chain quietly breaks. I watch this every time I get students [coding agents in my Cornell workshops](https://ecornell.cornell.edu/courses/artificial-intelligence/building-enterprise-ready-ai-agents-from-prototypes-to-production/).

— [The Missing Moat In AI: Your Eval Data](https://www.forbes.com/sites/lutzfinger/2026/05/26/the-missing-moat-in-ai-your-eval-data/) · _Forbes_

Question 14

Why are coding applications seeing the biggest success with AI agents right now?

Accepted Answer

_Coding succeeds because compilers provide clear feedback loops_

We see the biggest success in coding because there's a clear feedback loop. When I ask an AI to write code, it can check if the code compiles. If it doesn't work, ChatGPT critiques that and the next step is to rewrite the code including the critique. This iterative loop continues till it actually works. The combination of knowing what was put in previously through memory, plus the ability to talk to a compiler, plus the iteration workflow creates a loop to generate good code. It's more difficult when the task isn't very clear or doesn't have such obvious success criteria.

— [Connecting LLMs to the world: The possibilities of the feedback loop](https://www.lutzfinger.com/transcript/2023-05-02-connecting-llms-to-the-world-the-possibilities-of-the-feedback-loop/) · _The Edge_

Question 15

Why are radically lean teams the future?

Accepted Answer

_How AI compresses the team size needed to ship._

> But what hinders many of the large corporates to adapt them? >>Yeah, well, I think there's a lot of components there but in the end, it comes down to the size, and the politics, and the setup they built. Large companies are usually built to mitigate risk and focus on their core business. If there's a new technology that comes in that is not obviously threatening the core business, or opening a huge opportunity for the core business,…

— [Unit 5 Full Transcript](https://www.lutzfinger.com/ecornell/) · _eCornell course_

Question 16

Why did Ultimate AI initially focus on helping human agents instead of automating customer conversations directly?

Accepted Answer

_Agent assistance was a learning ground before full automation_

We turned the problem around. Instead of having consumers talk directly to bots, we gave recommendation tools to human agents. Agents had more tolerance for failures because they could ignore incorrect suggestions and still do their jobs, but when recommendations were correct they got value and could train the system. This was less stressful for building products. We could iterate and fail without ruining the customer experience. The technology wasn't good enough yet for full automation, so this approach let us learn gradually. Once models improved, we could then turn it back to direct user interaction.

— [How Ultimate evolved from hundreds of supervised models to UltimateGPT](https://www.lutzfinger.com/transcript/2023-05-12-how-ultimate-evolved-from-hundreds-of-supervised-models-to-ultimategpt/) · _The Edge_

Question 17

Why do AI models still need human involvement even with unsupervised learning?

Accepted Answer

_Even advanced models can't escape the need for human judgment._

We need humans because there isn't always a true north for what's correct. Supervised learning works when there's a clear label, like Obama was president. That's a fact. But when you get into perception, like whether a joke is funny or which word to use about Obama's policies, it depends on context and perspective. The same happens with generated images. Art often creates things society didn't expect, so at what point is something random versus amazing? Since there's not a true label for certain things, we constantly need people to give feedback on the model and provide guardrails.

— [AI and the human factor](https://www.lutzfinger.com/transcript/2023-07-07-ai-and-the-human-factor/) · _The Edge_

Question 18

Why does Catalog change the user interface depending on the type of request?

Accepted Answer

_Dynamic interfaces that adapt to what you actually need to see._

We maintain about twenty to twenty-five abstract views, not thousands of deterministic flows like traditional enterprise tools. If it's a search, we render search results. If you ask for a summary, we render a summary view. If you ask for revenue from Q2 2023, we render a graph. The LLM dynamically adapts the interface to the use case. This is one level of abstraction higher than traditional UIs, which build very bespoke workflow-level interfaces. Ninety percent of use cases fall within the first five views.

— [Large Language Models: one interface to rule them all?](https://www.lutzfinger.com/transcript/2023-08-15-large-language-models-one-interface-to-rule-them-all/) · _The Edge_

Q&A, AI Workflows

How are AI agents different from RPA (robotic process automation)?

How can AI support frontline workers who aren't sitting at computers all day?

How do venture firms use AI in their own operations?

How does Catalog ensure certain workflows always follow the same steps when using LLMs?

How does Catalog use large language models to simplify enterprise software access?

What does 'AI as an operating model' mean?

What is an AI agent, really?

What makes autonomous AI agents different from traditional automation tools like RPA?

What patterns make a workflow 'agentic' rather than just a wrapper around an LLM?

What practical business use cases exist for language model chaining beyond autonomous agents?

What problem did transformers solve for Ultimate AI's multi-language support?

What was Ultimate AI's key insight that made customer onboarding faster than competitors?

Why are AI workflows the real moat?

Why are coding applications seeing the biggest success with AI agents right now?

Why are radically lean teams the future?

Why did Ultimate AI initially focus on helping human agents instead of automating customer conversations directly?

Why do AI models still need human involvement even with unsupervised learning?

Why does Catalog change the user interface depending on the type of request?