How AI Changed the Way We Work - Lessons from Introducing LLMs

TL;DR Introducing LLMs is not just choosing a model. To make AI useful in daily work, teams need retrieval, permissions, review steps, and security practices designed as one operating system.

You have probably heard the phrase, "AI will take people's jobs." But inside a company, it is often hard to see how AI is actually used. Here is the practical story of what Minisoft experienced while bringing LLMs, or large language models, into our work over the past year.

How a Business Request Becomes an Output

A work request does not end with the LLM alone. Internal data retrieval, human review, and final output validation are what make the result usable in real business.

What Is So Different About LLMs?

Traditional chatbots answered fixed questions with fixed responses. If a user asked in a slightly different way, the answer was often, "Sorry, I did not understand."

LLMs are different. They understand sentences as people write them, read the context, and generate an answer. It feels a little like giving a new employee the entire manual and letting them answer freely.

What We Tried First - And Why It Failed

Our first attempt was simple. We connected a public LLM API to an internal inquiry bot. The result was rough.

Problem 1: It Did Not Know Our Company

When someone asked, "What is our vacation policy?", it answered with general advice. It had no way to know Minisoft's actual policy.

Problem 2: It Made Things Up Convincingly

Sometimes it invented internal policies that did not exist. This is the familiar problem of hallucination. If an employee trusts the wrong answer, the damage can be real.

Starting Again with RAG

The answer was RAG, or retrieval-augmented generation. The system searches internal documents first, then passes those materials to the LLM with a prompt such as, "Please answer using these sources."

Think of a librarian. When you ask about a topic, the librarian first finds the relevant books, then helps answer from those books. If the answer is not in the book, the system can say so honestly.

What Actually Changed

New-hire Training Took Less Time

New employees started asking the bot instead of searching the internal wiki. Questions like "How do I settle travel expenses?" or "My VPN is not connecting" became easier to resolve. Repeated HR and admin questions dropped by about 40%.

Meeting Notes Became Automated

Upload a two-hour meeting recording, and within five minutes the system produces a summary, action items, and owners. The 30 minutes usually spent cleaning up notes after meetings disappeared.

AI Became the First Pass of Code Review

On the engineering team, an LLM now performs the first pass when a pull request is opened. It catches obvious mistakes, security risks, and convention violations. Human reviewers can spend more time on the design decisions that matter.

What We Learned

1. AI is a tool, not magic The key is deciding what to delegate to AI and what must stay with people.

2. Data cleanup is half the work For an LLM to answer well, internal documents must be organized. We had to clean up documents before the AI work could succeed.

3. Start small, then expand We did not try to automate everything at once. We solved one problem for one team first, then expanded after the effect was proven.

Closing

LLMs are not magic. But used well, they reduce repetitive work and let people focus on more important decisions. In the next article, we will look more closely at how a RAG system is built.

References

• NIST AI Risk Management Framework
• OWASP Top 10 for Large Language Model Applications