Is an LLM the same as a chatbot?
No. An LLM is the model, and a chatbot or voice agent is a product built around one, with an interface, instructions, knowledge sources and limits. The same LLM can sit behind a text chatbot, a coding assistant or a voice agent.
What is the difference between conversational AI and generative AI?
Generative AI is any AI that produces new content, such as text, images or audio. Conversational AI is about dialogue with people. Modern conversational AI usually uses a generative model to write its replies, but conversational systems can also be fully scripted.
Is conversational AI the same as a chatbot?
A chatbot is one kind of conversational AI: the kind you type to. Conversational AI also covers voice assistants, phone voicebots and voice agents on websites, and the same language model can power several of them.
What is the difference between a virtual agent and a chatbot?
The terms overlap. A chatbot usually means a text interface, while virtual agent is a contact-centre term for AI that handles customer conversations on any channel, including voice, often with access to support systems.
Is a virtual agent the same as a virtual assistant?
Not quite. A virtual assistant can mean a person who does administrative work remotely, or a consumer AI assistant on a phone or smart speaker. Virtual agent is a customer service term for AI that handles the conversations a support or sales agent would otherwise take.
What is the difference between an AI agent and an AI workflow?
In a workflow, your code decides the steps and calls the model at fixed points. In an agent, the model decides which step or tool comes next, based on what it has found so far. Workflows are more predictable, and agents suit open-ended tasks that can’t be scripted in advance.
Is function calling the same as tool calling?
Yes. OpenAI uses both names for the same thing, and other providers call it tool use. A function is one kind of tool, defined by a name, a description and a JSON Schema for its arguments.
Does the model run the function itself?
No. The model only asks for the call. Your application runs the code, decides whether the call is allowed and returns the result, so permission checks belong in your code rather than in the prompt.
What is the difference between a system prompt and a user prompt?
The system prompt comes from the application and sets the rules for the whole conversation. A user prompt is what the person types or says in each turn. OpenAI documents that its models give developer instructions priority over user messages when the two conflict.
Can users see an AI’s system prompt?
Not directly, but a model can sometimes be talked into repeating it. Treat a system prompt as private but not secret, and keep credentials and sensitive data out of it.
What happens when a conversation is longer than the context window?
The oldest material has to be dropped or summarised, so the model can lose details from early in the conversation. Applications usually keep important facts outside the model, for example in a database, and add them back when they’re needed.
Does a bigger context window remove the need for retrieval?
Not usually. A bigger window holds more documents, but a longer prompt is usually slower to process, and focused excerpts make it easier for the model to use the passage that matters. Retrieval also lets you change the knowledge without rewriting the prompt.
What is the difference between grounding and RAG?
Grounding is the goal: answers based on trusted sources. Retrieval-augmented generation is one way to reach it, by searching a knowledge base and adding the results to the prompt. Grounding can also draw on other sources, such as a search engine or a database query.
Does grounding stop an AI from making things up?
It makes it less likely. A grounded model can still add details its sources don’t contain, or repeat a source that is wrong, so test with real questions and review the answers.
Can AI hallucinations be eliminated?
Not with current models. Grounding in checked sources, instructions to admit uncertainty and testing all reduce them, but a model can still state something false, so answers that matter need checking.
Is a wrong answer from an out-of-date source a hallucination?
Not strictly. An agent that repeats an approved but outdated source is grounded but wrong, while a hallucination is content the source doesn’t support. Both show up in transcripts, and the fixes differ: update the source, or tighten the instructions and test again.
Is RAG better than fine-tuning?
They do different jobs. Fine-tuning changes how a model behaves by training it further, while RAG gives it facts at the moment it answers. For product knowledge that changes often, RAG is easier to keep current, because you edit a document instead of retraining a model.
Does RAG need a vector database?
No. Many RAG systems use embeddings and a vector database to find passages by meaning, but the retriever can also be keyword search or a mix of both. Kawl Now uses keyword search over a small set of approved sources.
What is the difference between keyword search and semantic search?
Keyword search finds documents that contain the query’s words. Semantic search finds documents whose meaning is close to the query’s, even when the words differ, usually by comparing embeddings. Many systems combine the two, because each finds matches the other misses.
What is the difference between an embedding and a vector?
A vector is any ordered list of numbers. An embedding is a vector produced by a model to represent a piece of data, arranged so that similar items get similar vectors.
Are embeddings the same as tokens?
No. Tokens are the pieces text is split into, such as words or parts of words. An embedding is the list of numbers a model uses to represent a token, a sentence or a whole document.
What is the difference between a vector database and a regular database?
A regular database looks records up by their stored values, such as an ID, a date or a word. A vector database finds the records whose vectors are closest to a query vector, which suits searching by meaning. Extensions such as pgvector add vector search to an existing database, so one system can do both.
Can PostgreSQL be a vector database?
Yes, with an extension. pgvector adds a vector type, distance operators and approximate indexes such as HNSW to PostgreSQL, so embeddings can be stored with the rest of your data.
What is the difference between NLU and NLP?
Natural language processing (NLP) is the whole field of computers working with human language, including translation, summarisation and speech. NLU is the part concerned with meaning: working out what a person intends from what they said or typed.
Do large language models replace NLU?
In many conversational products, the LLM now does the understanding as part of writing its reply. Intent classification is still useful where each message has to trigger one of a fixed set of actions, such as a menu or a booking flow.