Can we please stop throwing an LLM in a chat UI and call it...
Victoria Slocum@victorialslocum
12 views
Nov 06, 2025
~2 min read
Advertisement
1
Can we please stop throwing an LLM in a chat UI and call it โagenticโ?
True agentic systems are built with actual intelligence.
And no, I don't mean artificial intelligence or some special model. I mean well-architectured systems that ๐ฅ๐ฐ things.
I've seen this pattern way too many times lately: slap GPT-4 into a chat interface, maybe add a system prompt, and suddenly it's marketed as an "agentic AI system."
That's not agentic. That's just... a chatbot.
๐ฆ๐ผ ๐๐ต๐ฎ๐ ๐ฎ๐ฐ๐๐๐ฎ๐น๐น๐ ๐บ๐ฎ๐ธ๐ฒ๐ ๐ฎ ๐๐๐๐๐ฒ๐บ ๐ฎ๐ด๐ฒ๐ป๐๐ถ๐ฐ?
True ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐๐ requires specific architectural components working together:
โข ๐ฅ๐ฒ๐ฎ๐๐ผ๐ป๐ถ๐ป๐ด & ๐ฃ๐น๐ฎ๐ป๐ป๐ถ๐ป๐ด - The LLM needs to break down complex tasks, plan execution routes, and iterate on its approach. Not just respond to prompts.
โข ๐ง๐ผ๐ผ๐น ๐จ๐๐ฒ - Access to actual external tools it can call and interact with. Function calling that lets the agent DO things, not just talk about them.
โข ๐ ๐ฒ๐บ๐ผ๐ฟ๐ ๐ฆ๐๐๐๐ฒ๐บ๐ - Both short-term (conversation state) and long-term (learning from past interactions). This is where vector databases become essential.
โข ๐ฆ๐ฒ๐น๐ณ-๐ฅ๐ฒ๐ณ๐น๐ฒ๐ฐ๐๐ถ๐ผ๐ป - The ability to evaluate its own outputs, critique its reasoning, and adjust its approach.
Here's the thing: not every component needs to be present, but you need ๐ฎ๐ฐ๐ณ๐ฆ ๐ต๐ฉ๐ข๐ฏ ๐ซ๐ถ๐ด๐ต ๐ข๐ฏ ๐๐๐ to call something agentic.
๐ง๐ต๐ฒ ๐ฑ๐ถ๐๐๐ถ๐ป๐ฐ๐๐ถ๐ผ๐ป ๐บ๐ฎ๐๐๐ฒ๐ฟ๐:
An "AI agent" = an end application built for a specific task (like a docs search assistant)
"Agentic AI" = a system designed with agentic components like decision-making, reasoning loops, tool orchestration.
A simple chat interface, even with a great LLM? ๐ก๐ผ๐. ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ.
A system using a decision tree architecture, with tool access, memory, and iterative planning? Now we're talking.
IMHO, we need more precision in our terminology. The capabilities are genuinely impressive when built properly - let's not dilute the term by applying it to everything with a text box.
Ok rant over, thanks for coming to my TED talk โ๏ธ
True agentic systems are built with actual intelligence.
And no, I don't mean artificial intelligence or some special model. I mean well-architectured systems that ๐ฅ๐ฐ things.
I've seen this pattern way too many times lately: slap GPT-4 into a chat interface, maybe add a system prompt, and suddenly it's marketed as an "agentic AI system."
That's not agentic. That's just... a chatbot.
๐ฆ๐ผ ๐๐ต๐ฎ๐ ๐ฎ๐ฐ๐๐๐ฎ๐น๐น๐ ๐บ๐ฎ๐ธ๐ฒ๐ ๐ฎ ๐๐๐๐๐ฒ๐บ ๐ฎ๐ด๐ฒ๐ป๐๐ถ๐ฐ?
True ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐๐ requires specific architectural components working together:
โข ๐ฅ๐ฒ๐ฎ๐๐ผ๐ป๐ถ๐ป๐ด & ๐ฃ๐น๐ฎ๐ป๐ป๐ถ๐ป๐ด - The LLM needs to break down complex tasks, plan execution routes, and iterate on its approach. Not just respond to prompts.
โข ๐ง๐ผ๐ผ๐น ๐จ๐๐ฒ - Access to actual external tools it can call and interact with. Function calling that lets the agent DO things, not just talk about them.
โข ๐ ๐ฒ๐บ๐ผ๐ฟ๐ ๐ฆ๐๐๐๐ฒ๐บ๐ - Both short-term (conversation state) and long-term (learning from past interactions). This is where vector databases become essential.
โข ๐ฆ๐ฒ๐น๐ณ-๐ฅ๐ฒ๐ณ๐น๐ฒ๐ฐ๐๐ถ๐ผ๐ป - The ability to evaluate its own outputs, critique its reasoning, and adjust its approach.
Here's the thing: not every component needs to be present, but you need ๐ฎ๐ฐ๐ณ๐ฆ ๐ต๐ฉ๐ข๐ฏ ๐ซ๐ถ๐ด๐ต ๐ข๐ฏ ๐๐๐ to call something agentic.
๐ง๐ต๐ฒ ๐ฑ๐ถ๐๐๐ถ๐ป๐ฐ๐๐ถ๐ผ๐ป ๐บ๐ฎ๐๐๐ฒ๐ฟ๐:
An "AI agent" = an end application built for a specific task (like a docs search assistant)
"Agentic AI" = a system designed with agentic components like decision-making, reasoning loops, tool orchestration.
A simple chat interface, even with a great LLM? ๐ก๐ผ๐. ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ.
A system using a decision tree architecture, with tool access, memory, and iterative planning? Now we're talking.
IMHO, we need more precision in our terminology. The capabilities are genuinely impressive when built properly - let's not dilute the term by applying it to everything with a text box.
Ok rant over, thanks for coming to my TED talk โ๏ธ
2
BTW we release our context engineering ebook yesterday, which basically goes into the practical applications of the above. Download it here: weaviate.io/ebooks/the-conโฆ