# Please explain Manager LLM like I am 25 **URL:** \ **Category:** CrewAI Community Support\ **Tags:** crewai\ **Created:** [May 4, 2025, 11:06am UTC](https://community.crewai.com/t/please-explain-manager-llm-like-i-am-25/5636 "2025-05-04T11:06:02Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Amitava\_Ghosh](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/amitava_ghosh/32/1345_2.png) [@Amitava\_Ghosh](https://community.crewai.com/u/Amitava_Ghosh)\ **Post date:** [May 4, 2025, 11:06am UTC](https://community.crewai.com/t/please-explain-manager-llm-like-i-am-25/5636/1 "2025-05-04T11:06:02Z")
I understand a planner llm, and then there are llm’s which are built for tool calling, And based on that, we have a rough idea on what llms to choose for: - classification - tool calling - task planning - where to use tools and control probability of success with guardrails. Like deepseek-r1 seems like the choice for task planning. Although qwen2.5-coder is also working. And then for tool calling, we have a determining factor, function\_calling\_llm . And as I understand, the task planning llm, is used to control the thought process part of the execution flow. But what is this Manager LLM, what are the characteristics of such an llm? What knobs does it tune, from as user perspective, what difference will there by, and if its not user side, then is it for optimizing execution. I have a thought, such an llm would also have same properties of a task planner llm. When looking for training, we are looking at training task planning, with multiple agents, so that the manager knows how to use multiple agents. Thereby having more control over `allow_delegation`. I don’t know if that’s right, also feels more like philosophy than technicality. So if someone could give a rough idea of this part of crewai. Thanks ---
**Author:** ![maxmoura](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/maxmoura/32/4206_2.png) [@maxmoura](https://community.crewai.com/u/maxmoura)\ **Post date:** [May 4, 2025, 3:24pm UTC](https://community.crewai.com/t/please-explain-manager-llm-like-i-am-25/5636/2 "2025-05-04T15:24:09Z")
Hey Amitava, I think the issue you’re bringing up might be the same one I discussed [over in this other thread here](https://community.crewai.com/t/does-hierarchical-process-even-work-your-experience-is-highly-appreciated/2690/8), is that right? My answer there might not cover _all_ of your questions. If that’s the case, once you’ve had a chance to look over the points I clarified there, maybe that can be a starting point for you to explain what doubts still remain. ---
**Author:** ![Amitava\_Ghosh](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/amitava_ghosh/32/1345_2.png) [@Amitava\_Ghosh](https://community.crewai.com/u/Amitava_Ghosh)\ **Post date:** [May 4, 2025, 7:31pm UTC](https://community.crewai.com/t/please-explain-manager-llm-like-i-am-25/5636/3 "2025-05-04T19:31:00Z")
Yes, thanks. It clears things up. ---
**Author:** ![Amitava\_Ghosh](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/amitava_ghosh/32/1345_2.png) [@Amitava\_Ghosh](https://community.crewai.com/u/Amitava_Ghosh)\ **Post date:** [May 5, 2025, 11:55am UTC](https://community.crewai.com/t/please-explain-manager-llm-like-i-am-25/5636/4 "2025-05-05T11:55:50Z")
I had a question. So for a manager llm, If I were to use it, should I mention the order of execution, in maybe the backstory? So that the Thought Action part can have better predictability? ---
**Author:** ![maxmoura](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/maxmoura/32/4206_2.png) [@maxmoura](https://community.crewai.com/u/maxmoura)\ **Post date:** [May 5, 2025, 3:43pm UTC](https://community.crewai.com/t/please-explain-manager-llm-like-i-am-25/5636/5 "2025-05-05T15:43:47Z")
Amitava, - If you choose to pass just an `LLM`—meaning, you use the `manager_llm` parameter—then the manager `Agent` itself will be built internally by CrewAI. It’ll create an `Agent` with a `role`, `goal`, and `backstory` tailored to be a pretty competent manager. This agent will be responsible for coordinating tasks (or sub-tasks, however it decides) and assigning them to the other `Agents` (these are the coworkers you define the standard way). - Now, if you opt to provide a `manager_agent` instead, it has to be an `Agent` that you _cannot_ assign any `Task` to. You’ll need to define its `role`, `goal`, and `backstory` yourself to best suit your needs. That’s pretty much the extent of the control you have over customizing the manager in this case. > [@Amitava\_Ghosh](#): > > So that the Thought Action part can have better predictability? This part caught my eye, and I’m going to repeat something I often say: this is an _agentic_ approach, which means you need a good deal of trust in your coordinating agent. You have to accept that at the end of a slightly unpredictable (probabilistic) process, you’ll hopefully get a valid solution. You might get the big picture of what needs doing, you might see details of what’s currently happening, but you’re not micromanaging every single step. In most situations, you (or your client) will want fine-grained control. Especially in the corporate world, processes are usually very well-defined (or hey, they _should_ be!), and agentic systems need to fit into and boost these established methodologies. For those scenarios, the [Flows paradigm](https://docs.crewai.com/concepts/flows) in CrewAI is a much better fit. It features well-defined steps, flow control, and persistence, excelling at capturing structured processes and delivering that _better predictability_. [In this other thread](https://community.crewai.com/t/manager-agent-delegates-task-to-wrong-agent-in-a-hierarchical-process/3179/4), I actually tackled the same problem using both `crewai.Process.hierarchical` and then showed a really clear and simple solution using `crewai.flow`. ---
**Author:** ![Amitava\_Ghosh](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/amitava_ghosh/32/1345_2.png) [@Amitava\_Ghosh](https://community.crewai.com/u/Amitava_Ghosh)\ **Post date:** [May 6, 2025, 5:44am UTC](https://community.crewai.com/t/please-explain-manager-llm-like-i-am-25/5636/6 "2025-05-06T05:44:40Z")
Awesome. Thanks. Yeah after reading the thread, I realized too, the manager\_agent is not something I can just introduce, I mean, most of the time I am looking for structured output, from the inputs and outputs. Tbh, writing predictable flows, it is starting to feel like another way to write apis. Especially the controller layer. ---
**Author:** ![system](https://us1.discourse-cdn.com/flex025/uploads/crewai/original/1X/ecda97e72f77c7100e0a761444b1c991925cc789.png) [@system](https://community.crewai.com/u/system)\ **Post date:** [May 7, 2025, 5:45am UTC](https://community.crewai.com/t/please-explain-manager-llm-like-i-am-25/5636/7 "2025-05-07T05:45:26Z")
This topic was automatically closed 24 hours after the last reply. New replies are no longer allowed.