update the doc structure

docs/core_abstraction/communication.md

@@ -81,7 +81,7 @@ Here:
 ## 2. Params
 
 **Params** let you store *per-Node* or *per-Flow* config that doesn't need to live in the shared store. They are:
-- **Immutable** during a Node’s run cycle (i.e., they don’t change mid-`prep->exec->post`).
+- **Immutable** during a Node's run cycle (i.e., they don't change mid-`prep->exec->post`).
 - **Set** via `set_params()`.
 - **Cleared** and updated each time a parent Flow calls it.
 

docs/design_pattern/agent.md

@@ -8,11 +8,11 @@ nav_order: 6
 # Agent
 
 Agent is a powerful design pattern, where node can take dynamic actions based on the context it receives.
-To express an agent, create a Node (the agent) with [branching](./flow.md) to other nodes (Actions).
+To express an agent, create a Node (the agent) with [branching](../core_abstraction/flow.md) to other nodes (Actions).
 
 > The core of build **performant** and **reliable** agents boils down to:
 > 
-> 1. **Context Management:** Provide *clear, relevant context* so agents can understand the problem.E.g., Rather than dumping an entire chat history or entire files, use a [Workflow](./decomp.md) that filters out and includes only the most relevant information.
+> 1. **Context Management:** Provide *clear, relevant context* so agents can understand the problem.E.g., Rather than dumping an entire chat history or entire files, use a [Workflow](./workflow.md) that filters out and includes only the most relevant information.
 >
 > 2. **Action Space:** Define *a well-structured, unambiguous, and easy-to-use* set of actions. For instance, avoid creating overlapping actions like `read_databases` and `read_csvs`. Instead, unify data sources (e.g., move CSVs into a database) and design a single action. The action can be parameterized (e.g., string for search) or  programmable (e.g., SQL queries).
 {: .best-practice }

docs/design_pattern/mapreduce.md

@@ -12,7 +12,7 @@ MapReduce is a design pattern suitable when you have either:
 - Large output data (e.g., multiple forms to fill)
 
 and there is a logical way to break the task into smaller, ideally independent parts. 
-You first break down the task using [BatchNode](./batch.md) in the map phase, followed by aggregation in the reduce phase.
+You first break down the task using [BatchNode](../core_abstraction/batch.md) in the map phase, followed by aggregation in the reduce phase.
 
 
 ### Example: Document Summarization

docs/design_pattern/rag.md

@@ -8,7 +8,7 @@ nav_order: 4
 # RAG (Retrieval Augmented Generation)
 
 For certain LLM tasks like answering questions, providing context is essential.
-Use [vector search](./tool.md) to find relevant context for LLM responses.
+Use [vector search](../utility_function/tool.md) to find relevant context for LLM responses.
 
 ### Example: Question Answering
 

docs/design_pattern/workflow.md

@@ -7,7 +7,7 @@ nav_order: 2
 
 # Workflow
 
-Many real-world tasks are too complex for one LLM call. The solution is to decompose them into a [chain](./flow.md) of multiple Nodes.
+Many real-world tasks are too complex for one LLM call. The solution is to decompose them into a [chain](../core_abstraction/flow.md) of multiple Nodes.
 
 
 > - You don't want to make each task **too coarse**, because it may be *too complex for one LLM call*.
@@ -46,3 +46,5 @@ writing_flow = Flow(start=outline)
 shared = {"topic": "AI Safety"}
 writing_flow.run(shared)
 ```
+
+For *dynamic cases*, consider using [Agents](./agent.md).

docs/index.md

@@ -30,18 +30,18 @@ We model the LLM workflow as a **Nested Directed Graph**:
 
 ## Core Abstraction
 
-- [Node](./node.md)
-- [Flow](./flow.md)
-- [Communication](./communication.md)
-- [Batch](./batch.md)
-- [(Advanced) Async](./async.md)
-- [(Advanced) Parallel](./parallel.md)
+- [Node](./core_abstraction/node.md)
+- [Flow](./core_abstraction/flow.md)
+- [Communication](./core_abstraction/communication.md)
+- [Batch](./core_abstraction/batch.md)
+- [(Advanced) Async](./core_abstraction/async.md)
+- [(Advanced) Parallel](./core_abstraction/parallel.md)
 
 ## Utility Function
 
-- [LLM Wrapper](./llm.md)
-- [Tool](./tool.md)
-- [Viz and Debug](./viz.md)
+- [LLM Wrapper](./utility_function/llm.md)
+- [Tool](./utility_function/tool.md)
+- [Viz and Debug](./utility_function/viz.md)
 - Chunking
 
 > We do not provide built-in utility functions. Example implementations are provided as reference.
@@ -50,13 +50,13 @@ We model the LLM workflow as a **Nested Directed Graph**:
 
 ## Design Pattern
 
-- [Structured Output](./structure.md)
-- [Workflow](./decomp.md)
-- [Map Reduce](./mapreduce.md)
-- [RAG](./rag.md)
-- [Chat Memory](./memory.md)
-- [Agent](./agent.md)
-- [(Advanced) Multi-Agents](./multi_agent.md)
+- [Structured Output](./design_pattern/structure.md)
+- [Workflow](./design_pattern/workflow.md)
+- [Map Reduce](./design_pattern/mapreduce.md)
+- [RAG](./design_pattern/rag.md)
+- [Chat Memory](./design_pattern/memory.md)
+- [Agent](./design_pattern/agent.md)
+- [(Advanced) Multi-Agents](./design_pattern/multi_agent.md)
 - Evaluation
 
-## [Build your LLM App](./guide.md)
+## [Develop your LLM Apps](./guide.md)