updating documentation

Author: utkarshx

docs/agents/1_agentIntroduction.md

@@ -0,0 +1,29 @@
+# Agents Introduction
+
+Codebolt is an extremely powerful tool for AI Code Editing and AI Code Generation. Most of the power of Codebolt comes from the ability to use Agents. These agents are powerful tools that can be used to automate tasks, generate code, and even create entire applications. 
+
+## What is an Agent?
+
+Codebolt uses AI Agents for doing all the actions. Thing of Codebolt Editor as a big Agent Orchestrator that can use any agent in the marketplace to do any task.
+AI Agents interface with Codebolt using Codebolt Editor APIs. They can run any logic from talking to LLMs, updating the code, and any other tasks. They can use decision making power of LLMs to make decisions and take actions.
+
+## Codebolt Editor APIs
+
+Codebolt Editor exposes all the functionality of the Editor in the format of APIs. We have created various Libraries to access the Editor APIs. These libraries are available in the following languages:
+- [JavaScript](https://github.com/codebolt-ai/codebolt-js)
+- [Python](https://github.com/codebolt-ai/codebolt-python)
+
+## Codebolt Agents
+
+Codebolt has Multiple Types of Agents that can do various tasks.
+- [Universal Agents](./AgentTypes/universalAgents.md)
+- [Action Agents](./AgentTypes/actionAgents.md)
+
+### Universal Agents
+Universal Agents are called whenever the user sends any chat in the editor or asks to perform any action that can be resolved to any agent. You can learn more about them at [Universal Agents](./AgentTypes/universalAgents.md)
+
+### Action Agents
+Action Agents are called whenever the user sends any chat in the editor or asks to perform any action that can be resolved to any agent. You can learn more about them at [Action Agents](./AgentTypes/actionAgents.md)
+
+## Create your own Agents
+You can create your own Agents and use them in the editor. You can learn more about them at [Create your own Agents](./AgentTypes/createYourOwnAgents.md)

docs/agents/1_firstExtension.md renamed to docs/agents/2_firstExtension.md

@@ -1,4 +1,4 @@
 # Create your First Extension
 
 
-## Create Codebolt Agent
+## Create Codebolt Agent

docs/agents/2_runExtension.md renamed to docs/agents/4_runExtension.md

@@ -0,0 +1 @@
+# Create Custom Universal Agents

docs/agents/AgentTypes/UniversalAgents/createUniversalAgents.md

@@ -0,0 +1 @@
+#

docs/agents/AgentTypes/UniversalAgents/integratedUniversalAgents.md

@@ -0,0 +1,35 @@
+# Universal Agents
+
+Whenever the user sends any chat in the editor, Universal Agents are called to handle that Chat Request. 
+
+The Universal Agents performs the following tasks:
+- Understands the user's message and devises a plan to achieve the user's goal.
+- Creates a list of tasks to be performed to achieve the user's goal. In a sense, it generates a DAG (Directed Acyclic Graph) of tasks to be performed. See [Task Graph](./taskGraph.md)
+- Matches the tasks with the available agents and picks the best agents to perform those tasks. These could be one or more Agents depending on the Task Graph, and hence generating a DAG of Agents. See [Agent Graph]().
+
+## Integrated Universal Agent
+
+There is one Universal Agent that is integrated within the Codebolt Editor. This ensures that the code does not leaves the editor as well as also to decreate the response latency.
+
+## Custom Universal Agents
+
+You can also have Custom Universal Agents, that can route the user query requests to the appropriate agents using your custom logic or custom LLMs. We have an option to create your own Universal Agents. You can learn more about them at [Create your own Universal Agents](../CreateAgents/createUniversalAgent.md)
+
+
+## Architecture Choices
+
+The Concept of Universal Agents is Created so that we can route the user query requests to a set of appropriate agents.
+
+This is a very powerful concept as it allows for using all the agents in the marketplace to be available at disposal, and allows Codebolt to function as a Mega Agent.
+
+While we keep on updating the logic for Agent Selection, based on our custom training models, we have allowed you to write your custom logic for universal agents.
+
+## Why Write Custom Universal Agents?
+
+There are many reasons for you to write your own Universal Agents.
+- You might have a better logic for agent selection.
+- You might want to use a specific Agent for doing something.
+- You might want to avoid using any specific Agent for doing something.
+- You might have trained a better model for agent selection.
+
+There are multiple reasons for you to write your own Universal Agents.