Skip to content

Commit e8b84ab

Browse files
author
ajosh0504
committed
Updating components lecture notes
1 parent 7709c16 commit e8b84ab

File tree

1 file changed

+9
-6
lines changed

1 file changed

+9
-6
lines changed

docs/10-ai-agents/3-components-of-agents.mdx

Lines changed: 9 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,10 @@
11
# 📘 Components of AI agents
22

3-
AI agents have three main components: **planning and reasoning**, **memory**, and **tools**.
3+
AI agents have four main components: **perception**, **planning and reasoning**, **tools**, and **memory**.
44

5+
## Perception
6+
7+
Perception, in the context of AI agents, is the mechanism by which the agent gathers information about its environment. Text inputs are currently the most common perception mechanism for AI agents, but we are slowly progressing towards audio, visual, multimodal or even physical sensory inputs.
58

69
## Planning and reasoning
710

@@ -41,6 +44,10 @@ Final Answer: the final answer to the original input question
4144

4245
Reflection involves prompting an LLM to reflect on and critique past actions, sometimes incorporating additional external information such as tool observations. The generation-reflection loop is run several times before returning the final response to the user. Reflection trades a bit of extra compute for a shot at better output quality.
4346

47+
## Tools
48+
49+
Tools are interfaces for AI agents to interact with the external world in order to achieve their objectives. These can be APIs, vector databases, or even specialized machine learning models.
50+
4451
## Memory
4552

4653
The memory component allows AI agents to store and recall past conversations, enabling them to learn from these interactions.
@@ -49,8 +56,4 @@ There are two main types of memory for AI agents:
4956

5057
* **Short-term memory**: Stores and retrieves information from a specific conversation.
5158

52-
* **Long-term memory**: Stores, retrieves and updates information based on multiple conversations had over a period of time.
53-
54-
## Tools
55-
56-
Tools are interfaces for AI agents to interact with the external world and achieve their objectives. These can be APIs, vector databases, or even specialized machine learning models.
59+
* **Long-term memory**: Stores, retrieves and updates information based on multiple conversations had over a period of time.

0 commit comments

Comments
 (0)