Skip to content

A programming framework for agentic AI

Update doc and README (#135)

Eric Zhu905e2e3f95bc
diff --git a/README.md b/README.md
index be9e04c30..c007fcbfb 100644
--- a/README.md
+++ b/README.md
@@ -2,5 +2,6 @@
See corresponding subdirectories for more information.
-- [Python Documentation](http://microsoft.github.io/agnext)
-- [Python Examples](https://github.com/microsoft/agnext/tree/main/python/examples)
+- [Python README](https://github.com/microsoft/agnext/tree/main/python/README.md) for how to develop and test the Python package.
+- [Python Documentation](http://microsoft.github.io/agnext) for the core concepts and API reference.
+- [Python Examples](https://github.com/microsoft/agnext/tree/main/python/examples) for examples of how to use the Python package and multi-agent patterns.
diff --git a/python/docs/src/core-concepts/agent.md b/python/docs/src/core-concepts/agent.md
index f5655fe95..d224735d9 100644
--- a/python/docs/src/core-concepts/agent.md
+++ b/python/docs/src/core-concepts/agent.md
@@ -4,10 +4,6 @@ An agent in AGNext is an entity that can react to, send, and publish
messages. Messages are the only means through which agents can communicate
with each other.
-Examples of agents include:
-
-- A chat completion agent that makes requests to an LLM in response to receiving messages.
-
## Messages
Messages are typed, and serializable (to JSON) objects that agents use to communicate. The type of a message is used to determine which agents a message should be delivered to, if an agent can handle a message and the handler that should be invoked when the message is received by an agent. If an agent is invoked with a message it is not able to handle, it must raise {py:class}`~agnext.core.exceptions.CantHandleException`.
diff --git a/python/docs/src/core-concepts/patterns.md b/python/docs/src/core-concepts/patterns.md
index e1b32b014..4e640ae03 100644
--- a/python/docs/src/core-concepts/patterns.md
+++ b/python/docs/src/core-concepts/patterns.md
@@ -10,5 +10,5 @@ like software development.
You can implement any multi-agent pattern using AGNext agents, which
communicate with each other using messages through the agent runtime
(see {doc}`/core-concepts/runtime` and {doc}`/core-concepts/agent`).
-See `examples <https://github.com/microsoft/agnext/tree/main/python/examples#pattern-examples>`_
+See [examples](https://github.com/microsoft/agnext/tree/main/python/examples#pattern-examples)
for how to implement patterns like reflection and group chat.