Update README

Author: johnsonr

README.md

@@ -16,9 +16,7 @@
 
     
 
-# Generated agent
-
-Java agent repository generated by the Embabel project creator.
+# Generated Agent Project
 
 Starting point for your own agent development using the [Embabel framework](https://github.com/embabel/embabel-agent).
 
@@ -31,7 +29,10 @@ Illustrates:
 - A simple agent
 - Unit tests for an agent verifying prompts and hyperparameters
 
-# To run
+> For the Kotlin equivalent, see
+> our [Kotlin agent template](https://github.com/embabel/kotlin-agent-template).
+
+# Running
 
 Run the shell script to start Embabel under Spring Shell:
 
@@ -43,47 +44,40 @@ There is a single example agent, `WriteAndReviewAgent`.
 It uses one LLM with a high temperature and creative persona to write a story based on your input,
 then another LLM with a low temperature and different persona to review the story.
 
-When the Embabel shell comes up, use the story agent like this:
+When the Embabel shell comes up, invoke the story agent like this:
 
 ```
 x "Tell me a story about...[your topic]"
 ```
 
-Try the `InjectedDemo` command to see simple, non-agent use:
+Try the `InjectedDemo` command to see simple, non-agent use.
+Type this in the interactive shell to see a single prompt create
+an imaginary animal:
 
 ```java
 animal
 ```
 
-## A2A Support
-
-Embabel integrates with the [A2A](https://github.com/google-a2a/A2A) protocol, allowing you to connect to other
-A2A-enabled agents and
-services.
-
-> Embabel agents can be exposed to A2A with zero developer effort.
+## Suggested Next Steps
 
-Check out the `a2a` branch of this repository to try A2A support.
+To get a feel for working with Embabel, try the following:
 
-You'll need the following environment variable:
+- Modify the prompts in `WriteAndReviewAgent` and `InjectedDemo`.
+- Experiment with different models and hyperparameters by modifying `withLlm` calls.
+- Integrate your own services, injecting them with Spring. All Embabel `@Agent` classes are Spring beans.
+- Run the tests with `mvn test` and modify them to experiment with prompt verification.
 
-- `GOOGLE_STUDIO_API_KEY`: Your Google Studio API key, which is used for Gemini.
+## Model support
 
-Start the Google A2A web interface using Docker compose:
-
-```bash
-docker compose up
-```
+Embabel integrates with any LLM supported by Spring AI.
 
-Go to the web interface running within the container at `http://localhost:12000/`.
+See [LLM integration guide](docs/llm-docs.md) (work in progress).
 
-Connect to your agent at `host.docker.internal:8080/a2a`. Note that `localhost:8080/a2a` won't work as the server
-cannot access it when running in a Docker container.
+Also see [Spring AI models](https://docs.spring.io/spring-ai/reference/api/index.html).
 
-Your agent will have automatically been exported to A2A. Add it in the UI, and start a chat.
-You should see something like this:
+## A2A support
 
-<img src="images/a2a_ui.jpg" alt="A2A UI" width="600">
+Embabel integrates with Google A2a. See [A2A integration](docs/a2a.md).
 
 ## Contributors
 

docs/a2a.md

@@ -0,0 +1,29 @@
+# A2A Support
+
+Embabel integrates with the [A2A](https://github.com/google-a2a/A2A) protocol, allowing you to connect to other
+A2A-enabled agents and
+services.
+
+> Embabel agents can be exposed to A2A with zero developer effort.
+
+Check out the `a2a` branch of this repository to try A2A support.
+
+You'll need the following environment variable:
+
+- `GOOGLE_STUDIO_API_KEY`: Your Google Studio API key, which is used for Gemini.
+
+Start the Google A2A web interface using Docker compose:
+
+```bash
+docker compose up
+```
+
+Go to the web interface running within the container at `http://localhost:12000/`.
+
+Connect to your agent at `host.docker.internal:8080/a2a`. Note that `localhost:8080/a2a` won't work as the server
+cannot access it when running in a Docker container.
+
+Your agent will have automatically been exported to A2A. Add it in the UI, and start a chat.
+You should see something like this:
+
+<img src="images/a2a_ui.jpg" alt="A2A UI" width="600">