docs: update README (#52)

docs/overview.mdx

@@ -1,6 +1,6 @@
 ---
 title: Overview
-description: 'Build test and deploy reliable AI applications at scale.'
+description: 'A TypeScript library to create and orchestrate AI Agents.'
 ---
 
 AgentKit is a framework for creating and orchestrating AI Agents, from single model inference calls to multi-agent systems that use tools. Designed with orchestration at it's core, AgentKit enables developers to build, test, and deploy reliable AI applications at scale.

packages/agent-kit/README.md

@@ -1,7 +1,7 @@
 # ![AgentKit by Inngest](./.github/logo.png)
 
 <p align="center">
-    <a href="https://www.inngest.com/docs/agent-kit/overview?ref=github-agent-kit-readme">Documentation</a>
+    <a href="https://agentkit.inngest.com/overview">Documentation</a>
     <span>&nbsp;·&nbsp;</span>
     <a href="https://www.inngest.com/blog?ref=github-agent-kit-readme">Blog</a>
     <span>&nbsp;·&nbsp;</span>
@@ -19,64 +19,75 @@ AgentKit is a framework for creating and orchestrating AI Agents, from single mo
 
 ## Overview
 
-A networked agent:
+Below is an example of a [Network](https://agentkit.inngest.com/concepts/networks) of three [Agents](https://agentkit.inngest.com/concepts/agents):
 
 ```ts
+import {
+  createNetwork,
+  createAgent,
+  openai,
+  anthropic,
+} from "@inngest/agent-kit";
+
+const navigator = createAgent({
+  name: "Navigator",
+  system: "You are a navigator...",
+});
+
+const classifier = createAgent({
+  name: "Classifier",
+  system: "You are a classifier...",
+  model: openai("gpt-3.5-turbo"),
+});
+
+const summarizer = createAgent({
+  name: "Summarizer",
+  system: "You are a summarizer...",
+  model: anthropic("claude-3-5-haiku-latest"),
+});
+
 // Create a network of agents with separate tasks and instructions
 // to solve a specific task.
 const network = createNetwork({
   agents: [navigator, classifier, summarizer],
-  defaultModel: openai({ model: "gpt-4o", step }),
+  defaultModel: openai({ model: "gpt-4o" }),
 });
 
 const input = `Classify then summarize the latest 10 blog posts
   on https://www.deeplearning.ai/blog/`;
 
-const result = await network.run(input, ({ network }) => {
-  // Use an agent which figures out the specific agent to call
-  // based off of the network's history.
-  return defaultRoutingAgent;
-});
+const result = await network.run(input);
 ```
 
-A simple agent:
-
-```ts
-const writer = createAgent({
-  name: "writer",
-  system:
-    "You are an expert writer.  You write readable, concise, simple content.",
-  model: openai({ model: "gpt-4o", step }),
-});
-
-const { output } = await writer.run(
-  "Describe the ideas behind the given input into clear topics, and explain any insight: " +
-    `<content>${content}</content>`,
-);
-```
+The Network will dynamically route the input to the appropriate Agent based on provided `input` and current [Network State](https://agentkit.inngest.com/concepts/state).
+AgentKit is flexible and allows for custom routing logic, tools, and the configuration of models at the Agent-level (_Mixture of Models_).
 
 ## Installation
 
-Agent kit requires the [Inngest TypeScript SDK](https://github.com/inngest/inngest-js) as a dependency. You can install both via `npm` or similar:
+You can install AgentKit via `npm` or similar:
 
 ```shell {{ title: "npm" }}
 npm install @inngest/agent-kit inngest
 ```
 
+Follow the [Getting Started](https://agentkit.inngest.com/getting-started/quick-start) guide to learn more about AgentKit.
+
 ## Documentation
 
 The full Agent kit documentation is available
 [here](https://www.inngest.com/docs/agent-kit/overview). You can also jump to
 specific guides and references:
 
-- [Agents and Tools](https://www.inngest.com/docs/agent-kit/ai-agents-tools)
-- [Network, state, and routing](https://www.inngest.com/docs/agent-kit/ai-agent-network-state-routing)
+- [Agents and Tools](https://agentkit.inngest.com/concepts/agents)
+- [Network, State, and Routing](https://agentkit.inngest.com/concepts/networks)
 
 ## Examples
 
 See Agent kit in action in fully functioning example projects:
 
-- [Test Writing Network](/demo#readme) - A ready-to-deploy Next.js demo using the Workflow Kit, Supabase, and OpenAI to power some AI content workflows.
+- [Hacker News Agent with Render and Inngest](https://github.com/inngest/agentkit-render-tutorial): A tutorial showing how to create a Hacker News Agent using AgentKit Code-style routing and Agents with tools.
+
+- [AgentKit SWE-bench](https://github.com/inngest/agent-kit/tree/main/examples/swebench#readme): This AgentKit example uses the SWE-bench dataset to train an agent to solve coding problems. It uses advanced tools to interact with files and codebases.
 
 ## License