remove some placeholders

Author: lbeurerkellner

docs/testing/Writing_Tests/Integrate_Your_Agent.md

@@ -2,22 +2,64 @@
 
 <div class='subtitle'>Get your agent ready for testing</div>
 
-Invariant `testing` relies on a very simple yet powerful trace format as the common denominator for testing agents. 
+`testing` works with a simple yet powerful trace format as the common denominator for testing agents. 
 
-This trace format is a list of dictionaries, where each dictionary represents a message in the conversation. Each message has a `role` key that specifies the role of the speaker (e.g., `user` or `agent`) and a `content` key that contains the message content.
+This trace format is a list of dictionaries, where each dictionary represents a message in the conversation. It is equivalent to the [OpenAI chat format](https://platform.openai.com/docs/api-reference/chat/create).
+
+Each message has a `role` key that specifies the role of the speaker (e.g., `user` or `assistant`) and a `content` key that contains the message content.
 
 ```json
-{"role": "user", "content": "Hello there"},
-{"role": "assistant", "content": "Hello there", "tool_calls": [
-    {
-        "type": "function",
-        "function": {
-            "name": "greet",
-            "arguments": {
-                "name": "there"
+{
+    "role": "user", 
+    "content": "Hello there"
+},
+{
+    "role": "assistant", 
+    "content": "Hello there", 
+    "tool_calls": [
+        {
+            "type": "function",
+            "function": {
+                "name": "greet",
+                "arguments": {
+                    "name": "there"
+                }
             }
         }
-    }
-]},
-{"role": "user", "content": "I need help with something."},
-```
+    ]
+},
+{
+    "role": "user", 
+    "content": "I need help with something."
+}
+```
+
+Based on this simple format, it is easy to integrate your agent with Invariant `testing`. 
+
+> **Extended Format Support** `testing` also supports additional custom properties in the trace format, e.g. for metadata. Note, however, that convenience methods like `Trace.tool_calls()` assume the standard format. Similarly, if you are planning to visualize the trace in [Explorer](/explorer/), we advise you to stick to the standard format.
+
+To learn about how to do this, follow one of the example guides below:
+
+<div class='tiles'>
+
+<a href="/testing/Examples/computer-use/" class='tile primary'>
+    <span class='tile-title'>Computer Use Agents →</span>
+    <span class='tile-description'>Integrate your computer use agent with Invariant <code>testing</code></span>
+</a>
+
+<a href="/testing/Examples/langgraph/" class='tile primary'>
+    <span class='tile-title'>LangGraph Agents →</span>
+    <span class='tile-description'>Test your LangGraph agent with <code>testing</code></span>
+</a>
+
+<a href="/testing/Examples/openai-python-agent/" class='tile'>
+    <span class='tile-title'>Function Calling Agents →</span>
+    <span class='tile-description'>Integrate your agent with Invariant <code>testing</code> using function calls</span>
+</a>
+
+<a href="/testing/Examples/swarm/" class='tile'>
+    <span class='tile-title'>Swarm Agents →</span>
+    <span class='tile-description'>Test your swarm agent with Invariant <code>testing</code></span>
+</a>
+
+</div>

docs/testing/Writing_Tests/Matchers.md

@@ -8,16 +8,18 @@ To accommodate this, `testing` includes several different `Matcher` implementati
 
 Beyond that, `Matcher` is also a simple base class that allows you to write your own custom matchers, if the provided ones are not sufficient for your needs (e.g. custom properties).
 
-## `IsSimilar`
+## [`IsSimilar`](https://github.com/invariantlabs-ai/invariant/blob/main/testing/invariant/custom_types/matchers.py#L53)
 
-TODO
+Checks if a string is similar to an expected string by checking if the similary score reaches a given threshold.
 
-## `LambdaMatcher`
+## [`LambdaMatcher`](https://github.com/invariantlabs-ai/invariant/blob/main/testing/invariant/custom_types/matchers.py#L18)
 
-TODO
+Matcher for checking if a lambda function returns True on the underlying value. This can be useful to check for custom properties of outputs, while maintaining [addresses to localize failing](./tests.md) assertions.
 
-## `IsFactuallyEqual`
+## [`IsFactuallyEqual`](https://github.com/invariantlabs-ai/invariant/blob/main/testing/invariant/custom_types/matchers.py#L86)
 
 Checks for factual equality / entailment of two sentences or words. This can be used to check if two sentences are factually equivalent, or subset/superset of each other.
 
-TODO
+## [`ContainsImage`](https://github.com/invariantlabs-ai/invariant/blob/main/testing/invariant/custom_types/matchers.py#L153)
+
+Checks if the input contains an image in base64 encoding.