diff --git a/CHANGELOG.md b/CHANGELOG.md
index c1e990d..3ab54f0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+- thread_id to track_llm_events
+
+### Changed
+- assistant_id now optional in track_llm_events
+
 ## [1.8.3] - 2025-02-26
 ### Changed
 - Change logging level to debug for flushing events and adding event to queue
diff --git a/README.md b/README.md
index 077211a..33ba6c2 100644
--- a/README.md
+++ b/README.md
@@ -40,10 +40,10 @@ client.track_llm(
     assistant_id="gpt-4",
     generation="The capital of France is Paris.",
     properties={
-        "$thread_id": "your-thread-id",  # special trubrics property to group an interaction by conversation thread
-        "model": "gpt-4"
+        "support_tier": "entreprise",
     },
-    latency=1.5  # seconds
+    latency=1.5,  # seconds
+    thread_id="user123_thread_id"
 )
 ```
 
diff --git a/trubrics/main.py b/trubrics/main.py
index e6ec2c2..dc3c58d 100644
--- a/trubrics/main.py
+++ b/trubrics/main.py
@@ -114,22 +114,24 @@ def track_llm(
         self,
         user_id: str,
         prompt: str,
-        assistant_id: str,
         generation: str,
+        assistant_id: str | None = None,
         properties: dict | None = None,
         timestamp: datetime | None = None,
         latency: float | None = None,
+        thread_id: str | None = None,
     ):
         """
         Track an LLM prompt and generation.
         Args:
             user_id (str): The ID of the user.
             prompt (str): The prompt given to the LLM.
-            assistant_id (str): The ID of the assistant.
             generation (str): The generated response from the LLM.
+            assistant_id (str | None): The ID of the assistant.
             properties (dict | None): Additional properties to track.
             timestamp (datetime | None): The timestamp of the generation event. If None, the current time in UTC is used.
             latency (float | None): The latency in seconds between the prompt and the generation. Defaults to 1.
+            thread_id (str | None): The ID of the thread, used to link messages in a conversation.
         """
 
         llm_event_dict = {
@@ -145,6 +147,7 @@ def track_llm(
             ),
             "latency": latency,
             "event_type": EventTypes.llm_event,
+            "thread_id": str(thread_id) if thread_id else None,
         }
 
         with self._lock: