The exact context of every model call
Read the prompt that produced the answer — "why did it say that", answered by reading.
WhereTracing
Introduced Aug 9, 2026
Context · llm call 2
View context history
systemYou are a finance analyst…
messageWhich suppliers drove the Q3 overspend?
tool_resultpostgres_query → 1,204 rows
summary…compressed from 14 earlier items
How it works
The prompt is stored.
Each call keeps the exact context assembled for it — instructions, conversation, tool results.
Answered by reading.
Open the call behind any answer and read what the model actually saw — "why did it say that" stops being a debate.
Compression is an event too.
When a conversation is summarized to fit the model, you can see what the agent stopped seeing.
See it on your own cluster.
Thirty minutes, your infrastructure, your stack. Or skip the call — it is one Helm release onto a cluster you already run.