Evaluator Dashboard
Inspect recent LLM calls, failures, saved sessions, and compare branches.
Summary
2
saved sessions
4
persisted turns
0
saved compare branches
4
logged LLM calls
0
LLM call errors
Recent LLM Calls
| Time | Model | Status | Duration | Tokens | Prompt | Log |
|---|---|---|---|---|---|---|
| 3/18/2026, 3:08:34 PM | gpt-4.1-mini | ok | 8732 ms | 4846 | Use the following structured data to answer the user's question. Keep the response concise but helpf… | 2026-03-18-15-08-25-ans-001.json |
| 3/18/2026, 3:08:25 PM | gpt-4.1-mini | ok | 14922 ms | 17408 | { "userText": "show me the breakdown of GHGs in the atmosphere in case fusion energy is commercial… | 2026-03-18-15-08-25-sdk-001.json |
| 3/18/2026, 2:45:09 PM | gpt-4.1-mini | ok | 5278 ms | 3679 | Use the following structured data to answer the user's question. Keep the response concise but helpf… | 2026-03-18-14-45-02-ans-001.json |
| 3/18/2026, 2:45:02 PM | gpt-4.1-mini | ok | 4609 ms | 16495 | { "userText": "How is the distribution of GHGs affected by a $100 per ton carbon tax?", "activeI… | 2026-03-18-14-45-02-sdk-001.json |