From 09089c3ae3ffc7663993d07d1b8edf11e8bb5a0e Mon Sep 17 00:00:00 2001 From: Mason Hall Date: Thu, 29 Jan 2026 15:54:29 -0500 Subject: [PATCH] testing --- packages/external/mcp/evals/README.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/packages/external/mcp/evals/README.md b/packages/external/mcp/evals/README.md index 46787636c..77be3fb40 100644 --- a/packages/external/mcp/evals/README.md +++ b/packages/external/mcp/evals/README.md @@ -109,3 +109,16 @@ After running, these files are generated: 1. **Merit Systems Funding** - Find the total raised ($10M expected) 2. **CEO Email** - Find Merit Systems CEO's email address 3. **Top Carry Traders** - Find the top carry traders + + +### Notes + +Comparing against same config: + +Metric Value +Passed 17 +Failed 7 +Pass Rate 70.8% +Tokens 114,318 +Duration 4m 30s (concurrency: 4) +View detailed results → https://www.promptfoo.app/eval/eval-quR-2026-01-29T17:45:20 \ No newline at end of file