feat(agno): instrument agno evals - #723
Merged
Merged
Conversation
Every `agno.eval` run becomes a Braintrust eval row: input, expected, output,
scores. Agno's 1-10 scales and pass/fail verdicts normalize to 0-1; the raw
values are kept alongside them.
```py
from agno.eval.accuracy import AccuracyEval
import braintrust
braintrust.auto_instrument()
braintrust.init_logger(project="agno-agents")
AccuracyEval(agent=agent, input="...", expected_output="...").run()
```
Experiment — open one, and rows route there instead:
```py
braintrust.auto_instrument()
experiment = braintrust.init(project="agno-agents", experiment="v3")
```
A suite run opens an experiment of its own when none is already open, and
logs one row per Case:
```py
import sys
from agno.eval import Case, cli
sys.exit(cli(CASES))
```
```
multiplies_with_tool eval row, scores {judge, reliability}
|- Suite Calculator Agent.arun agent under test
| `- OpenAI.aresponse_stream
|- judge score span
`- reliability score span
```
What each eval type contributes:
```
AccuracyEval scores.accuracy + a score span per iteration
AgentAsJudgeEval scores.judge + a score span per batch case
ReliabilityEval scores.reliability tool-call evidence in output
PerformanceEval metrics only agno spans stand down while measuring
suite Case judge / reliability / scorer
```
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
Luca Forstner (lforst)
approved these changes
Sep 1, 2026
Member
Author
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Every
agno.evalrun becomes a Braintrust eval row: input, expected, output, scores. Agno's 1-10 scales and pass/fail verdicts normalize to 0-1; the raw values are kept alongside them.Experiment:
A suite run opens an experiment of its own when none is already open, and logs one row per Case:
What each eval type contributes: