Skip to content

Commit eccfdec

Browse files
authored
blog: fix typos in experimentation-over-capabilities.md
1 parent 1546300 commit eccfdec

1 file changed

Lines changed: 3 additions & 3 deletions

File tree

_posts/2025-07-06-experimentation-over-capabilities.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -16,10 +16,10 @@ When teams face pressure to pass specific scenarios by sprint's end, they often
1616
{: display: block;"}
1717
![Value via exp](/assets/experimentation-over-capabilities/grow-value-via-experiments.png){: style="float: left; margin: 0px 15px 0px 0px;" width="250"} Rather than expecting guaranteed capabilities as sprint outputs, teams building LLM-based products should focus on (i) defining experiments and (ii) growing their evaluation test suites.
1818

19-
Before each sprint, teams should consult with domain experts to:
19+
Before each sprint, teams should consult within themselves and other domain experts to:
2020

21-
1. **Propose an experimental approach** for addressing the evals (divide and conquering a multi-agent architecture, agent roles, tool specifications)
21+
1. **Propose an experiment** for addressing the evals (divide and conquering a multi-agent architecture, agent roles, tool specifications)
2222
2. **Propose additional realistic eval scenarios** that test new potential failure modes
2323

24-
At sprint's end, teams report eval [pass rates](https://www.philschmid.de/agents-pass-at-k-pass-power-k) (pass@1, pass@k, and passk) and provide an [error analysis](https://hamel.dev/notes/llm/officehours/erroranalysis.html) report explaining where the system falls short. This analysis then informs the next set of experiments to address those gaps.
24+
At sprint's end, teams report eval [pass rates](https://www.philschmid.de/agents-pass-at-k-pass-power-k) (pass@1, pass@k, and pass^k) and provide an [error analysis](https://hamel.dev/notes/llm/officehours/erroranalysis.html) report explaining where the system falls short. This analysis then informs the next set of experiments to address those gaps.
2525

0 commit comments

Comments
 (0)