85742ab165
Deploy Documentation / deploy (push) Has been cancelled
CPU Test / Test (Utilities, legacy, Python 3.10) (push) Has been cancelled
CPU Test / Test (LLM proxy, stable, Python 3.11) (push) Has been cancelled
CPU Test / Test (Others, stable, Python 3.11) (push) Has been cancelled
CPU Test / Test (Store, stable, Python 3.11) (push) Has been cancelled
CPU Test / Test (Utilities, stable, Python 3.11) (push) Has been cancelled
CPU Test / Test (Weave, stable, Python 3.11) (push) Has been cancelled
CPU Test / Test (AgentOps, stable, Python 3.12) (push) Has been cancelled
CPU Test / Test (LLM proxy, stable, Python 3.12) (push) Has been cancelled
CPU Test / Test (Others, stable, Python 3.12) (push) Has been cancelled
CPU Test / Test (Weave, latest, Python 3.13) (push) Has been cancelled
Dashboard / Chromatic (push) Has been cancelled
CPU Test / Lint - fast (push) Has been cancelled
CPU Test / Lint - next (push) Has been cancelled
CPU Test / Lint - slow (push) Has been cancelled
CPU Test / Lint - JavaScript (push) Has been cancelled
CPU Test / Build documentation (push) Has been cancelled
CPU Test / Test (AgentOps, legacy, Python 3.10) (push) Has been cancelled
CPU Test / Test (LLM proxy, legacy, Python 3.10) (push) Has been cancelled
CPU Test / Test (Others, legacy, Python 3.10) (push) Has been cancelled
CPU Test / Test (Store, legacy, Python 3.10) (push) Has been cancelled
CPU Test / Test (Weave, legacy, Python 3.10) (push) Has been cancelled
CPU Test / Test (AgentOps, stable, Python 3.11) (push) Has been cancelled
CPU Test / Test (Store, stable, Python 3.12) (push) Has been cancelled
CPU Test / Test (Utilities, stable, Python 3.12) (push) Has been cancelled
CPU Test / Test (Weave, stable, Python 3.12) (push) Has been cancelled
CPU Test / Test (AgentOps, latest, Python 3.13) (push) Has been cancelled
CPU Test / Test (LLM proxy, latest, Python 3.13) (push) Has been cancelled
CPU Test / Test (Others, latest, Python 3.13) (push) Has been cancelled
CPU Test / Test (Store, latest, Python 3.13) (push) Has been cancelled
CPU Test / Test (Utilities, latest, Python 3.13) (push) Has been cancelled
CPU Test / Test (JavaScript) (push) Has been cancelled
17 lines
802 B
Plaintext
17 lines
802 B
Plaintext
<poml>
|
|
<role>You are a prompt engineer.</role>
|
|
<task>Analyze where the current prompt failed to elicit the right mechanism.</task>
|
|
<cp caption="Current Prompt Template">
|
|
<text whiteSpace="pre">{{ prompt_template }}</text>
|
|
</cp>
|
|
<cp caption="Sample Runs with Current Prompt Template">
|
|
<p>The following are the OpenTelemetry spans collected from the sample runs with the current prompt template. They should contain both prompt, responses and rewards.</p>
|
|
<cp for="experiment in experiments" caption="Sample Run #{{ loop.index + 1 }} Diagnostics">
|
|
<object for="span in experiment.spans" data="{{ span }}" />
|
|
</cp>
|
|
</cp>
|
|
<output-format>
|
|
Write 3-5 short bullets titled 'Critique:' focusing on missing constraints, ordering, or formatting.
|
|
</output-format>
|
|
</poml>
|