Skip to main content

Optimizer troubleshooting

The Optimizer reports problems in three places: as banners on Setup, as a Couldn't launch optimization notice when a launch is refused, and as a Failed run whose reason appears on Live run and Results. The platform's raw text sits behind Technical details.

Who can use it: the Builder role or higher sees these messages. Configuring the optimiser's tier and granting access need an Admin or Super Admin.

Before a launch​

The top of Setup with an amber banner headed Configure a model for the optimizer first, explaining that the Prompt Optimizer needs an AI Gateway tier and naming the path Control Room → Platform Settings → Optimizer, with an Open Settings link; below it section 01 What to optimize with the Customer Support Agent selected and its facts.The top of Setup with an amber banner headed Configure a model for the optimizer first, explaining that the Prompt Optimizer needs an AI Gateway tier and naming the path Control Room → Platform Settings → Optimizer, with an Open Settings link; below it section 01 What to optimize with the Customer Support Agent selected and its facts.
Until an administrator picks a tier under Platform Settings, Setup opens with this banner and Launch optimization stays disabled.
The messageWhat it meansWhat to do
Configure a model for the optimizer first.No AI Gateway tier is set for the optimiser, so every trial's model call would fail.An administrator opens Platform Settings, Optimizer, picks a tier and selects Configure. Open Settings on the banner goes there.
This agent is a draft.The selected agent has no published version.Open agent and publish it, then come back.
No evaluators configured for this workspace yet.The workspace has no evaluators, so there is nothing to score with.New evaluator opens Evaluations.
Couldn't load your evaluatorsThe evaluation service did not answer. Launch stays disabled.Reload, or open Evaluations to check the service.
Couldn't load datasetsThe evaluation service did not answer the dataset list.The same.
No datasets yetThe workspace has no dataset.Create one in Storage or upload a CSV.

When a launch is refused​

Couldn't launch optimization appears above the launch bar with one of these reasons.

The messageWhat it meansWhat to do
Couldn't find the agentThe agent has no published version to use as a baseline.Publish the agent first, then try again.
Couldn't find the datasetThe dataset linked to the run no longer exists.Pick a different dataset or recreate this one.
We can't start this optimizationA setting is invalid.Check the form and try again.
Some of the settings need attentionA value failed validation.Look for the fields highlighted in red.
You don't have accessYour session expired, or your role may not run optimisations on this agent.Sign in again, or ask an administrator to grant you Optimizer access.
This run is already in progressAnother optimisation is active for this agent.Wait for it to finish; History shows the run in flight.
Too many optimizations at onceNew runs are being throttled.Try again in a few minutes.
Our side hit a problemThe optimisation service failed.Try again in a moment; if it keeps failing, contact support with the error details.

When a run fails​

The Live run tab of a failed run: a FAILED pill with a See what went wrong link, an error card titled Configure a model for the optimizer with the explanation, an Open Platform Settings action and a Technical details disclosure, a hero reading Run failed with the same reason, and the Run live rail with Status Failed and no trials completed.The Live run tab of a failed run: a FAILED pill with a See what went wrong link, an error card titled Configure a model for the optimizer with the explanation, an Open Platform Settings action and a Technical details disclosure, a hero reading Run failed with the same reason, and the Run live rail with Status Failed and no trials completed.
A failed run: the pill reads Failed with See what went wrong, and the error card gives the reason in plain words with the fix and a Technical details disclosure.

The pill reads Failed with See what went wrong, which scrolls to the reason. Live run's hero reads Run failed and its trials table Run failed before any trials completed when no trial landed; Results shows the same reason in a Run failed card.

The messageWhat it meansWhat to do
Configure a model for the optimizerThe run started without an AI Gateway tier and the model client could not be built.An administrator picks a tier under Platform Settings, Optimizer; then re-run.
Couldn't start the optimization engineThe optimisation engine did not respond.Contact support with the run id.
An agent setting is missingThe agent's live version has no explicit temperature or top-p, and the optimiser reads them directly.Open the agent in Workspace, Advanced, set both values, re-publish, then retry.
The dataset isn't usableThe dataset is empty or was deleted.Pick a different dataset and try again.
Optimization timed outThe run exceeded its time budget.Lower the trial count or lock more knobs in the search space, then retry.
Optimization cancelledThe run was stopped before it finished, which is also what Stop and accept produces.Start a new run if you still need one.
A resource is missingThe agent's published version, the dataset or an evaluator was not found.Check that the agent is published and the dataset still exists.
Optimization failedThe platform gave no further reason.Open Technical details and check History; contact support if it repeats.

Reading the results​

  • Results populate when the run completes. and Run not complete: the run is still queued, running or paused.
  • baseline not scored: the baseline evaluation did not run, so Results and Promote show scores without a lift.
  • This run produced no optimized prompt: the winner's prompt equals the baseline, so there is nothing to apply. Open more knobs or add trials and run again.
  • Couldn't load runs on History: the optimisation service did not answer for that agent. Reload.

Describes the platform as of .

Was this page helpful?