Semogram Docs
Forecasting and predictionsRun and inspect

Read a prediction

Inspect the saved answer, evidence, lineage, warnings and execution state

A prediction is a durable run record, not just its generated output. Open it from the project Predictions list or use prediction_get with predictionId. Check execution and outcome separately before using the answer.

What to inspect

Record informationWhy it matters
Subject, horizon and horizonEndsAtEstablishes what and when the forecast addresses
Forecaster/version and query releaseIdentifies executable instructions and evidence logic
Evidence rows, diagnostics and snapshot/hashShows what supported the run and any retrieval limits
Prompt snapshot and modelRecords the actual instructions and selected runtime model
Output, probability and confidenceSeparates the answer from the model's support assessment
Warnings, error kind and attemptShows limitations or execution failure
Tokens, latency and cost statusMakes work and accounting availability visible
Evaluation versions and outcomeConnects the prediction to later observations

Equipment reading example

Suppose a P-101 run outputs probability 0.7 and confidence 0.4. Those values are illustrative, not an expected answer to the fixture. The forecast suggests a 70% chance of the defined event, with weak support. Inspect whether the evidence actually contains P-101's measurements, their timestamp, service history coverage and relevant diagnostics.

New runs require complete evidence within the shared query budgets. Source truncation, result overflow or unknown completeness fails the run before forecasting, including later agent evidence refreshes. The saved evidence snapshot includes completeness, incompleteReasons and truncatedSources. Older completed records can still contain limited evidence; inspect their stored metadata rather than treating them as newly verified.

Reproducibility limits

The query release freezes logic, not every external source value. The invocation cutoff is recorded but does not automatically enforce historical source filtering. Replaying a prompt against today's live records can answer a different question. Keep actual evidence artifacts when comparing historical forecasts.

A confidence value is not a calibration report. An apparently precise probability or polished rationale is not an observed failure. Prediction output must be checked against evidence, then evaluated against real outcomes.

Follow up

Completed forecasts can be evaluated when the window permits. Failed or Cancelled runs do not have a completed typed forecast to score. Pending outcomes need observation, not another interpretation of the generated output. Use a new run for a new window or revised configuration; do not rewrite an older result to fit what happened.

Evidence completeness is shown in the prediction summary. New successful runs retain complete evidence metadata. Older records without completeness metadata display “Completeness unverified”; they are not retroactively certified. Refused runs show the reason in their execution error.