Skip to main content
Xerg classifies spend into two groups:
  • confirmed waste
  • savings opportunities
This distinction is important because only confirmed waste contributes to wasteSpendUsd, structuralWasteRate, and CI threshold checks.

​
The five finding kinds

​
Retry waste

Classification: waste
Confidence: high Xerg treats failed calls that were followed by more work as pure retry overhead. The cost of those failed calls is counted as confirmed waste. Typical fix:
  • add exponential backoff
  • reduce retry count
  • avoid retrying known non-recoverable failures

​
Context bloat

Classification: opportunity
Confidence: medium For workflows with at least three runs, Xerg looks for runs whose input token volume is far above that workflow’s own baseline. This is a directional context-trimming signal, not proven waste. Typical fix:
  • trim prompt scaffolding
  • send less repeated context
  • split broad tasks into smaller scoped calls

​
Loop waste

Classification: waste
Confidence: high When a run reaches at least seven iterations, Xerg treats spend after iteration five as likely loop waste. Typical fix:
  • add an iteration cap
  • add an early exit condition
  • tighten workflow guardrails

​
Downgrade candidates

Classification: opportunity
Confidence: low Xerg flags expensive models on workflows that look operationally simple, such as heartbeat, triage, summary, tagging, or monitoring style tasks. This is intentionally an A/B test candidate rather than a claim of proven waste. Typical fix:
  • test a cheaper model on the same workflow
  • compare quality and cost before changing defaults

​
Idle waste

Classification: opportunity
Confidence: medium Xerg looks for workflow names that resemble recurring heartbeat, cron, poll, or monitoring loops. The spend may still be justified, but the cadence and model tier are worth reviewing. Typical fix:
  • reduce cadence
  • move to event-driven triggering
  • use a cheaper model for routine checks

​
Confidence levels

LevelMeaning
highStrong waste signal that is usually safe to act on immediately
mediumDirectional signal that should be investigated
lowExperiment candidate rather than a direct recommendation to roll out

​
Why this matters in the product

  • retry-waste and loop-waste roll up into confirmed structural waste
  • context-outlier, idle-spend, and candidate-downgrade roll up into opportunity impact
  • the first savings test in the terminal report may prioritize an opportunity even when it is not confirmed waste
For the recommendation object shape returned in JSON mode, see findings and recommendations.