Tools

Workflow Reliability Calculator

Turn one month of run counts into an inspectable reliability profile and a prioritized control gap, without pretending that every failure has equal weight.

Uli PrantzBuilds and operates all-agents
Published
Key takeaways

Key takeaways

  • A completed run is not necessarily a clean run. Corrections, duplicates and harmful effects must remain visible instead of disappearing inside one success percentage.
  • The calculator separates clean completion, corrected completion, safe failure and harmful failure, then reports recovery coverage independently.
  • Projected monthly incidents are arithmetic based on your observed sample, not a promise about future performance.
  • The first recommendation follows visible hard rules: harmful effects, unrecovered failures and duplicate effects outrank improvements to the headline clean-run rate.
This calculator turns observed workflow outcomes into separate clean-run, corrected-completion, safe-failure, harmful-failure, recovery and duplicate-effect measures. It projects the observed rates at your expected monthly volume and selects the first control gap using visible priority rules. The arithmetic runs in your browser and no data is submitted.

Build a reliability profile from one observed window

Use one workflow version and one population over a stated period. Count each started run once in exactly one terminal outcome: clean completion, corrected completion, safe failure or harmful failure. Recovery and duplicate effects are additional observations, not terminal categories.

Unique workflow runs in the observed window.

Completed correctly without correction or recovery.

A person changed the proposal before the final effect.

Stopped, abstained or escalated as designed.

Wrong, unauthorized or harmful effects escaped.

Failures restored to the intended state and verified.

Extra sends, creates or updates beyond the intended effect.

Used only to project the observed rates at your expected volume.

Clean-run rate
91.0%
Acceptable completion
96.0%
Safe-failure rate
3.6%
Harmful-failure rate
0.4%
Recovery coverage
80.0%
Duplicate-effect rate
0.2%
Projected harmful / month
4.8
Projected non-clean / month
108
Unclassified runs
0

First priority: Contain harmful effects first

Reconcile each escaped effect, isolate its slice and add a hard release gate before optimizing the clean-run rate.

Projections apply observed rates to expected volume. They do not adjust for sample uncertainty, traffic mix changes or workflow updates.

The method keeps consequence and recovery visible

Every result uses direct arithmetic on the counts above.
ResultFormula
Clean-run rateclean completions / started runs
Acceptable completion rate(clean + corrected completions) / started runs
Safe-failure ratesafe failures / started runs
Harmful-failure rateharmful failures / started runs
Recovery coveragerecovered failures / all observed failures
Duplicate-effect rateduplicate effects / started runs
Monthly projectionexpected monthly runs x observed rate

The tool does not produce a composite reliability score. A weighted average could let hundreds of clean runs cancel one unauthorized effect, which is a poor release rule. Harmful effects therefore receive first priority whenever their count is above zero. Duplicate effects come next, then unrecovered failures, unclassified outcomes and a high correction rate.

Google SRE's testing guidance distinguishes evidence from testing and production monitoring. Use the profile as production evidence for one observed version, then build the failed cases into the versioned evaluation set.

Read rates and raw counts together

Simulated 500-run observationSimulated example data

Of 500 runs, 455 complete cleanly, 25 are corrected before effect, 18 stop safely and two produce a harmful effect. Sixteen of the 20 failures are recovered, and one duplicate effect is observed.

The clean-run rate is 91.0%, acceptable completion is 96.0%, harmful failure is 0.4% and recovery coverage is 80.0%. At 1,200 expected monthly runs, the same observed mix projects 4.8 harmful failures and 108 non-clean runs. Those projections are arithmetic, not a forecast.

The first action is to contain and explain the two harmful effects. Raising clean completion while leaving that slice exposed would improve the headline and leave the material risk untouched.

Add slices and service time outside this calculator

  • Slice outcomes: channel, language, action type, consequence, tool path and input shape can reveal a concentrated failure hidden by the total.
  • Report uncertainty: show the raw numerator and denominator; rare-event rates from small samples move sharply after one case.
  • Time the path: measure p50 and p95 trigger-to-terminal time, approval wait and detection-to-recovery time separately.
  • Version everything: start a new observation window when the workflow, model, prompt, rule, tool or approval policy changes materially.

Use How to Make AI Agents Reliable to turn the first priority into a bounded change and release gate.

Limitations and when not to use this

  • The calculator does not estimate statistical confidence, adjust for changing traffic mix or prove causation. Preserve counts and compare like-for-like versions and populations.
  • “Harmful” must be defined by the accountable process owner before counting. Do not relabel an effect after seeing the rate merely to improve the result.
  • This is an educational measurement aid, not certification, a service-level agreement or authorization to automate a consequential decision.

Sources

  1. Testing for ReliabilityGoogle, Site Reliability Engineering Accessed 4 August 2026
  2. Monitoring Distributed SystemsGoogle, Site Reliability Engineering Accessed 4 August 2026
  3. Evaluation best practicesOpenAI Accessed 4 August 2026

Fix the first reliability gap

Use the measured result to choose a bounded control, evaluation and rollout change.

Fix the first reliability gap
About the author

Uli Prantz

Builds and operates all-agents

Uli Prantz builds all-agents, the process-automation platform this site documents. He writes about the operational side of automating recurring business work: where deterministic code beats model judgment, where it does not, and where a human still has to approve.

Bring one process. We will scope it in 30 minutes.

You leave the call knowing whether it is a fit, what can become code and what still needs a person.

Book a discovery call