DocsUsing DigitalHe

Task design and acceptance samples

Turn a business goal into a reproducible task and evaluate it with real samples.

Establish a human baseline

Measure effort, errors and review time over a full business cycle. Include preparation, waiting and rework when evaluating AI, not only generation time. Keep pilot inputs fixed so changing data does not obscure quality differences.

Write verifiable criteria

For a goal such as reducing report preparation time, define scope, calculations, review effort and acceptable exceptions. The business owner approves these before deciding whether the task suits an Agent.

Example criteria to agree per project
DimensionCheckExample target
ReconciliationCompare with an approved sampleTotals match; discrepancies are listed
TraceabilitySample source referencesMaterial figures have evidence
Human effortTime preparation, review and reworkImprovement over baseline, measured in the pilot
Unauthorized actionsRun denied-action samplesUnauthorized reads and sends are blocked

Cover normal and exceptional paths

Include complete inputs, missing fields, duplicates, conflicting rules, out-of-scope requests and provider timeouts. When evidence is absent, a correct response may identify the gap and escalate rather than invent a complete answer.

Evaluate a fixed revision

Record the brief, skill revision, model configuration, sample revision and output summary. Repeat selected cases to measure variation. Passing demonstrates the tested scope, not all possible scenarios. Rerun affected samples after policy or integration changes.

Turn failures into specific changes

Classify failures as missing inputs, obsolete knowledge, tool failures, access failures or unacceptable output. Assign owners and make each revision address a verifiable issue. Retain before-and-after results, then expand data volume and frequency after business acceptance.

All documentationNext guide

Still have a question?

Explore expert support