Task completion
Programmatic check of FHIR end state; MedAgentBench 300 tasks; <70% (2025) to >90% (2026) per secondary summary.
What task completion means
Programmatic check of FHIR end state; MedAgentBench 300 tasks; <70% (2025) to >90% (2026) per secondary summary.
Why it matters. Agents are judged by whether the record ends up correct.
A test checks that the requested order exists and nothing else changed.
How to measure it
Set tasks
Define tasks with a clear correct end state in the record.
Run in a sandbox
Use a FHIR test record, never a live chart.
Check the end state
Programmatically compare resulting records.
Review actions
Log every write and which needed approval.
Judging only the final answer misses harmful actions along the way.
Task completion with resources touched, actions taken, and approval coverage.
Report task completion with the FHIR resources touched, the actions taken, and which actions needed human approval.
Reviewed by the Precision research team.
How strong is the evidence
E3 · Secondary or single-source report. Reported by trade press or a single source. Directional only until checked against the primary document.
What the sources say
(Stanford HAI).
- Automatable. Can be scored by software, including an AI grader that is spot-checked against clinicians.
- Stanford HAIhai.stanford.edu
Found something out of date? Write to hello@precision.example.
Agents that measure this
Quick answers
What is task completion in healthcare AI?
Programmatic check of FHIR end state; MedAgentBench 300 tasks; <70% (2025) to >90% (2026) per secondary summary. It sits in the agentic ehr workflows group.
Why does task completion matter?
Agents are judged by whether the record ends up correct. A test checks that the requested order exists and nothing else changed.
How is task completion measured?
Set tasks, then Run in a sandbox, then Check the end state, then Review actions. Report task completion with the FHIR resources touched, the actions taken, and which actions needed human approval.
What should I watch out for with task completion?
Judging only the final answer misses harmful actions along the way. A good report gives: task completion with resources touched, actions taken, and approval coverage.
Can task completion be automated?
Largely yes, including AI graders that are spot-checked against clinicians. Report the grader's error rate beside every score.