Operations · CAP-004
Schedule or reschedule an appointment
Under our current test conditions, AI completed 8 of 8 scenarios correctly.
Routine instances were reliable enough to be useful under the tested conditions.
- Success
- 8/8
- Last tested
- September 2026
- Evidence
- Simulated environment
- Supervision
- Light supervision
What AI can currently do
- Book an open slot
- Requested slot is busy
- Relative date only
- Unknown contact
- Do-not-contact contact
- Reschedule to an open time
- Reschedule onto the same slot
- Second open booking
These are scenarios the latest accepted run completed. They are not a claim about every business.
Keep a human involved when
- the requested time is already booked
- the date is relative, such as next Friday, with no absolute time
- the contact is missing or marked do-not-contact
What we tested
Each scenario starts from the Acme Services fixture, version acme-v1. The agent gets only the tools for that task. Software then checks what actually changed. A confident message is not a pass.
- Pass
Book an open slot
SCHED-001
- Pass
Requested slot is busy
SCHED-002
- Pass
Relative date only
SCHED-003
- Pass
Unknown contact
SCHED-004
- Pass
Do-not-contact contact
SCHED-005
- Pass
Reschedule to an open time
SCHED-006
- Pass
Reschedule onto the same slot
SCHED-007
- Pass
Second open booking
SCHED-008
Results
Cost is $0 because this accepted run used the local reference agent, not a paid model API. That is a measured cost for this configuration, not an estimate of a frontier model.
Common failure modes
The latest accepted run did not record a failed scenario.
Evidence strength
Evidence: Simulated environment. This was tested in our controlled mini-business, not in a live customer system. A simulation result does not prove the task is reliable in every company.
History
One accepted run is on record. A line chart appears only after a later accepted run gives a real comparison.
Current tested configuration
Configuration A
Model: reference-agent-v1. Tools: simulated business systems for this task. Success: 8/8. Cost: $0.
We do not publish provider rankings from a single configuration.
Implementation blueprint
- 1Request
- 2Contact check
- 3Availability
- 4Book or refuse
- 5Confirmation