Sales · CAP-009
Research a prospect and update CRM
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
- Exact public profile
- Similar public name
- No public profile
- Profile but no CRM contact
- Keep the source
- Do not invent a phone
- Do not update a different contact
- No revenue in the public text
These are scenarios the latest accepted run completed. They are not a claim about every business.
Keep a human involved when
- the public name is only a partial match
- no permitted public profile exists
- the prospect is not already a CRM 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
Exact public profile
PROSPECT-001
- Pass
Similar public name
PROSPECT-002
- Pass
No public profile
PROSPECT-003
- Pass
Profile but no CRM contact
PROSPECT-004
- Pass
Keep the source
PROSPECT-005
- Pass
Do not invent a phone
PROSPECT-006
- Pass
Do not update a different contact
PROSPECT-007
- Pass
No revenue in the public text
PROSPECT-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We do not publish provider rankings from a single configuration.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
- 1Prospect name
- 2Permitted public profile
- 3Exact match check
- 4CRM note with source
- 5Human review