Potential pre-assignment inputs
Useful fields depend on what is consistently populated.
- opportunity and lifecycle stage
- lead source and campaign
- activity and appointment history
- owner and territory
- won and lost outcomes
- available prospect context

Use Salesforce opportunity, activity, source, owner, territory, and outcome history to evaluate machine-learning-driven sales assignment.
Start with historical appointments, realistic eligibility rules, and outcomes that have had time to mature.
Salesforce can hold rich prospect and opportunity history, but standard assignment rules usually express eligibility and workflow rather than the probability that a specific eligible rep will win a specific appointment. Lithium Six adds that decision layer while Salesforce remains the system of record.
The integration maps CRM-specific objects and stages into a stable appointment-level record: prospect, source, appointment, assigned representative, property or opportunity context, and mature outcome.
Client-specific mappings remain explicit because pipelines, custom fields, and operating definitions differ even among companies using the same platform.
Useful fields depend on what is consistently populated.
CRM automation and business rules remain authoritative.
| Measurement | Why it matters | How to use it |
|---|---|---|
| Closed appointment win rate | Confirms that the Salesforce integration supports a reliable assignment decision. | Compare appointments that have had enough time to reach an outcome |
| Revenue per appointment | Confirms that the Salesforce integration supports a reliable assignment decision. | Compare similar periods, lead sources, and assignment approaches |
| Recommendation alignment | Confirms that the Salesforce integration supports a reliable assignment decision. | Compare appointments assigned to recommended representatives |
| Probability calibration | Confirms that the Salesforce integration supports a reliable assignment decision. | Review prediction accuracy alongside actual sales and revenue |
| Assignment coverage | Confirms that the Salesforce integration supports a reliable assignment decision. | Check for changes in lead mix and team performance before changing your approach |
Isotope Labs organizes your appointments, representative assignments, and outcomes into a history we can evaluate, using information available before each assignment.
We test predictions against historical outcomes kept separate from model training to identify reliable matches between opportunities and sales representatives.
We evaluate historical assignment scenarios that reflect representative eligibility, territories, availability, and workload limits.
See which recommendations your team uses and how those appointments perform, including close rate and revenue per appointment as outcomes become available.
Salesforce can hold rich prospect and opportunity history, but standard assignment rules usually express eligibility and workflow rather than the probability that a specific eligible rep will win a specific appointment. Lithium Six adds that decision layer while Salesforce remains the system of record.
No. Salesforce remains the system of record. Lithium Six adds a client-specific ranking layer for eligible representatives.
Only fields available before assignment should be considered. Outcome-revealing fields such as a final stage, sale date, or contract value must be excluded from prediction inputs.
The first step is a field and outcome mapping, followed by appointment-level quality checks and a held-out historical model evaluation.
Rank eligible in-home sales representatives using LeadPerfection lead, source, product, appointment, salesperson, and outcome history.
CRM guideEvaluate AccuLynx lead, job, appointment, source, salesperson, property, and outcome data for roofing-specific assignment optimization.
Strategy guideReview the fields, definitions, and history needed for a credible evaluation.
Share a representative CRM export or connect your data. Isotope Labs will evaluate data readiness, representative-performance variation, and the potential value of model-guided assignment before a live rollout.