Salesforce Commercial and Professional Services Risk Management
Broughton Partners needed to move mass-tort claimant cases through its intake and confirmation work quickly while maintaining high case quality. Its audit work required distinguishing checks suited to predictable deterministic logic from those where AI reasoning could help, without surrendering human judgment on discrepancies.
Reported impact
The 18 Agentforce agents increase daily audit capacity while improving case quality, reduce claimant drop-off and daily audit work, and surface potential discrepancies for human review rather than making final decisions.
Broughton Partners connects mass-tort law firms with qualified claimants through lead generation, intake qualification, and claim confirmation, with quality and compliance at the center of the service. It needed to move cases out quickly without lowering the quality its clients expect. The Salesforce deployment uses 18 Agentforce agents to increase daily audit capacity and improve case quality. The team assigns checks according to whether they require deterministic logic or AI reasoning, their operating cost, and tolerance for error; AI is used for interpretation while clear-cut decisions remain predictable. Agents surface discrepancies with their reasoning, but Broughton staff make the final decision, keeping human review in the workflow and focusing staff on cases needing intervention. Salesforce lists Mulesoft and Apex, but the story gives no deployment roles for them and describes no ingestion, storage, model configuration, or external integrations.
10 reduction in claimant drop-off
2 x daily audit capacity while improving quality with 18 Agentforce Agents
60 reduction in daily audit work
A critical part of building confidence was knowing the agents would not make the final call on a discrepancy. They surfaced it for review, showed the reasoning, and Elizabeth’s team made the decision.
We had to figure out a way to get these cases out the door as quickly as possible while maintaining the high quality of cases that we are known for.
We looked at each check through three lenses: whether it needed deterministic logic or AI reasoning, the cost of running it, and how much room there was for error.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
OpenAI Sample Oct 15, 2026 Sullivan & Cromwell Sullivan & Cromwell needed to review draft agreements against relevant precedents, client priorities, and market practice in one workflow so lawyers could do deeper legal analysis without losing transparency into… Agreement Analyzer · ChatGPT Enterprise 
Anthropic Sample Archived · Sep 15, 2026 DXC Technology DXC needed to reduce insurance document backlogs and automate highly regulated underwriting and claims decisions without losing auditability, policy fidelity, or human oversight. 8 hours to stand up a regulated benefits calculation, 80% right on the first pass Assure · Claude Code · Claude Platform 
MongoDB Sample Aug 31, 2026 LexisNexis Risk Solutions LexisNexis needed an AI retrieval architecture that could preserve relationships and time context across fast-changing financial and commodities data, because standard RAG could not produce reliable answers for… LexisNexis publishes 2,000 articles daily and tracks over 2,200 global commodities. MongoDB Atlas 