Agentforce on Help Handles Over 2 Million Conversations
Salesforce· United StatesAgentforce · Data 360 · Atlas Reasoning Engine +1Salesforce built Agentforce on Help, an AI agent on its Help site that answers customer service questions in natural language grounded in unified Data 360, using the Atlas Reasoning Engine to classify intent and orchestrate prompts and LLM calls. The agent has handled more than 2 million conversations, freeing human support engineers for complex issues. Its Japanese-language launch facilitated more than 50,000 conversations with a 77% resolution rate, and the agent now supports French, German, Italian, Japanese, Portuguese, and Spanish without human translation.
Overview
Salesforce built Agentforce on Help, an AI agent on its Help site that answers customer service questions in natural language grounded in unified Data 360, using the Atlas Reasoning Engine to classify intent and orchestrate prompts and LLM calls. The agent has handled more than 2 million conversations, freeing human support engineers for complex issues. Its Japanese-language launch facilitated more than 50,000 conversations with a 77% resolution rate, and the agent now supports French, German, Italian, Japanese, Portuguese, and Spanish without human translation.
This entry has 15 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Salesforce wanted to scale high-quality, meaningful customer service without compromising trust or experience regardless of volume or time of day, while freeing human support engineers to focus on complex issues instead of routine, repetitive support questions.
The solution
Agentforce on Help, launched October 2024, is an AI agent built into Salesforce's unified platform that answers customer service questions in natural language on the Salesforce Help site, powered by Data 360 to analyze both structured data (account history, product usage) and unstructured content (knowledge articles, product documentation), with the Atlas Reasoning Engine orchestrating prompts, code and LLM calls to classify intent, and Agentforce Observability tracking latency, escalations and errors in real time.
Reported business value
Agentforce on Help has handled more than 2 million conversations with adoption still accelerating, freeing support and success teams to focus on complex issues and deeper customer relationships; its Japanese-language launch alone facilitated more than 50,000 conversations with a 77% resolution rate.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other technology & software entries in the register.
HP crafts marketing campaigns that resonate with customers using Databricks and Uniphore
HP centralized first-party customer data on the Databricks Data + AI Platform with Delta Lake and Unity Catalog, and connected it to Uniphore's HybridCompute for federated query pushdown, cutting campaign setup from 2 weeks to 2 hours and processing 400 million records in seconds.
Building a safer and more sustainable world
Novade, a construction management software company, partnered with Databricks to modernize its analytics and ML infrastructure, moving from a homegrown Apache Airflow stack to the Databricks Data + AI Platform with Delta Lake, Unity Catalog and MLflow. The move reduced total cost of ownership by 60% and supported a 100% increase in new clients, while enabling ML models for predicting incident risk affecting worker safety and project delivery schedules.
Transforming Weather Forecasting with Lakeflow Jobs
AccuWeather migrated from on-premises infrastructure to Databricks and Lakeflow Jobs, working with Datadog for observability, to unify diverse weather data formats and orchestrate 4,500+ weekly jobs. Lakeflow Jobs coordinates the ingestion of multiple weather models, triggers machine learning processes that weight and blend different forecasts, and manages complex job dependencies for reinforcement training workflows used in AccuWeather's proprietary forecasting engine. AccuWeather reports 3x faster dataset development (three months to one month per dataset), a 50% reduction in unactionable alerts, and 50% cost savings on serverless job usage.
AccuWeatherLakeflow Jobs · Delta Sharing · DatadogAdobe brings creativity to life with Databricks
Adobe uses the Databricks Data + AI Platform for end-to-end data management that unifies all data and AI at scale, with 20% faster performance. Databricks equips over 92 teams at Adobe to unify data from financials, sales, products, customers and employees so they can drive personalized experiences across Adobe's digital platforms with AI.
Was this helpful?
Your feedback helps us improve our use case database