Engineering articles from Salesforce
AI summaries and key learnings from Salesforce engineering teams.
Engineering Platform Trust: Cutting Customer Case Volume 20x with Petabyte-Scale Health Signals
The article details the development of a Technical Health Score system at Salesforce, aimed at quantifying platform trust through analytics pipelines that handle petabytes of telemetry data. By...
How Data 360 Optimized Kubernetes Scheduling Architecture, Delivering 13% Cost Savings
The article discusses how the Data 360 Compute Fabric team at Salesforce optimized Kubernetes scheduling to enhance resource efficiency and reduce costs. By evolving the default kube-scheduler...
Delivering Accurate, Low-Latency Voice-to-Form AI in Real-World Field Conditions
The article explores the development of a hybrid architecture for a voice-to-form AI system used in field service applications. It highlights the integration of on-device speech-to-text capabilities...
Hyperforce Migration at Scale: How Deterministic Automation Replaced Manual Spreadsheets Across 95,000 Organizations
The article outlines the development of the Migration Intake and Processing Service (MIPS) at Salesforce, which automates the migration of over 95,000 organizations to Hyperforce. It highlights the...
Building an AI-Accelerated Compliance Automation Platform for 24x Faster Audits
The article outlines the development of FastTrack, a compliance automation platform by Salesforce, which significantly reduces audit execution time through AI-assisted development and API-based...
From Audio to Action: How Speech Invocable Action Powers Native AI Automation Across Salesforce
The article explores the creation of the Speech Invocable Action by Salesforce's Agentforce Speech Foundations team, which enables secure, native speech automation within the Salesforce platform....
How Agentforce Achieved Accurate Flow Generation Across 461 Billion Monthly Executions Using a Constrained DSL
The article discusses the innovative approach taken by Agentforce to enhance the accuracy of flow generation by replacing fine-tuned models with a constrained Domain-Specific Language (DSL). This...
Against the Clock: How Data 360 Launched the Informatica Help Agent in 24 Days
The article outlines the rapid development of the Informatica Help Agent, achieved in just 24 days through the innovative use of Data 360. The team focused on transforming 100,000 unstructured...
How Agentic Memory Enables Durable, Reliable AI Agents Across Millions of Enterprise Users
The article discusses the development of Agentic Memory within Salesforce's Agentforce, aimed at enhancing the durability and reliability of AI agents across enterprise environments. It addresses the...
Re-Architecting Enterprise Applications for an Agentic System of Action
The article explores the necessity of re-architecting enterprise applications to accommodate agentic systems that can dynamically interpret situations and coordinate actions across various business...
How Agentforce Enhanced Chat Built an Agent-first Chat Experience While Ensuring Easy Migration for 3,000+ Customers
The article outlines the engineering efforts behind the development of Agentforce Enhanced Chat, emphasizing a microservices architecture that allows for seamless integration with existing customer...
Scaling Code Reviews: Adapting to a Surge in AI-Generated Code
The article explores the impact of AI-assisted coding tools on traditional code review processes, highlighting a significant increase in code volume and complexity that outpaces existing review...
Inside Salesforce Edge: Automating Global Rollback for 1.5 Trillion Requests in 10 Minutes
The article discusses the innovative architecture of Salesforce Edge, focusing on how the team reduced global rollback time from hours to minutes by implementing a blue-green deployment strategy. By...
How Agentforce, Data, and Apps Turned the Salesforce Stack into Agentforce 360
The article outlines the engineering innovations behind Salesforce's Agentforce 360 platform, emphasizing the integration of data, agent, and application layers into a cohesive architecture. It...
How Agentforce Runs Secure AI Agents at 11 Million Calls Per Day
The article provides an in-depth look at how Salesforce's Agentforce platform manages over 11 million daily agent calls while ensuring security and reliability. It highlights the architectural design...
How a Mock LLM Service Cut $500K in AI Benchmarking Costs, Boosted Developer Productivity
The article discusses the implementation of a mock LLM service at Salesforce, which significantly reduced AI benchmarking costs by over $500K annually. This internal service allows developers to...
How Agentforce Enabled Conversational Recommendations with AI-Driven Intent on Data 360
The article explores how the Data 360 Personalization team at Salesforce implemented AI-driven intent extraction to enhance conversational recommendations in Agentforce. By leveraging large language...
Scaling Sales Agents: Engineering Next-Gen AI for the Enterprise Era
The article outlines the engineering advancements made in scaling the Engagement Agent, a generative AI system designed for automating personalized sales outreach. It describes the transition from a...
Migration at Scale: Moving Marketing Cloud Caching from Memcached to Redis at 1.5M RPS Without Downtime
The article discusses a complex migration of the Marketing Cloud Caching infrastructure from Memcached to Redis, achieving a zero-downtime transition while handling approximately 1.5 million cache...
How Agentforce Enabled Incident Response Automation to Cut Common Resolution Time by 70 – 80%
The article outlines how Salesforce's Centralized Incident Response team leveraged AI-based anomaly detection and automation to significantly enhance incident management efficiency. By employing...