# Salesforce

See what's happening beyond the cloud.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Building Predictive AI Models When Synthetic Data Is All You Have

DevFeed: [Building Predictive AI Models When Synthetic Data Is All You Have](<https://devfeed.tech/articles/building-predictive-ai-models-when-synthetic-data-is-all-you-have-144066.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/building-predictive-ai-models-when-synthetic-data-is-all-you-have/>)

Author: Taniya Ghosh

Published: 2026-11-19T00:59:15Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [customer-data](<https://devfeed.tech/tags/customer-data.md>), [data](<https://devfeed.tech/tags/data.md>), [data-360](<https://devfeed.tech/tags/data-360.md>), [predictive-ai](<https://devfeed.tech/tags/predictive-ai.md>), [synthetic-data](<https://devfeed.tech/tags/synthetic-data.md>), [training-data](<https://devfeed.tech/tags/training-data.md>)

### AI overview

Salesforce's team built reusable IT service management prediction templates before real customer incidents were available for training. Product-manager scenarios, varied within guardrails and expanded with open-source LLMs, supplied synthetic data for testing. To avoid being misled by aggregate accuracy on rare SLA breaches, the team checked whether scores changed as expected when one risk factor changed and whether the top three predictors made sense to service managers; these scenario tests did not establish production accuracy. Data 360 transforms customer incident histories into training data, Einstein on Data 360 trains an XGBoost model, and a scoring transform writes predictions for display on incident records. Templates carry the data contract and model structure, while each customer's history supplies its own learned parameters. The excerpt says training requires about 400 completed incidents and scoring runs in scheduled batches about hourly; thin or poor-quality histories may reduce reliability, and immediate scoring remained a need. At interview time, the team had received no reports of the anticipated challenges becoming production problems and was awaiting more user反馈.

### Source excerpt

In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Taniya Ghosh, Senior Manager of Software Engineering, whose team faced a brutal engineering contradiction: build predictive AI models that warn of escalating incidents before they had real customer incidents to learn from. Synthetic training data gave them [...] The post Building Predictive AI Models When Synthetic Data Is All You Have appeared first on Salesforce Engineering Blog.

## 6 AI Agent Capabilities to Evaluate Before Enterprise Deployment

DevFeed: [6 AI Agent Capabilities to Evaluate Before Enterprise Deployment](<https://devfeed.tech/articles/6-ai-agent-capabilities-to-evaluate-before-enterprise-deployment-130713.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/6-ai-agent-capabilities-to-evaluate-before-enterprise-deployment/>)

Author: Shelby Heinecke

Published: 2026-11-12T00:34:46Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Application Development](<https://devfeed.tech/topics/application-development.md>)

Tags: [agent-evaluation](<https://devfeed.tech/tags/agent-evaluation.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-capabilities](<https://devfeed.tech/tags/ai-agent-capabilities.md>), [ai-agent-evaluation](<https://devfeed.tech/tags/ai-agent-evaluation.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-benchmarks](<https://devfeed.tech/tags/ai-benchmarks.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-deployment](<https://devfeed.tech/tags/enterprise-deployment.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>)

### AI overview

EGI-Bench evaluates enterprise LLMs across six dimensions: task outcomes, tool actioning, planning, grounding, safety, and engineering. Salesforce's framework maps eight benchmarks into more than 20 subdomains and 1,500 test tasks, normalizes their different metrics, and combines them into six subscores and a weighted global score. Practitioners can change the weights to fit their priorities and choose deep mode for full evaluation or quick mode for a faster directional signal. Tests of 14 models found no single model led across all dimensions, planning scores were relatively low, and several lower-cost models were competitive. The text presents EGI-Bench as a way to compare models against enterprise capabilities; it does not claim that evaluation guarantees production readiness.

### Source excerpt

In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Shelby Heinecke, Director of AI Research, whose team tackled a high-stakes problem: how do you know an AI agent is truly ready for the enterprise before production exposes what your benchmarks missed? Getting the answer right is [...] The post 6 AI Agent Capabilities to Evaluate Before Enterprise Deployment appeared first on Salesforce Engineering Blog.

## How Salesforce Scaled Engineering AI Adoption Without Stifling Innovation

DevFeed: [How Salesforce Scaled Engineering AI Adoption Without Stifling Innovation](<https://devfeed.tech/articles/how-salesforce-scaled-engineering-ai-adoption-without-stifling-innovation-129311.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/how-salesforce-scaled-engineering-ai-adoption-without-stifling-innovation/>)

Author: Paul Constantinides

Published: 2026-11-10T19:17:30Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>), [Developer Enablement](<https://devfeed.tech/topics/developer-enablement.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [but](<https://devfeed.tech/tags/but.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [delivery](<https://devfeed.tech/tags/delivery.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [first](<https://devfeed.tech/tags/first.md>), [hyperforce](<https://devfeed.tech/tags/hyperforce.md>), [initiative](<https://devfeed.tech/tags/initiative.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [little](<https://devfeed.tech/tags/little.md>), [platform](<https://devfeed.tech/tags/platform.md>), [practices](<https://devfeed.tech/tags/practices.md>), [resources](<https://devfeed.tech/tags/resources.md>), [room](<https://devfeed.tech/tags/room.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [salesforce](<https://devfeed.tech/tags/salesforce.md>), [scaling](<https://devfeed.tech/tags/scaling.md>)

### AI overview

Salesforce's Hyperforce Runtime Platform scaled AI across roughly 500 engineers by pairing shared distribution and governance with team ownership and freedom to experiment. A Steering Committee set guidance and quality standards; scrum teams volunteered solutions to existing pain points and owned delivery and support, while AI Champions connected teams with committee decisions and shared new capabilities. The HRPDX Claude Code plugin distributed common instructions and skills, with session-start hooks handling updates; teams could extend it or keep solutions local. SDLC and DORA metrics, including pull-request-based lead time, helped teams choose where to focus and assess results. The excerpt reports adoption near 100% in the first three months, a 26% throughput gain, 32% better inner-loop efficiency, cycle time falling from 22 to 11 days, and sprint forecast ratio rising from 66% to 90%, while maintainability remained 6.04. Plugin adoption reached 97%, while uptake differed by capability: Prizm reached 95% and shared Claude instructions lagged. Increased coding output also lengthened review cycles, prompting team-specific review skills and work on testing and deployment bottlene�.

### Source excerpt

By Paul Constantinides, Anubhav Dhoot and Jackie Chambers de Freitas Salesforce's Hyperforce Runtime Platform (HRP) engineers were already experimenting with AI. But promising capabilities remained scattered across teams, overlapping efforts competed for limited resources, and tight delivery commitments left little room for another initiative. Scaling AI adoption demanded shared practices; preserving innovation demanded team freedom. [...] The post How Salesforce Scaled Engineering AI Adoption Without Stifling Innovation appeared first on Salesforce Engineering Blog.

## Using AI to Build AI: How Agentforce Engineers Scale Automation Without Sacrificing Reliability

DevFeed: [Using AI to Build AI: How Agentforce Engineers Scale Automation Without Sacrificing Reliability](<https://devfeed.tech/articles/using-ai-to-build-ai-how-agentforce-engineers-scale-automation-without-sacrificing-reliability-126488.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/using-ai-to-build-ai-how-agentforce-engineers-scale-automation-without-sacrificing-reliability/>)

Author: Fereydoon Vafaei

Published: 2026-11-09T19:02:12Z

Content type: news

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Code quality](<https://devfeed.tech/topics/code-quality.md>), [reliable codebases](<https://devfeed.tech/topics/reliable-codebases.md>)

Tags: [agentforce](<https://devfeed.tech/tags/agentforce.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [atlas](<https://devfeed.tech/tags/atlas.md>), [automation](<https://devfeed.tech/tags/automation.md>), [brain](<https://devfeed.tech/tags/brain.md>), [build](<https://devfeed.tech/tags/build.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [driving](<https://devfeed.tech/tags/driving.md>), [engine](<https://devfeed.tech/tags/engine.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [help](<https://devfeed.tech/tags/help.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [q-a](<https://devfeed.tech/tags/q-a.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [scale](<https://devfeed.tech/tags/scale.md>), [using](<https://devfeed.tech/tags/using.md>)

### AI overview

Salesforce's Agentforce team reports reducing typical Atlas Reasoning Engine bug resolution from two to four weeks to one or two days, while weekly availability reports reached 100% during the observed period. To support this, the team links incidents, fixes, code, Slack discussions, and bridge notes in a semantic knowledge base that removes outdated material. It evaluates AI work through scenario tests, replay, mutation testing, and checks of the full reasoning trajectory; different models judge work rather than judging their own, with engineers overseeing results. Agents can design, implement, review, and deploy changes to non-production environments, but require explicit human approval to merge to main or deploy to production. The team bases autonomy on verifiability, reversibility, available context, detectable failures, and risk. Reported code-review capacity is about 10 automated reviews at once; retrieval is measured by precision and recall. The excerpt says improvements vary by workflow.

### Source excerpt

In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Fereydoon Vafaei, a Principal Software Engineer on the Agentforce team, who faced a formidable challenge: using AI engineering automation to help build and maintain the Atlas Reasoning Engine, the brain of Agentforce, without allowing unreliable AI-generated work [...] The post Using AI to Build AI: How Agentforce Engineers Scale Automation Without Sacrificing Reliability appeared first on Salesforce Engineering Blog.

## Apache Spark Resource Optimization: Lessons From Eight Million Jobs a Day

DevFeed: [Apache Spark Resource Optimization: Lessons From Eight Million Jobs a Day](<https://devfeed.tech/articles/apache-spark-resource-optimization-lessons-from-eight-million-jobs-a-day-77355.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/apache-spark-resource-optimization-lessons-from-eight-million-jobs-a-day/>)

Author: Scott Nyberg

Published: 2026-10-08T15:15:37Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Apache Spark](<https://devfeed.tech/topics/spark.md>), [performance-optimization](<https://devfeed.tech/topics/performance-optimization.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>), [backpressure](<https://devfeed.tech/topics/backpressure.md>)

Tags: [apache-spark](<https://devfeed.tech/tags/apache-spark.md>), [concurrency](<https://devfeed.tech/tags/concurrency.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cpu-utilization](<https://devfeed.tech/tags/cpu-utilization.md>), [data](<https://devfeed.tech/tags/data.md>), [etcd](<https://devfeed.tech/tags/etcd.md>)

### AI overview

Salesforce's Data 360 team describes a telemetry and analysis workflow for identifying inefficient Apache Spark resource allocations across a high volume of daily executions. It used a shared submission gateway to collect execution metrics without application code changes, then validated targeted executor changes in production while monitoring cost, performance, reliability, and platform pressure. Targeted workloads showed a 31% reduction in weekly compute-cost run rate in matched four-week before-and-after windows; the authors note this was not a controlled experiment.

### Source excerpt

By Siddharth Sharma, Suvhrajit Basak, Kusum Dhalia, and Nabeel Qaiser. Your compute bill keeps climbing, and your Spark workloads keep succeeding. Successful execution tells you the configuration worked. It does not tell you how much of the allocated capacity the workload actually needed. Cutting CPU, memory, or executors without that evidence can turn potential savings [...] The post Apache Spark Resource Optimization: Lessons From Eight Million Jobs a Day appeared first on Salesforce Engineering Blog.

## AI Agents Need Memory: Building Persistent Memory for Agentforce

DevFeed: [AI Agents Need Memory: Building Persistent Memory for Agentforce](<https://devfeed.tech/articles/ai-agents-need-memory-building-persistent-memory-for-agentforce-65035.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/ai-agents-need-memory-building-persistent-memory-for-agentforce/>)

Author: Scott Nyberg

Published: 2026-10-05T18:04:20Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [sessions](<https://devfeed.tech/topics/sessions.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [rachels-ramblings](<https://devfeed.tech/topics/rachels-ramblings.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [architect](<https://devfeed.tech/tags/architect.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [context-management](<https://devfeed.tech/tags/context-management.md>), [customer-value](<https://devfeed.tech/tags/customer-value.md>), [developer](<https://devfeed.tech/tags/developer.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [memory](<https://devfeed.tech/tags/memory.md>), [persistent-memory](<https://devfeed.tech/tags/persistent-memory.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

In a Salesforce Engineering Q&A, the Agentforce Memory team describes how it built persistent memory for enterprise AI agents. The system evolved from using conversation history and user profiles to semantic retrieval, then moved into the platform so administrators could enable it through a simple context.memory configuration. The team discusses limiting context and latency with pre-orchestration keyword search, as well as user controls for reviewing and managing stored memories.

### Source excerpt

By Roopang Chauhan, Sundar Vedula, Peng-Wen Chen, and Nikhil Bojja. In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Roopang Chauhan, a software engineering architect on the Agentforce team, who helped architect Agentforce Memory, a capability designed to eliminate one of enterprise AI's biggest limitations: stateless [...] The post AI Agents Need Memory: Building Persistent Memory for Agentforce appeared first on Salesforce Engineering Blog.

## How Deterministic Controls Turn AI Output Into Reliable Prompt Templates

DevFeed: [How Deterministic Controls Turn AI Output Into Reliable Prompt Templates](<https://devfeed.tech/articles/how-deterministic-controls-turn-ai-output-into-reliable-prompt-templates-63443.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/how-deterministic-controls-turn-ai-output-into-reliable-prompt-templates/>)

Author: Scott Nyberg

Published: 2026-09-30T13:38:41Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [prompt](<https://devfeed.tech/topics/prompt.md>), [Code Modularity](<https://devfeed.tech/topics/code-modularity.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [api](<https://devfeed.tech/tags/api.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [software-engineer](<https://devfeed.tech/tags/software-engineer.md>)

### AI overview

Salesforce engineers describe Assistive Authoring, a workflow that turns natural-language requests into grounded prompt templates using Agent Graph, specialized agents, and backend tools. Deterministic routing, validated data discovery, server-side ID mapping, structured output checks, and an editor review gate constrain the LLM; the agent proposes drafts but cannot save or execute them.

### Source excerpt

By Vaibhav Raizada, Kumar Kasimala, and Ashish Gite. In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Vaibhav Raizada, a senior software engineer at Salesforce, whose team faced a high-stakes AI engineering contradiction while building Assistive Authoring for Salesforce Prompt Builder: transforming open-ended instructions into complete, [...] The post How Deterministic Controls Turn AI Output Into Reliable Prompt Templates appeared first on Salesforce Engineering Blog.

## Engineering Multi-Agent AI Teams That Build and Test Themselves

DevFeed: [Engineering Multi-Agent AI Teams That Build and Test Themselves](<https://devfeed.tech/articles/engineering-multi-agent-ai-teams-that-build-and-test-themselves-61257.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/engineering-multi-agent-ai-teams-that-build-and-test-themselves/>)

Author: Scott Nyberg

Published: 2026-09-28T18:53:47Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [multi-agent-ai](<https://devfeed.tech/tags/multi-agent-ai.md>), [self-healing](<https://devfeed.tech/tags/self-healing.md>), [verify](<https://devfeed.tech/tags/verify.md>)

### AI overview

Salesforce's Agent Designer automates the creation and testing of multi-agent AI teams. Specialized agents analyze architecture, failure modes, and compliance, while an orchestrator coordinates file creation, verification, testing, and bounded repairs but cannot write agent files itself. The workflow reduced the reported process from two to four hours to approximately 15 to 30 minutes.

### Source excerpt

By Sohini Arya and Manish Kumar Jha. In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Sohini Arya, AI Delivery Lead for Marketing Cloud, whose team pursued an audacious goal: build AI agents that could design, verify, test, and repair teams of other agents, even though [...] The post Engineering Multi-Agent AI Teams That Build and Test Themselves appeared first on Salesforce Engineering Blog.

## How Intelligent Load Shedding Prevents Cascading Failures in Tier-0 Systems

DevFeed: [How Intelligent Load Shedding Prevents Cascading Failures in Tier-0 Systems](<https://devfeed.tech/articles/how-intelligent-load-shedding-prevents-cascading-failures-in-tier-0-systems-59460.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/how-intelligent-load-shedding-prevents-cascading-failures-in-tier-0-systems/>)

Author: Scott Nyberg

Published: 2026-09-24T16:56:36Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [systems](<https://devfeed.tech/topics/systems.md>), [Authentication](<https://devfeed.tech/topics/authentication.md>), [Availability](<https://devfeed.tech/topics/availability.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [retry](<https://devfeed.tech/topics/retry.md>), [Automation](<https://devfeed.tech/topics/automation.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [automation](<https://devfeed.tech/tags/automation.md>), [availability](<https://devfeed.tech/tags/availability.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [identity](<https://devfeed.tech/tags/identity.md>), [outage](<https://devfeed.tech/tags/outage.md>), [platform](<https://devfeed.tech/tags/platform.md>), [protection](<https://devfeed.tech/tags/protection.md>), [queuing](<https://devfeed.tech/tags/queuing.md>), [rate-limiting](<https://devfeed.tech/tags/rate-limiting.md>), [regions](<https://devfeed.tech/tags/regions.md>), [retries](<https://devfeed.tech/tags/retries.md>), [service](<https://devfeed.tech/tags/service.md>), [services](<https://devfeed.tech/tags/services.md>), [systems](<https://devfeed.tech/tags/systems.md>), [traffic](<https://devfeed.tech/tags/traffic.md>), [upstream](<https://devfeed.tech/tags/upstream.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

A Salesforce Engineering Q&A explains how the Cloud Atlas team protects a globally distributed identity data store from cascading failures. It describes intelligent load shedding, distributed rate limiting, and coordinator-free quota management used to isolate traffic spikes, protect tenants, and maintain high availability for authentication.

### Source excerpt

By Ramya Subramani and Prateek Vats In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Ramya Subramani, Vice President of Engineering. Ramya leads the Cloud Atlas team, which operates the globally distributed identity data store behind a large portion of Salesforce authentication. Every login and token [...] The post How Intelligent Load Shedding Prevents Cascading Failures in Tier-0 Systems appeared first on Salesforce Engineering Blog.

## AI Agent Observability: Making Silent Production Failures Visible and Actionable

DevFeed: [AI Agent Observability: Making Silent Production Failures Visible and Actionable](<https://devfeed.tech/articles/ai-agent-observability-making-silent-production-failures-visible-and-actionable-58115.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/ai-agent-observability-making-silent-production-failures-visible-and-actionable/>)

Author: Scott Nyberg

Published: 2026-09-22T18:05:16Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Availability](<https://devfeed.tech/topics/availability.md>), [incident](<https://devfeed.tech/topics/incident.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-observability](<https://devfeed.tech/tags/ai-agent-observability.md>), [alerting](<https://devfeed.tech/tags/alerting.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [availability](<https://devfeed.tech/tags/availability.md>), [incident](<https://devfeed.tech/tags/incident.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-gateway](<https://devfeed.tech/tags/llm-gateway.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [observability](<https://devfeed.tech/tags/observability.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

A Salesforce engineering Q&A explains Agentforce Health Monitoring, a system for detecting silent production failures in AI agents. It uses availability, error, response, engagement, and latency metrics with alerting and session context to help agent builders and operations managers investigate incidents.

### Source excerpt

By Archana Kumari, Yushu Yao, and Priya Lal. In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Archana Kumari, Director of Software Engineering, whose team built Agentforce Health Monitoring (AHM). AHM is designed to help agent builders and operations managers detect production-agent availability problems, investigate incidents, [...] The post AI Agent Observability: Making Silent Production Failures Visible and Actionable appeared first on Salesforce Engineering Blog.

## How Data 360 Builds Trusted Context: The Enduring Layer for Enterprise AI

DevFeed: [How Data 360 Builds Trusted Context: The Enduring Layer for Enterprise AI](<https://devfeed.tech/articles/how-data-360-builds-trusted-context-the-enduring-layer-for-enterprise-ai-52423.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/how-data-360-builds-trusted-context-the-enduring-layer-for-enterprise-ai/>)

Author: Scott Nyberg

Published: 2026-09-16T17:23:42Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [context](<https://devfeed.tech/topics/context.md>), [data-platforms](<https://devfeed.tech/topics/data-platforms.md>), [data](<https://devfeed.tech/topics/data.md>), [distributed-systems](<https://devfeed.tech/topics/distributed-systems.md>), [databricks](<https://devfeed.tech/topics/databricks.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [context](<https://devfeed.tech/tags/context.md>), [data](<https://devfeed.tech/tags/data.md>), [data-platforms](<https://devfeed.tech/tags/data-platforms.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [distributed-systems](<https://devfeed.tech/tags/distributed-systems.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [snowflake](<https://devfeed.tech/tags/snowflake.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

Salesforce describes Data 360 as a shared runtime foundation for compiling current, relevant, and authorized enterprise evidence into trusted context for humans, applications, and AI agents. The approach combines ingestion and Zero Copy connections across structured and unstructured data, knowledge graphs, streaming signals, and external platforms while applying access, masking, residency, consent, freshness, latency, token, and cost controls.

### Source excerpt

By Raveendrnathan Loganathan and Tobias Muehlbauer. How do you compile the smallest sufficient body of current, relevant, and authorized evidence for every agent turn but without loading the entire enterprise data estate into every prompt? That is the context problem at the center of enterprise AI. Putting everything into every prompt consumes tokens, increases latency [...] The post How Data 360 Builds Trusted Context: The Enduring Layer for Enterprise AI appeared first on Salesforce Engineering Blog.

## How AI Agents Get Trusted Customer Context with Data 360 Data Graphs

DevFeed: [How AI Agents Get Trusted Customer Context with Data 360 Data Graphs](<https://devfeed.tech/articles/how-ai-agents-get-trusted-customer-context-with-data-360-data-graphs-52421.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/how-ai-agents-get-trusted-customer-context-with-data-360-data-graphs/>)

Author: Scott Nyberg

Published: 2026-09-14T19:32:39Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [data](<https://devfeed.tech/topics/data.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [id](<https://devfeed.tech/topics/id.md>), [Back end](<https://devfeed.tech/topics/backend.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [business-logic](<https://devfeed.tech/tags/business-logic.md>), [context](<https://devfeed.tech/tags/context.md>), [customer](<https://devfeed.tech/tags/customer.md>), [data](<https://devfeed.tech/tags/data.md>), [identity](<https://devfeed.tech/tags/identity.md>), [many-to-many](<https://devfeed.tech/tags/many-to-many.md>), [performance](<https://devfeed.tech/tags/performance.md>), [relationships](<https://devfeed.tech/tags/relationships.md>)

### AI overview

A Salesforce AI Engineering team uses Data 360 data graphs to unify fragmented customer, product, contract, entitlement, and case data into trusted context for Agentforce. The approach resolves identities, manages relationships, and lets agents retrieve personalized context at runtime, with a stated P50 performance below 200 milliseconds.

### Source excerpt

In our Engineering Energizers Q&A series, we explore the engineering minds behind some of Salesforce's most complex technical challenges. Today, we spotlight Alex Smith, Senior Director of AI Engineering, whose team uses Data 360 data graphs to give Agentforce something every personalized interaction depends on: trusted customer context. Their goal is to turn decades of [...] The post How AI Agents Get Trusted Customer Context with Data 360 Data Graphs appeared first on Salesforce Engineering Blog.

## Engineering Real-Time Mobile Personalization Across iOS, Android, React Native, and Flutter

DevFeed: [Engineering Real-Time Mobile Personalization Across iOS, Android, React Native, and Flutter](<https://devfeed.tech/articles/engineering-real-time-mobile-personalization-across-ios-android-react-native-and-flutter-52417.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/engineering-real-time-mobile-personalization-across-ios-android-react-native-and-flutter/>)

Author: Scott Nyberg

Published: 2026-09-11T20:36:38Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Mobile](<https://devfeed.tech/topics/mobile.md>), [personalization](<https://devfeed.tech/topics/personalization.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Android](<https://devfeed.tech/topics/android.md>), [cross-platform](<https://devfeed.tech/topics/cross-platform.md>), [Flutter](<https://devfeed.tech/topics/flutter.md>), [iOS](<https://devfeed.tech/topics/ios.md>), [React Native](<https://devfeed.tech/topics/react-native.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [data](<https://devfeed.tech/topics/data.md>), [Deployment](<https://devfeed.tech/topics/deployment.md>), [Web Accessibility (a11y)](<https://devfeed.tech/topics/web-accessibility.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [android](<https://devfeed.tech/tags/android.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [cross-platform](<https://devfeed.tech/tags/cross-platform.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [flutter](<https://devfeed.tech/tags/flutter.md>), [ios](<https://devfeed.tech/tags/ios.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [react](<https://devfeed.tech/tags/react.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

A Salesforce engineering Q&A explains how a team built real-time mobile personalization across iOS, Android, React Native, and Flutter. It addresses technology fragmentation, cross-channel identity, data integrity, constrained rendering, privacy and consent, deployment cycles, and marketer autonomy.

### Source excerpt

In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Sneha Singla, a director of software engineering, whose team confronted a brutal engineering contradiction: making one real-time mobile personalization architecture work across four fundamentally different technology stacks without breaking native layouts, corrupting customer identities, exposing unnecessary profile [...] The post Engineering Real-Time Mobile Personalization Across iOS, Android, React Native, and Flutter appeared first on Salesforce Engineering Blog.

## Enterprise AI Accuracy: Building a More Trustworthy RAG Application

DevFeed: [Enterprise AI Accuracy: Building a More Trustworthy RAG Application](<https://devfeed.tech/articles/enterprise-ai-accuracy-building-a-more-trustworthy-rag-application-52418.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/enterprise-ai-accuracy-building-a-more-trustworthy-rag-application/>)

Author: Scott Nyberg

Published: 2026-09-09T22:30:06Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Parsing](<https://devfeed.tech/topics/parsing.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [parsing](<https://devfeed.tech/tags/parsing.md>), [product](<https://devfeed.tech/tags/product.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

This engineering article examines why RAG applications can perform well on clean benchmarks yet fail on complex enterprise documents. It traces lost meaning across parsing, chunking, enrichment, embedding, retrieval, and answer generation, and discusses improving accuracy by inspecting the context pipeline rather than blaming the language model alone.

### Source excerpt

By Sivakumar Shanmugam, Kartik Muktinutalapati, and Palani Ramanathan. Your retrieval-augmented generation (RAG) application passes its benchmarks, reaches production, and begins confidently giving customers the wrong answers. Financial tables lose their headers at page breaks. Coverage matrices become garbled. Retrieval selects an article that appears relevant but belongs to the wrong product. Meanwhile, the clean, text-based [...] The post Enterprise AI Accuracy: Building a More Trustworthy RAG Application appeared first on Salesforce Engineering Blog.

## How Metadata and Runtime Telemetry Reveal Which Enterprise System Problems to Fix First

DevFeed: [How Metadata and Runtime Telemetry Reveal Which Enterprise System Problems to Fix First](<https://devfeed.tech/articles/how-metadata-and-runtime-telemetry-reveal-which-enterprise-system-problems-to-fix-first-52424.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/how-metadata-and-runtime-telemetry-reveal-which-enterprise-system-problems-to-fix-first/>)

Author: Scott Nyberg

Published: 2026-09-08T21:39:21Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Product Management](<https://devfeed.tech/topics/product-management.md>), [Transactions](<https://devfeed.tech/topics/transactions.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automation](<https://devfeed.tech/tags/automation.md>), [data](<https://devfeed.tech/tags/data.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [management](<https://devfeed.tech/tags/management.md>), [platform](<https://devfeed.tech/tags/platform.md>), [runtime-telemetry](<https://devfeed.tech/tags/runtime-telemetry.md>), [scale](<https://devfeed.tech/tags/scale.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [transactions](<https://devfeed.tech/tags/transactions.md>)

### AI overview

A Salesforce engineering Q&A explains how the team combines configuration metadata with runtime telemetry to monitor complex enterprise orgs, prioritize high-impact remediation, and evolve static health reports into a context-aware in-app experience.

### Source excerpt

By Karishma Lalwani, Anand Vardhan, and Sanjeevani Bhardwaj. In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Karishma Lalwani, Vice President of Product Management and a Certified Technical Architect at Salesforce, whose team faced a formidable engineering problem: monitoring enterprise orgs handling billions of daily transactions [...] The post How Metadata and Runtime Telemetry Reveal Which Enterprise System Problems to Fix First appeared first on Salesforce Engineering Blog.

## How Agentforce Achieves 100% Deterministic Rendering for AI Agent UX

DevFeed: [How Agentforce Achieves 100% Deterministic Rendering for AI Agent UX](<https://devfeed.tech/articles/how-agentforce-achieves-100-deterministic-rendering-for-ai-agent-ux-52420.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/how-agentforce-achieves-100-deterministic-rendering-for-ai-agent-ux/>)

Author: Scott Nyberg

Published: 2026-09-03T19:18:50Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>), [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [JSON](<https://devfeed.tech/topics/json.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [json](<https://devfeed.tech/tags/json.md>), [llm](<https://devfeed.tech/tags/llm.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [product-management](<https://devfeed.tech/tags/product-management.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [system](<https://devfeed.tech/tags/system.md>), [ux](<https://devfeed.tech/tags/ux.md>)

### AI overview

A Salesforce Engineering Q&A explains how the Agentforce team separates stochastic LLM reasoning from deterministic presentation. Its Agentforce Connections layer uses rendering controls and orchestration to ensure critical forms, components, and compliance disclosures appear reliably across channels and headless experiences.

### Source excerpt

In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Abhi Rathna, Product Management Director for Agentforce, whose team tackled a fundamental engineering contradiction: how do you preserve the stochastic LLM reasoning that makes an AI agent intelligent while guaranteeing that specific outputs render correctly 100% of [...] The post How Agentforce Achieves 100% Deterministic Rendering for AI Agent UX appeared first on Salesforce Engineering Blog.

## Why AI Agents Get the Right Facts but the Wrong Answer--and How GraphRAG Helps

DevFeed: [Why AI Agents Get the Right Facts but the Wrong Answer--and How GraphRAG Helps](<https://devfeed.tech/articles/why-ai-agents-get-the-right-facts-but-the-wrong-answer-and-how-graphrag-helps-52425.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/why-ai-agents-get-the-right-facts-but-the-wrong-answer-and-how-graphrag-helps/>)

Author: Scott Nyberg

Published: 2026-08-31T17:41:11Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

The article explains why retrieval-augmented generation can produce incorrect decisions from individually accurate facts when it fails to retrieve connected context. Using Salesforce Agentforce as an example, it describes how GraphRAG and knowledge graphs can connect product, policy, and customer data to identify conditional exceptions.

### Source excerpt

By Sivakumar Shanmugam and Indrojit Deb.An AI agent rejects a valid customer return. You check its citation: the policy really does say 90 days. You check the purchase: it falls outside that window. Both facts are correct, but the customer qualifies for an exception the system never retrieved. Checking the evidence has made the wrong [...] The post Why AI Agents Get the Right Facts but the Wrong Answer--and How GraphRAG Helps appeared first on Salesforce Engineering Blog.

## How AI-Powered Attacks Led Salesforce to Reinvent Hyperscale DDoS Defense

DevFeed: [How AI-Powered Attacks Led Salesforce to Reinvent Hyperscale DDoS Defense](<https://devfeed.tech/articles/how-ai-powered-attacks-led-salesforce-to-reinvent-hyperscale-ddos-defense-52422.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/how-ai-powered-attacks-led-salesforce-to-reinvent-hyperscale-ddos-defense/>)

Author: Scott Nyberg

Published: 2026-08-28T16:49:20Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [DDoS](<https://devfeed.tech/topics/ddos.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [cloud-infrastructure](<https://devfeed.tech/topics/cloud-infrastructure.md>), [Multi-tenancy](<https://devfeed.tech/topics/multi-tenancy.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Availability](<https://devfeed.tech/topics/availability.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [availability](<https://devfeed.tech/tags/availability.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [ddos](<https://devfeed.tech/tags/ddos.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [inference](<https://devfeed.tech/tags/inference.md>), [scale](<https://devfeed.tech/tags/scale.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

A Salesforce engineering Q&A describes DREAM, an AI-powered DDoS mitigation platform for the company's global, shared cloud infrastructure. The platform uses AI-driven inference and automated execution to respond to machine-speed attacks, reducing time to first mitigation by 5x while protecting millions of customer organizations and maintaining high availability.

### Source excerpt

In our Engineering Energizers Q&A series, we spotlight the engineering leaders driving innovation across Salesforce. Today, we meet Herman Kwong, EVP of Software Engineering, whose team developed DREAM (DDoS Response and Mitigation), an AI-powered DDoS mitigation platform protecting Salesforce's global cloud infrastructure against machine-speed attacks. DREAM reduced time to first mitigation by 5x across a [...] The post How AI-Powered Attacks Led Salesforce to Reinvent Hyperscale DDoS Defense appeared first on Salesforce Engineering Blog.

## From Prediction to Action: How to Turn AI Outputs Into Decisions

DevFeed: [From Prediction to Action: How to Turn AI Outputs Into Decisions](<https://devfeed.tech/articles/from-prediction-to-action-how-to-turn-ai-outputs-into-decisions-52419.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/from-prediction-to-action-how-to-turn-ai-outputs-into-decisions/>)

Author: Scott Nyberg

Published: 2026-08-24T23:42:02Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [Users](<https://devfeed.tech/topics/users.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [product](<https://devfeed.tech/tags/product.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

The article argues that accurate machine-learning predictions, alerts, scores, and recommendations are not useful to users unless they provide context and support a concrete decision. Drawing on Salesforce's experience with many dashboards and applications, it presents model outputs as signals that must be translated into actionable guidance.

### Source excerpt

By Ali Nahvi, Akshit Behera, Yvonne Fan, and Melissa Ramey. Your models are accurate. Your pipelines are healthy. Your dashboards are working. And your system is still failing its users. Imagine thousands of dashboards and more than 20 applications continuously producing machine learning predictions, alerts, scores, and recommendations. Nothing is technically broken. Yet the people [...] The post From Prediction to Action: How to Turn AI Outputs Into Decisions appeared first on Salesforce Engineering Blog.

## Why AI-Generated Code Is Easy but Engineering Trust Is Hard

DevFeed: [Why AI-Generated Code Is Easy but Engineering Trust Is Hard](<https://devfeed.tech/articles/why-ai-generated-code-is-easy-but-engineering-trust-is-hard-52426.md>)

Original publisher: [Read original article](<https://engineering.salesforce.com/why-ai-generated-code-is-easy-but-engineering-trust-is-hard/>)

Author: Scott Nyberg

Published: 2026-08-20T21:56:01Z

Content type: article

Language: en

Sources: [Salesforce](<https://devfeed.tech/sources/salesforce-engineering-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [trust](<https://devfeed.tech/topics/trust.md>), [Code generation](<https://devfeed.tech/topics/code-generation.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [test](<https://devfeed.tech/topics/test.md>), [Boilerplate](<https://devfeed.tech/topics/boilerplate.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agent](<https://devfeed.tech/tags/ai-coding-agent.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [human-review](<https://devfeed.tech/tags/human-review.md>), [plan](<https://devfeed.tech/tags/plan.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>), [technical-debt](<https://devfeed.tech/tags/technical-debt.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

An engineering article examines why AI-generated code can pass builds, tests, and code review while still implementing an ambiguous requirement incorrectly. It argues that engineering trust must be established earlier by making assumptions, success measures, unresolved questions, and failure conditions explicit in a specification before implementation begins.

### Source excerpt

Imagine an AI coding agent generating a large pull request filled with AI-generated code. Everything looks exactly as it should: Later, your team discovers the agent quietly misinterpreted an ambiguous requirement near the beginning of the implementation. Every decision that followed was internally consistent. The tests validated the implementation. The reviewer approved the diff. The [...] The post Why AI-Generated Code Is Easy but Engineering Trust Is Hard appeared first on Salesforce Engineering Blog.