Data 360 does not fix RAG with one switch—the benchmark must become a diagnosis
Salesforce reports a jump from 62.5% to 92.5% on knowledge-base questions after changing parsing, indexing, chunks, retrieval depth and the generation prompt. The result matters, but it becomes a production decision only when a team identifies where its own documents fail.
Read article
One agent or many? A new map for multi-agent architectures
SOMA separates complex domains across specialist agents while preserving one conversational front door.
Flow testing evolves to validate outcomes, not just paths
Assertions and test suites help admins prove that automation produced the expected state before production.
OrbTrail
Latest
31 stories found
BusinessHow Salesforce pilots its own software before scaling
Thousands of employees use products in real situations to reveal friction, validate adoption and reduce surprises for customers.
BusinessSalesforce and Entre Ríos advance AI for government and SMBs
The agreement combines public-sector modernization, digital skills and productivity support for smaller businesses.
AgentforceRight-sized models cut cost and latency in Agentforce
Intent routing reserves larger models for hard tasks and uses lighter options for predictable work.
PlatformAgentforce helps admins investigate sharing configuration
Natural-language queries make it faster to discover who can see a record, why and which rules need review.
CareersThe next generation of builders blends curiosity, AI and storytelling
Early in a career, learning quickly, asking better questions and communicating decisions can matter as much as mastering tools.
BusinessAgentforce Commerce bets on intent-driven discovery
Agents connect discovery, catalog, inventory, orders and service to turn conversations into commercial action.