Salesforce Data 360 Data Graphs give AI agents a prepared, structured view of related customer information to retrieve when needed, instead of requiring the agent to join fragmented records during every interaction. The approach can make customer-specific context easier to supply, but it depends on deliberate graph design, identity handling, permissions, and the agent’s retrieval path.
How do AI agents get trusted customer context?
An AI agent does not automatically know which customer it is serving, what that customer owns, or which entitlements, cases, and interactions matter. Those facts may sit in different systems and use different identifiers. Salesforce’s Help Agent example uses Data Graphs to bring relevant records together and apply joins, aggregation, relationship management, and business logic before the agent asks for context.
As an Amazon Associate I earn from qualifying purchases.
At runtime, the agent can provide an identifier such as a tenant ID and retrieve a prepared context object. This differs from having the agent issue several queries, map identifiers, and join records for each request. Salesforce describes the graph as a cohesive data product for agent use, not as a substitute for deciding which data the agent is permitted to access. Salesforce AI Engineering’s account of its Help Agent architecture explains this design.
What is a Data Graph in Salesforce Data 360?
A Data Graph is a structured, flattened representation of related data that can be retrieved as a single context object. Salesforce Trailhead describes a graph record as a JSON view of related information: relationships remain represented in the JSON even though the data is presented in a form an agent can consume. A graph can combine CRM data with external lake data through Zero Copy, according to Salesforce’s documented example. Trailhead’s explanation of trusted agents and Data Cloud describes the graph and its role in grounding.
#1 Best Overall
- Built for Local AI Development: AMD Ryzen AI Halo is designed for local AI development and inference, featuring 128GB unified memory and support for up to 200B parameter models to build and run intensive AI workloads locally.
- 128GB Unified Memory: Features 128GB LPDDR5x unified memory at 8000 MT/s with 256 GB/s memory bandwidth, providing a shared memory pool across the CPU, GPU, and NPU to support larger AI models.
- AMD Ryzen AI Max+ 395 Processor: Features 16 cores, 32 threads, and Zen 5 architecture, paired with AMD Radeon 8060S integrated graphics featuring 40 RDNA 3.5 compute units and an AMD XDNA 2 NPU with up to 50 TOPS.
- Linux AI Developer Platform: Purpose-built for Linux-based AI development with full AMD ROCm software support and preloaded tools, models, and workflows optimized for local AI development.
- Compact, Connected Design: Includes a 2TB M.2 SSD, 10GbE LAN, Wi-Fi 7, Bluetooth 5.4, USB-C connectivity, and HDMI 2.1b.
Salesforce rebranded Data Cloud as Data 360 on October 14, 2025. Some product surfaces and older documentation may still use “Data Cloud,” so readers may encounter both names. Salesforce Trailhead’s overview of Data Cloud’s role in Agentforce notes the naming transition.
How does an agent know which customer or tenant it is helping?
The agent needs a reliable identifier from its interaction or calling system, and the data model must connect that identifier to the intended customer records. In Salesforce’s Help Agent example, a tenant ID is used to retrieve related context from a graph whose joins and mappings have been prepared in advance.
Correct identity matching and access isolation are separate design problems. Salesforce says its example keeps the broad identity graph in one data space and exposes a filtered customer-success view in another data space for particular agent-context and outreach use cases. The filtered view limits what that use case receives; the existence of a Data Graph alone does not automatically authorize access or guarantee tenant isolation. Organizations still need to design and enforce permissions and data boundaries for their own architecture. Salesforce Engineering’s Help Agent description explains this partitioned approach.
How do Data Graphs ground Agentforce prompts?
Salesforce Prompt Builder can reference an active Data Graph as a grounding resource. During testing, graph data can be previewed in JSON; Salesforce says sensitive data is masked before it is sent to the LLM. The documented support conditions are specific, so check Salesforce Help for the target org’s current edition, permissions, and setup:
Rank #2
- EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 64GB pool, which is perfect for running LLMs such as Deepseek 32B, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 4% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
- Data Graphs are supported on DMOs associated with CRM data streams for Salesforce sObjects and custom objects.
- Prompt Builder supports whole graphs, not subgraphs.
- The DMO associated with the object input must be the graph root or connect to a Unified Profile DMO at the root.
- Supported editions and required permission sets are listed in Salesforce Help and can change.
These constraints affect how a graph must be modeled and connected to the prompt. Review Salesforce Help’s Prompt Builder grounding requirements before configuring a production agent.
Can a Data Graph give an agent real-time customer behavior?
Salesforce documents a specific real-time behavioral-context example using its Web Connector SDK. The SDK captures a session and passes an IndividualId to the agent; the agent queries a Data Graph, which returns a structured behavioral profile to context variables. The example groups catalog engagement, cart engagement, and agent engagement under an Individual entity. This is an implementation example, not evidence that every Data Graph is real-time by default. Salesforce Help’s context-aware agent guidance details the flow.
How should teams shape graphs for retrieval?
Graph design should start with the agent’s actual access patterns: which identifiers it receives, which questions it must answer, and which related records are needed to answer them. Salesforce Engineering says an oversized graph can hurt performance, while a graph that is too small may leave the agent needing joins at retrieval time. The team describes building indexes so retrieval can find relevant information rather than scan entire tables.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
- Map the agent’s questions and inputs. Identify the customer or tenant key available at runtime and the data needed to answer each supported request.
- Model the necessary relationships and business logic. Prepare joins and mappings in the graph rather than leaving every interaction to reconstruct them.
- Choose graph boundaries and data spaces deliberately. Include the context needed for the use case and expose filtered views where appropriate.
- Index for the retrieval path. Tune indexes and graph size against the agent’s access patterns, then validate the behavior and performance in the target environment.
Salesforce AI Engineering reports that its Help Agent context path had live-monitoring P50 performance below 200 milliseconds, compared with an earlier benchmark of about 400 milliseconds. These are Salesforce’s figures for that implementation; the account does not provide workload or methodology details, and the number is not a general Data 360 performance guarantee or platform SLA. The engineering account also attributes the team’s mission to “close the context gap for agents.”
Rank #3
- Intel Core Ultra 9 285 Processor: Newly developed cores deliver ultra-smooth and responsive gameplay. AI accelerators prepare users for the next era of gaming on an AI PC.
- Simplistic Design: Enjoy the latest generation of Windows 11 Home for your everyday needs. *MSI recommends Windows 11 Pro for business use.
- NVIDIA GeForce RTX 5070 Ti GPU
- Cool While Gaming: In conjunction with an RGB CPU Air Cooler, the Aegis RS features four system cooling fans; three in the front and one in the rear to pull in cool air and push heat out of the PC.
- Turn on the Bright Lights: With the built-in RGB lighting, take your gaming experience to the next level by pressing the MSI LED button to cycle through lighting options. Customize lighting even further with MSI Center software.
When is a Data Graph a better fit than an Agentforce Data Library?
The choice depends on whether the need is a quick-start document-retrieval setup or a more controlled, modeled context layer. Salesforce describes Agentforce Data Library as a preconfigured RAG solution that automatically sets up a vector data store, search index, and retriever. A deeper Data 360 implementation takes more setup but can support broader data sources, transformed and harmonized data, and more retrieval control.
| Approach | Setup and data reach | Freshness and retrieval | Context structure |
|---|---|---|---|
| Agentforce Data Library | Preconfigured quick-start; Salesforce documents one data source per library. | Salesforce’s comparison says it lacks real-time and Zero Copy capabilities. | Uses a vector store, search index, and retriever for RAG. |
| Data 360 with Data Graphs | Requires implementation work such as ingestion, modeling, identity resolution, and graph setup; can support broader sources, including the documented Zero Copy path. | Can support real-time retrieval in documented configurations; retrieval can be designed around the use case. | Returns related information in a structured JSON representation with relationships preserved. |
This is a distinction in the documented product approaches, not a claim that every deployment has identical capabilities. See Salesforce Trailhead’s comparison of Data Library and Data 360 approaches and its Agentforce and Data Cloud overview.
What does implementation require?
A Data Graph is most useful when an organization can identify the relevant source systems and identifiers, model the relationships the agent needs, and define permissions and boundaries for each use case. A fuller deployment may involve connecting sources, harmonizing data, resolving identities, designing graphs, configuring retrieval, and checking performance. That work offers more control than a quick-start library, but it also means teams must plan the data and security architecture rather than treating graph creation as a prompt-only change.
Salesforce describes Data 360 Data Graphs as a way to prepare customer context for retrieval. Whether that context is trustworthy in a particular deployment depends on the quality of identity mappings, the graph’s scope, its freshness, the applicable permissions, and the agent’s runtime inputs.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
