Skip to content

FAQ

SmartForge Nexes is the secure execution layer of SmartForge.
It connects SmartForge Cortex requests to approved enterprise systems, executes them in real time, and returns a single, trusted answer.


How is SmartForge Nexes different from traditional integrations?

Section titled “How is SmartForge Nexes different from traditional integrations?”

Traditional integrations rely on data replication (ETL) and point-to-point connections.

SmartForge Nexes is query-centric:

  • No data copying or syncing
  • Queries run directly on source systems
  • Results are merged in real time

This reduces latency, complexity, and maintenance.


Does SmartForge Nexes store or replicate data?

Section titled “Does SmartForge Nexes store or replicate data?”

No.
SmartForge Nexes does not store or duplicate data. It executes queries directly on source systems and returns results in real time.


How does SmartForge Nexes produce a single answer from multiple systems?

Section titled “How does SmartForge Nexes produce a single answer from multiple systems?”

It combines several steps:

  1. Runs federated queries across systems (ERP, WMS, TMS, etc.)
  2. Performs live aggregation of responses
  3. Applies on-the-fly transformations (filters, grouping, calculations)
  4. Uses business-defined reducer logic to select the final result

The outcome is a single, consistent answer.


SmartForge Cortex is the intelligent conversational interface of SmartForge that lets users interact with enterprise systems using natural language.

You can:

  • Retrieve live operational data
  • Run approved workflows
  • Ask follow-up questions
  • Generate charts and dashboards

How is SmartForge Cortex different from document-based chat (RAG)?

Section titled “How is SmartForge Cortex different from document-based chat (RAG)?”

SmartForge Cortex is API-centric, not document-based.

Feature Document Chat SmartForge Cortex
Data source Static documents Live systems
Accuracy Depends on documents System-verified data
Actions Not supported Supported (approved only)
Freshness Can be outdated Real-time

Can SmartForge Cortex trigger actions or workflows?

Section titled “Can SmartForge Cortex trigger actions or workflows?”

Yes—but only if:

  • The function is pre-approved
  • The user has the required permissions (RBAC)

No arbitrary or unsafe actions can be executed.


A function is an approved capability that SmartForge can execute, such as:

  • Fetching data (orders, inventory, shipments)
  • Running workflows
  • Calling APIs or system commands

Each function includes:

  • Implementation (code/script/API)
  • Metadata (inputs, outputs, description)

SmartForge Studio is the builder studio where teams create and manage functions.

It provides:

  • function definition (metadata + implementation)
  • Connections to enterprise systems
  • Evaluation tools (to test AI tool selection)
  • Governance via Git

How does SmartForge turn a question into a system action?

Section titled “How does SmartForge turn a question into a system action?”
  1. User asks a question in SmartForge Cortex
  2. LLM extracts intent + parameters
  3. A matching function is selected
  4. SmartForge Nexes validates permissions and inputs
  5. The function executes on target systems
  6. Results are returned in a user-friendly format

No.

  • The LLM only receives user query + metadata
  • All execution happens inside your environment
  • No raw business data is exposed externally

For analytics:

  • Only column names (and optional small samples) may be used
  • Full datasets remain internal

Security is built-in at multiple levels:

  • RBAC (role-based access control)
  • Approved functions only (no arbitrary execution)
  • Centralized validation and permissions
  • Secure API layer

Users can only access what they are authorized to see and run.


Can users see what happened behind the scenes?

Section titled “Can users see what happened behind the scenes?”

Yes (if enabled).

Users can:

  • View executed commands or API calls
  • Understand how their request was processed
  • Troubleshoot results

Can SmartForge Cortex handle follow-up questions?

Section titled “Can SmartForge Cortex handle follow-up questions?”

Yes.

SmartForge maintains session context, so users can:

  • Refine results
  • Ask incremental questions
  • Build on previous responses

Can SmartForge Cortex generate charts and dashboards?

Section titled “Can SmartForge Cortex generate charts and dashboards?”

Yes.

From any dataset, users can:

  • Create charts (pie, bar, line, stacked, etc.)
  • Generate dashboards automatically
  • Analyze trends without manual setup

What systems can SmartForge Nexes connect to?

Section titled “What systems can SmartForge Nexes connect to?”

Any system with an API, including:

  • WMS (e.g., Blue Yonder, Manhattan)
  • ERP (e.g., SAP)
  • CRM (e.g., Salesforce)
  • Data platforms (e.g., Snowflake)
  • Custom REST / SQL / proprietary systems

SmartForge Nexes supports secure tracking, including:

  • Who made the request
  • Which function was executed
  • Execution timing and run IDs
  • Masked parameters

Sensitive data is never logged or exposed.


Use it when:

  • Data is spread across multiple systems
  • Real-time answers are required
  • Actions must be secure and governed
  • A unified interface is needed

ForgeView is a capability publishing model for visual experiences. It allows organizations to create operational screens by composing existing intents into grids, charts, detail panels, and actions — without traditional application development.


How is ForgeView different from a screen builder or low-code platform?

Section titled “How is ForgeView different from a screen builder or low-code platform?”

ForgeView is not a screen builder or low-code platform. It is a capability publishing model. The visual experience emerges from capabilities that already exist as operationalized intents. No new integrations, APIs, or business logic are required.


Screen Forge is the visual screen editor within SmartForge Studio where users can create and edit operational screens. It allows you to map existing intents to visual constructs like grids, tabs, detail panels, and action buttons — all through configuration rather than coding.


Do I need to create new functions for ForgeView screens?

Section titled “Do I need to create new functions for ForgeView screens?”

No. ForgeView uses existing operationalized intents as its building blocks. If a capability already exists as an intent, it can be immediately consumed in a visual workspace without new development.


Can ForgeView screens use intents from different systems?

Section titled “Can ForgeView screens use intents from different systems?”

Yes. ForgeView is system-agnostic. An intent from SAP can be displayed alongside an intent from JD Edwards, Blue Yonder, or a custom application — all in the same screen. The underlying capability layer handles the orchestration.


What makes SmartForge + SmartForge Nexes unique?

Section titled “What makes SmartForge + SmartForge Nexes unique?”
  • No ETL or data duplication
  • Real-time, federated execution
  • API-driven (not document-based)
  • Built-in governance and security
  • Low-code extensibility via SmartForge Studio