The independent daily for Salesforce admins, developers and architects

Curated by Abhinav (opens in a new tab)

Carter, a shopper agent for B2C Commerce storefronts built on Agentforce (opens in a new tab)

You will learn how Carter is structured, with its four preconfigured subagents, page awareness and merchant controls over guided discovery, and what the Shopper Agent template gives you to start from.

Why read this

You will also see the customer results Salesforce reports, though they are vendor claims.

  1. Shopper asks in natural language
  2. Agentic Commerce Search reads the intent
  3. Carter routes to a subagent
  4. Answer grounded in the product catalog
How Carter handles a shopper request across its subagents

Salesforce introduces Carter, a shopper agent from Commerce Cloud that gives online shoppers a conversational interface in place of keyword search and category pages. The article argues that shoppers now expect the guided, context-aware help a good in-store sales associate gives, and that Carter is meant to provide it. It is available through B2C Commerce and can be reached from the search bar, the header icon, or FAQ widgets on product detail pages.

Carter is powered by Agentic Commerce Search, which interprets the intent behind a natural language request rather than matching keywords. Its answers are grounded in the merchant’s product catalog, and brands can add other knowledge sources through Data 360. Merchants control how Carter sells by choosing which follow-up questions are required or optional in guided discovery and which selling points it highlights when comparing products.

Getting started means using the Shopper Agent for B2C Commerce template in Agentforce, which comes with all the subagents and actions preconfigured. Product Expert handles browsing, search, recommendations, comparisons and product questions. Site FAQ covers policies such as shipping, returns and refunds. Cart manages products, variants, promotions and coupons. Order Confirmation confirms orders and recovers carts after failed or cancelled payments. Carter orchestrates these behind one chat, and because it is page-aware it can answer questions about the product or cart the shopper is currently viewing.

The article cites several retailers using Carter under their own brand names, including Cuisinart’s Compass, Hibbett AI and SharkNinja’s combined commerce and support interface. Hibbett reports going live in six weeks and handling 90% of core shopper journeys. These are vendor-supplied results. Carter is generally available now as an add-on for B2C Commerce customers and works in every language Agentforce supports.

Read the original at Salesforce Blog (opens in a new tab)

Worth reading?

Must-read

Restricting Shopper API traffic to Managed Runtime with eCDN rules (opens in a new tab)

You will learn how to lock SCAPI traffic to Managed Runtime with the SCAPI Identity Header, allow other integrations, harden SLAS, and rate limit AI crawlers using eCDN fields and rule expressions.

  1. Enable SCAPI Request Identification per instance
  2. Add a block rule for the instance's path
  3. Place the rule after the Salesforce allow rule
  4. Start in Log mode, then switch to Block
How to restrict Shopper API traffic to Managed Runtime, rolled out in stages

Bots increasingly call the B2C Commerce API directly, bypassing storefronts, and AI crawlers and shopping agents add search and LLM costs and skew analytics. The October 2026 release lets you manage the SCAPI zone in Business Manager and the CDN API, accept Shopper API traffic only from Managed Runtime through the new SCAPI Identity Header, and identify AI traffic on any eCDN zone with verified-bot fields. The SCAPI zone is provisioned automatically and shared across Development, Staging and Production, managed from Production. Some controls such as WAF managed rulesets, mTLS, TLS 1.3 settings and HSTS are not available.

To restrict traffic, enable the Managed Runtime SCAPI Request Identification feature per instance, then add a firewall rule that blocks Shopper API paths for that instance’s org-specific path segment, placed after the locked Salesforce allow rule. Start with Log, then switch to Block. Other integrations such as a custom BFF can be allowed with their own rules carrying a separate shared secret header that must stay server-side. For SLAS, Strict Client Auth requires a client secret header on login and authorize requests, though Composable Storefront and Storefront Next do not send it yet, so it should be enabled only for private clients called from your own server code. SLAS also throttles refresh-token exchanges to 3 per 60 seconds.

For AI traffic, the Known Bot and Verified Bot Category fields sort verified bots into 17 categories. The post recommends rate limiting AI Crawler and AI Search traffic on expensive endpoints such as product search rather than blocking it, with thresholds tuned from logs and Log mode run first. Spoofed or unverified automation needs behavioral detection from a bot management partner or Bot Management in front of eCDN.

Read the original at Salesforce Developers Blog (opens in a new tab)

Worth reading?

Must-read

B2C Commerce October 2026 release adds events GA and self-service unpairing (opens in a new tab)

You will learn what the October 2026 B2C Commerce release changes for integrations, environment setup and licensing, including the Event Framework going generally available and the removal of the Data 360 license requirement for the trusted connection.

Why read this

You will also see which agentic and developer tooling features arrived with it.

Before October 2026

  • Data 360 license needed
  • Admin support ticket to reset pairing
  • Sandbox type limits

October 2026

  • No Data 360 license needed
  • Self-service unpairing
  • Any Salesforce sandbox type
Trusted connection to a Salesforce org no longer requires a Data 360 license

The October 2026 release for B2C Commerce focuses on speed, automation and unified commerce. It adds Universal Commerce Protocol integration, which lets merchants turn on UCP-powered checkout on Google so shoppers can buy directly from surfaces such as the Gemini app and Google Search while the merchant stays the merchant of record. Agentic features built into Business Manager include conversational catalog search, where the Merchandising Agent builds filter logic from plain English, and AI-suggested category assignments with a dashboard insight for uncategorized products.

For integration work, the most relevant changes are the Event Framework going generally available, with process-level and granular replication events, shopper registered and order placed events routed to HTTP webhook connectors, and support for custom events declared in a cartridge. The trusted connection to a Salesforce org no longer needs a Data 360 license, admins get self-service unpairing after a sandbox refresh, and developers can pair non-production instances with any Salesforce sandbox type. Profile updates now sync to connected Person Accounts in near real time, and partial POS catalog syncs let stores receive only modified pricing and product data.

On the tooling side, the Agentic Developer Toolkit gains more built-in knowledge, new operations runbooks that always ask for approval before making changes, and SCAPI Code Mode, which lets an AI assistant look up Salesforce Commerce API operations and run small scripts against a live instance. Direct SCAPI security controls for rate limits, WAF rules and cache purges are also available in Business Manager or by API.

Read the original at Salesforce Blog (opens in a new tab)

Worth reading?

B2C Commerce release 26.9 introduces edge credential detection and SFRA password warnings (opens in a new tab)

Readers will learn how to configure Cloudflare firewall and rate limiting rules in B2C Commerce to block leaked credentials, and how to implement server-side header checks in SFRA to prompt users to rotate breached passwords.

The September 2026 update to B2C Commerce adds built-in credential stuffing protection through its eCDN layer without requiring additional entitlements. Four new detection fields evaluate login attempts against known breach data, allowing administrators to create custom firewall and rate limiting rules at the network edge.

The article provides exact rule syntax examples to throttle malicious traffic while preserving verified search crawlers. It explains how to use managed challenges for password leaks and emphasizes separating counting expressions from rule expressions to avoid penalizing legitimate bot activity.

For storefront implementations, the piece details how to read a server-side request header added by Cloudflare after a successful login. A working SFRA code example demonstrates how to map header values to user-facing warning messages and direct shoppers to a password reset flow, deliberately avoiding failed login responses to prevent information leakage to attackers.

Finally, the author outlines monitoring strategies using Security Analytics in Business Manager and eCDN Logpush exports, recommending these detections as a baseline before layering in broader bot mitigation controls.

Read the original at Salesforce Developers Blog (opens in a new tab)

Worth reading?