The independent daily for Salesforce admins, developers and architects

Curated by Abhinav (opens in a new tab)

Must-read

Agentforce agents move to AiAgentDefinition metadata types in API version 68.0 (opens in a new tab)

You will learn how the new AiAgentDefinition and AiAgentDefinitionVersion types replace Bot, GenAiPlannerBundle and AiAuthoringBundle for Agentforce agents, how to write a manifest and retrieve a single version with its dependencies, and which deployment rules and migration steps apply.

Agentforce agent at API 68.0

  • AiAgentDefinition
  • AiAgentDefinitionVersion
  • AiAuthoringBundle
The three old metadata types and the two new types that replace them

Winter ’27 introduces two metadata types for Agentforce agents at API version 68.0: AiAgentDefinition, which holds agent-level settings, and AiAgentDefinitionVersion, which holds one version’s settings, messages and an inline planner with its subagents and actions. Under the previous structure, one agent was spread across the Bot, GenAiPlannerBundle and AiAuthoringBundle types, with generated name suffixes, hard-to-find welcome messages and folder names that changed between retrieves. The author compares a sample agent retrieved at API 67.0 and 68.0, showing that the content was identical and only the names and packaging changed.

At API 68.0, Agentforce agents must use the new types, and retrieving or deploying them as Bot or BotVersion returns an error. The # delimiter lets a manifest or the –metadata flag select a single version, such as TestAgent#1, all versions with TestAgent#, or every version of every agent. Salesforce CLI version 2.149.9 or later is needed, and the –root-type-with-dependencies AiAgentDefinitionVersion flag pulls in the parent definition, the authoring bundle and the Flows, Apex classes and Prompt Templates the version uses. The dependency retrieve is limited to 25 requests per day, 100 components per request, and one level deep.

Deployments fail if the old and new formats are mixed, if a version is deployed without its definition existing in the target org or the same deployment, or if the Agent Script source is omitted. The author also notes that the agent user from the source org must be replaced for a draft agent, and recommends switching to API 68.0 in its own commit and updating any scripts that parse the old files.

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

Worth reading?

Must-read

Running a seven-stage agent-driven Salesforce lifecycle with the Headless Toolkit (opens in a new tab)

You will learn how to structure a Salesforce project around coding agents, using Skills, hosted MCP Servers and the Salesforce CLI across seven stages from grounding to observation.

Why read this

You will also see how to keep the agent's context lean and feed each mistake back into the project's instructions, checks and specs.

  1. Ground in business and org
  2. Specify what to build
  3. Build with the agent
  4. Verify with tests and checks
  5. Review with a reviewer agent
  6. Release through a human gate
  7. Observe and feed mistakes back
The seven stages of the agent-driven Salesforce lifecycle, each leaving an artifact for the next

This Salesforce Developers Blog post, written by Principal Developer Advocate Mohith Shrivastava, proposes an agent-driven development lifecycle built on the Headless Toolkit: the Salesforce Skills Library (sf-skills), Salesforce Hosted MCP Servers for org context, and the Salesforce CLI for testing and deploying. The author argues that coding agents drift from platform best practices and miss what already exists in an org, so a team should wrap them in its own project layer of skills, instructions, ontology, tools and checks. The linear project model becomes a loop in which each stage leaves an artifact for the next, and every mistake feeds back into the project. The author also stresses keeping the agent’s context lean, since accuracy falls as the context window fills, and notes that the agent’s built-in harness is the same for everyone while the project harness is what makes it effective on a specific org.

The seven stages run as follows. Ground gives the agent the org’s existing metadata through the read-only Metadata Grounding MCP Server (Beta), a feature map and an ontology of business terms. Specify has the agent produce a short, human-approved spec kept up to date alongside the code, recommended as spec-anchored and used only for features that span several metadata types or sessions. Build lets one agent work step by step, or subagents work in parallel in separate git worktrees, with each subagent given only the context it needs. Verify runs independent checks such as Apex tests, Code Analyzer, ApexGuru scans, LWC and accessibility checks, and hooks that run automatically. Review uses a separate, read-only adversarial reviewer agent whose findings humans judge. Release has the agent validate and promote changes through deterministic gates, with a human owning the production step. Observe has the agent read debug logs and traces to find production issues and start the next loop.

The post closes with a principle: each repeated mistake should become a constraint. Advisory instructions and skills reduce errors, but deterministic tests, Code Analyzer rules, hooks and quality gates catch them regardless of who wrote the code, and the author recommends choosing the strongest option available and cleaning up existing code that the agent might copy. The author presents this as one approach to adapt rather than the only way, and suggests installing the skills and starting with the stages that suit the team.

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

Worth reading?

Must-read

Route real phone calls to your Agentforce Voice agent using Salesforce CLI and Omni-Channel flows (opens in a new tab)

You will learn how to configure an Agentforce Service Agent user, request a phone number, and build a one-element Omni-Channel routing flow to connect callers to your voice enabled script.

Why read this

You will also know how to verify call routing and inspect post call records using the Salesforce CLI.

  1. Verify entitlements and licenses
  2. Create an Agentforce Service Agent user
  3. Build an Omni-Channel routing flow
  4. Activate the flow and PSTN Voice channel
  5. Test the call and query records
This diagram shows the five-step process for routing real phone calls to an Agentforce Voice agent

The article explains that routing live calls requires an active Agentforce Voice agent, a dedicated Einstein Agent User license, and available inbound voice credits. Developers must verify entitlements and create a service agent user through the Salesforce CLI before configuring any routing logic.

A call reaches the agent through three linked components: a purchased phone number, a PSTN Voice channel, and an Omni-Channel flow. The flow requires a single input variable named recordId and one Route Work element that directs the call to the activated service agent, with a voice queue as a fallback.

After activating the flow and channel, administrators can test the connection by dialing the assigned number. Since live sessions do not generate transcripts, the author demonstrates how to query VoiceCall and AgentWork records via SOQL to confirm call duration, vendor type, and successful routing.

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

Worth reading?

A VS Code extension runs anonymous Apex and SOQL with a single keyboard shortcut (opens in a new tab)

Readers will learn how to install and configure Virga to execute throwaway Apex and SOQL scripts without leaving the editor.

Why read this

The piece also explains how the extension resolves common language server completion issues and disables telemetry during local runs.

Virga is a free VS Code extension designed to streamline the execution of throwaway Apex and SOQL scripts directly within the editor. Setup requires VS Code version 1.90 or newer, the Salesforce CLI on the system path, and an active Salesforce DX project. Users create dedicated scratch tabs for either language, trigger execution with a keyboard shortcut, and receive formatted output showing compilation status, debug logs, governor limits, or flattened query results.

The tool handles execution through a temporary file copy rather than direct command line arguments, which prevents partial edits from affecting the run. It achieves a seamless experience by applying a brief auto-save delay that clears tab dirtiness markers, allowing instant closure without save prompts. Scratch files persist in a version control ignored folder and survive editor restarts, while conflicting keymaps are handled to preserve the shortcut exclusively for scratch contexts.

Beyond basic execution, the extension patches gaps in the standard Salesforce Extension Pack. It adds completion support for inner types declared in the same file, identifies and offers quick fixes for parameter shapes that crash the language server, and supplies missing snippets for annotations and user mode operations. Privacy is maintained by automatically disabling Salesforce CLI telemetry for each run, though administrators can enforce global telemetry suppression through standard configuration commands.

Read the original at dev.to (opens in a new tab)

Worth reading?

Build a Claude Code mod to display Salesforce CLI org context (opens in a new tab)

You will learn how to create a Claude Code mod that reads Salesforce CLI configuration files to show your default org, its type, and Scratch Org expiry directly above the command prompt.

Why read this

The guide covers the required plugin structure, event hooks, and testing steps.

The article walks through creating a custom plugin for Claude Code that surfaces Salesforce CLI context directly in the terminal interface. It explains how to set up the plugin manifest, define reactive state types, and structure the directory for hooks and tests.

Instead of running slow CLI commands, the mod reads internal Salesforce authentication and configuration files to determine the target org alias, My Domain, org type, and Scratch Org expiration date. It also tracks which organizations are connected to configured Salesforce MCP servers.

The tutorial details several event hooks that trigger when sessions start, directories change, or tool calls execute. A render hook draws a colored status band above the prompt, using theme-aware colors to distinguish production, sandbox, and Scratch environments. The author includes validation and testing procedures, plus instructions for making the plugin load automatically across sessions.

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

Worth reading?

Winter 27 release brings Headless Toolkit, Multi Framework support, and Data SDK extensions (opens in a new tab)

Readers will learn how to build cross-framework applications on the platform using the new Headless Toolkit and understand how to extend the Data SDK with custom logic.

The Winter ’27 release, whose final rollout is set for October 9, 2026, centers on the Headless Toolkit. Salesforce capabilities are exposed as APIs, Model Context Protocol (MCP) tools and CLI commands that any authenticated caller can use. The Salesforce Development plugin for Claude Code adds Salesforce-specific skills, org context and recommendations for specialized plugins, and its skills also work with other coding agents. Multi-Framework apps now support Angular alongside React, with new templates, 2GP packaging and a Data SDK that can package custom logic as typed extensions. Beta microfrontends let an app run inside a Lightning page, with data passed down from the host component and events sent back up.

The Headless Experience Layer (Beta) lets a developer define a widget once and render it in Agentforce, Claude and Slackbot, linked through Apex, Lightning type and widget metadata. MCP now works in both directions, so Agentforce agents can be exposed as tools on custom MCP servers and AgentExchange MCP tools can be added to agents. The Marketing Cloud Engagement MCP server gains 40 tools. The CLI stops printing access tokens and secrets, with the temporary workaround ending October 28, 2026, and it adds async Apex templates and Scratch Org settings. API version 68.0 requires the Use Any API Auth permission for SOAP login from December 1, 2026, retires API versions 31.0 through 40.0, and adds a latest alias for REST URIs.

In Lightning Web Components, template expressions and LWC:external reach general availability, and state managers gain a refresh() method. Apex heap limits rise to 10 MB for synchronous and 25 MB for asynchronous transactions, and integration tests, FORMULA() and the Apex Symbol API are in preview or beta. Agentforce gains new Agent Script language features, file uploads in conversations, and generally available Multi-Agent Orchestration, along with simplified agent metadata types. Data 360 adds a context precision metric for retrievers and Python code extensions for zero-copy data. Web Console, a browser-based IDE, is generally available and needs no installation.

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

Worth reading?

Recommended

Deploy Python Code Extensions for complex Data 360 batch transformations (opens in a new tab)

You will learn how to structure, validate, and deploy Python scripts as managed Code Extensions within Data 360.

Why read this

The guide also covers connecting these scripts to batch data transforms and monitoring execution through the platform.

Northstar Outfitters faced inconsistent product data across commerce systems and needed a trusted catalog. Native visual transforms could not handle the required standardization, enrichment, and scoring logic, prompting the use of Data 360 Code Extension to run modular Python and PySpark scripts directly on Salesforce infrastructure.

The solution relies on isolated runtime environments where scripts read from and write to designated Data Lake Objects using explicit permissions defined in a configuration file. Developers validate logic locally against sampled data before packaging the script, dependencies, and tests into a deployable archive.

The guide details both Setup interface and Salesforce CLI workflows for uploading packages, selecting compute sizes, and linking the extension to a batch data transform. Execution, scheduling, and logging are handled by the platform, while operators can trigger runs and review history through REST API calls.

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

Worth reading?