Salesforce aware access
Uses the Salesforce access model your team already manages
Security & Trust
Governed AI for Salesforce teams that need control, review, and audit.
ConvoPro lets users create and share prompt buttons inside admin-defined boundaries. Salesforce permissions control access, admins define what AI can see and do, and data-changing actions route through human review before they run.
Start with one workflow. Define the boundaries. Keep human review where required. Expand what proves useful.
Governed workflow pathAdministrator controlled
Access policy
Approved data and users
Allowed action
Configured tools and changes
Human review
Required where configured
Approved update
Salesforce or connected action
Activity record
Reviewable workflow status
Boundary first governance
Admins define what AI can see, use, and trigger
Human review on write
Create, update, send, delete, and trigger actions require review by default
Usage and audit visibility
Review who ran what, what was reviewed, and what was promoted
Governance model
Model and connector control without unmanaged sprawl.
Model flexibility only works when admins can govern providers, credentials, connectors, tools, and usage visibility.
01
Access
Define the information and capabilities available to each workflow.
- Salesforce records and objects
- Connected systems and data sources
- Approved model configurations
- User, role, and team availability
02
Actions
Control what a workflow is permitted to do after it prepares an output.
- Permitted tools
- Record creation and updates
- External-system actions
- Restricted or sensitive operations
03
Review
Set where a person must confirm an output or proposed action.
- Required human confirmation
- Approval thresholds
- Exception and escalation paths
- Source and output review
04
Lifecycle
Manage a workflow after it becomes available to a team.
- Workflow ownership
- Publishing and versioning
- Usage and activity visibility
- Central update or disablement
Workflow data flow
Clear data flow for evaluation teams.
ConvoPro is designed around a clear operating path: Salesforce access first, admin-defined boundaries second, approved processing third, and human review before data-changing actions execute.
User starts in Salesforce
A user runs a prompt button, workflow, or Studio request from the Salesforce work context.
Access and boundaries are checked
The request is evaluated against Salesforce access and ConvoPro admin policy.
Approved context is processed
Approved context, instructions, and tools needed for the task move through the configured processing path.
Result returns for review or action
Read and draft results return to the user. Data-changing actions route through review before execution.
ConvoPro installs in your Salesforce org and calls approved AI models through admin-configured connectors. Detailed data flow documentation is available for evaluation teams. Security, retention, and model-provider details depend on the selected ConvoPro configuration and customer requirements.
Human review
Fast for read and draft work. Reviewed when actions change data.
ConvoPro is designed so teams can move quickly on read, summarize, classify, analyze, and draft tasks. When a prompt button creates, updates, sends, deletes, or triggers an action, review rules can require a human to confirm before the action runs.
Move quickly on read, analysis, and draft tasks
Employees can use approved workflows to prepare work without turning every repeated request into an admin or development ticket.
- Summarize a case or account
- Draft a customer follow-up
- Extract information from a file
- Classify or route a request
- Prepare a handoff or next-step recommendation
Keep a person in control where the workflow changes data
Configured review points let the organization decide which proposed actions require confirmation before execution.
- Create or update a Salesforce record
- Send a customer-facing message
- Trigger a downstream workflow
- Push data to an external system
- Handle exceptions or restricted operations
Activity visibility
See what was used, reviewed, and promoted.
Audit visibility should help answer practical questions: who used AI, what context was used, what action was proposed, who reviewed it, and what changed.
Security review
What evaluation teams can review before deployment
Use the public summary to understand the operating model. Use the security review to confirm the details of your selected workflow and configuration.
Salesforce access model
Public summaryConvoPro is designed to work within Salesforce access and administrator-defined workflow policy.
Confirm during evaluationReview the permission-check approach, installation scope, and workflow-specific object and field access.
Data flow and handling
Security reviewApproved Salesforce context is processed through the configured workflow path and returned for review or action.
Confirm during evaluationReview the selected workflow's data path, hosting, model providers, connector path, and handling requirements.
Models and connectors
Configuration-specificAdministrators define which model and connector configurations are available to approved workflows.
Confirm during evaluationConfirm provider terms, customer-key options, connector permissions, and external-system boundaries.
Retention and deletion
Security reviewSalesforce remains the operational system of record for the workflows described on this page.
Confirm during evaluationConfirm current prompt, output, file, activity, and audit retention, plus deletion and termination handling.
Subprocessors and infrastructure
Security reviewCurrent provider, hosting, and subprocessor information is available to qualified evaluation teams.
Confirm during evaluationReview the current list, data locations, encryption details, tenant isolation, and incident-response terms.
AppExchange and compliance
Security reviewConvoPro publishes certification and compliance claims only when they are current and documented.
Confirm during evaluationConfirm current AppExchange, legal, privacy, and compliance status for the intended deployment.
Security documentation
Request the security packet.
Share the intended Salesforce workflow and your review requirements. We will provide the current documentation relevant to that configuration.
The review package can include
- Architecture and workflow data-flow overview
- Salesforce permission and access approach
- Model-provider and connector handling
- Current retention and deletion terms
- Current subprocessor and infrastructure information
- Human-review and action-control model
- Activity and audit visibility details
- Current AppExchange, legal, and compliance status
FAQ
Security FAQ
Answers for CIOs, Salesforce admins, security reviewers, and implementation teams.
Does ConvoPro bypass Salesforce permissions?
No. ConvoPro is designed around Salesforce access first, then ConvoPro admin-defined boundaries for data, tools, models, connectors, and actions.
What actions require human review?
Data-changing actions such as create, update, send, delete, or trigger style actions require human review according to configured rules.
Can users share prompt buttons without admin approval?
Yes. Prompt buttons can be shared inside admin-defined boundaries. Human review is tied to data-changing actions, not sharing itself.
What data leaves Salesforce?
Approved context and instructions move through the configured processing path for the task. Evaluation teams can request the current data flow documentation for their selected configuration.
Is customer data used to train AI models?
Model-training and provider-handling details are documented for the selected configuration. Evaluation teams can request the current security packet before rollout.
Does ConvoPro require Data Cloud?
ConvoPro can often start without a broad Data Cloud program for the core prompt button and governed workflow model described on this page. Final architecture depends on the workflow, data sources, and customer configuration.
Can we choose which model provider is used?
Yes. ConvoPro is model-flexible. Admins choose which approved models are available for each workflow from the Console — with governed access to Claude (Anthropic), OpenAI, and Google models provided through ConvoPro’s keys. No customer API keys are required.
Is AppExchange Security Review complete?
Current AppExchange review status is provided during evaluation and should be confirmed with the ConvoPro team before procurement.
What gets logged?
Audit visibility includes usage, prompt button, review decision, action status, and promotion path. Specific fields and retention behavior are documented in the security packet.
Can we limit rollout by team or role?
Yes. Rollout can be planned by team, role, workflow, and policy needs during implementation.
Review ConvoPro with your security and Salesforce teams.
Start with the control model: Salesforce permissions, admin-defined boundaries, human review for data-changing actions, audit visibility, and documented data flow.
