Salesforce Einstein Agentic Access
Salesforce Einstein exposes 70 API operations that an AI agent could call, of which 35 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.
By consequence: 35 read, 34 write, and 1 physical.
Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.
By consequence
Highest-consequence actions
The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.
| Method | Path | Consequence | Human-in-loop |
|---|---|---|---|
| POST | /einstein/bots/{botId}/sessions/{sessionId}/messages | physical | conditional |
Source
Agentic Access
generated: '2026-07-15'
method: generated
source: openapi/salesforce-einstein-bots-openapi.yml, openapi/salesforce-einstein-discovery-openapi.yml,
openapi/salesforce-einstein-gpt-openapi.yml, openapi/salesforce-einstein-language-openapi.yml,
openapi/salesforce-einstein-prediction-builder-openapi.yml, openapi/salesforce-einstein-vision-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
audience per deployment. See research/curity/agentic-governance/.
summary:
operations: 70
by_action_class:
connected: 35
acting: 35
by_consequence:
read: 35
write: 34
physical: 1
human_in_the_loop_required: 0
operations:
- path: /einstein/bots
method: get
operationId: listBots
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/bots/{botId}
method: get
operationId: getBot
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/bots/{botId}/versions
method: get
operationId: listBotVersions
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/bots/{botId}/versions/{versionId}
method: get
operationId: getBotVersion
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/bots/{botId}/sessions
method: post
operationId: createSession
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/bots/{botId}/sessions/{sessionId}
method: get
operationId: getSession
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/bots/{botId}/sessions/{sessionId}
method: delete
operationId: endSession
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/bots/{botId}/sessions/{sessionId}/messages
method: post
operationId: sendMessage
x-agentic-access:
action-class: acting
consequence: physical
subject: required
audience: null
token:
max-ttl: 300
exchange: true
purpose-required: true
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/bots/{botId}/sessions/{sessionId}/messages
method: get
operationId: getMessages
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/stories
method: get
operationId: listStories
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/stories
method: post
operationId: createStory
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /wave/stories/{storyId}
method: get
operationId: getStory
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/stories/{storyId}
method: patch
operationId: updateStory
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /wave/stories/{storyId}
method: delete
operationId: deleteStory
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /wave/stories/{storyId}/stats
method: get
operationId: getStoryStats
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/models
method: get
operationId: listModels
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/models/{modelId}
method: get
operationId: getModel
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/models/{modelId}
method: delete
operationId: deleteModel
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /wave/prediction
method: post
operationId: predict
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /wave/lenses
method: get
operationId: listLenses
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/lenses/{lensId}
method: get
operationId: getLens
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/dashboards
method: get
operationId: listDashboards
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /wave/dashboards/{dashboardId}
method: get
operationId: getDashboard
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/llm/prompt/generations
method: post
operationId: generateFromPrompt
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/llm/prompt/completions
method: post
operationId: completePrompt
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/llm/prompt/chat/generations
method: post
operationId: chatGeneration
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/llm/prompt/templates
method: get
operationId: listPromptTemplates
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/llm/prompt/templates
method: post
operationId: createPromptTemplate
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/llm/prompt/templates/{templateId}
method: get
operationId: getPromptTemplate
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/llm/prompt/templates/{templateId}
method: patch
operationId: updatePromptTemplate
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/llm/prompt/templates/{templateId}
method: delete
operationId: deletePromptTemplate
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/llm/models
method: get
operationId: listModels
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/llm/models/{modelId}
method: get
operationId: getModel
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/llm/feedback
method: post
operationId: submitFeedback
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /datasets
method: get
operationId: listDatasets
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /datasets
method: post
operationId: createDataset
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /datasets/{datasetId}
method: get
operationId: getDataset
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /datasets/{datasetId}
method: delete
operationId: deleteDataset
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /datasets/{datasetId}/examples
method: get
operationId: listExamples
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /datasets/{datasetId}/examples
method: post
operationId: addExample
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /datasets/{datasetId}/models
method: get
operationId: listModelsForDataset
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /train
method: post
operationId: trainModel
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /retrain
method: post
operationId: retrainModel
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /models/{modelId}
method: get
operationId: getModel
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /models/{modelId}
method: delete
operationId: deleteModel
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /sentiment
method: post
operationId: analyzeSentiment
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /intent
method: post
operationId: detectIntent
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /apiusage
method: get
operationId: getApiUsage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/prediction-definitions
method: get
operationId: listPredictionDefinitions
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/prediction-definitions
method: post
operationId: createPredictionDefinition
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/prediction-definitions/{predictionDefinitionId}
method: get
operationId: getPredictionDefinition
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/prediction-definitions/{predictionDefinitionId}
method: patch
operationId: updatePredictionDefinition
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/prediction-definitions/{predictionDefinitionId}
method: delete
operationId: deletePredictionDefinition
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /einstein/prediction-definitions/{predictionDefinitionId}/predictions
method: get
operationId: listPredictions
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /einstein/ai-record-insights
method: post
operationId: getAIRecordInsights
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /datasets
method: get
operationId: listDatasets
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /datasets
method: post
operationId: createDataset
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /datasets/{datasetId}
method: get
operationId: getDataset
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /datasets/{datasetId}
method: delete
operationId: deleteDataset
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /datasets/{datasetId}/examples
method: get
operationId: listExamples
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /datasets/{datasetId}/examples
method: post
operationId: addExample
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /datasets/{datasetId}/models
method: get
operationId: listModelsForDataset
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /train
method: post
operationId: trainModel
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /retrain
method: post
operationId: retrainModel
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /models/{modelId}
method: get
operationId: getModel
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /models/{modelId}
method: delete
operationId: deleteModel
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /models/{modelId}/lc
method: get
operationId: getModelLearningCurve
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /predict
method: post
operationId: predictImage
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /detect
method: post
operationId: detectObjects
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /apiusage
method: get
operationId: getApiUsage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none