Vendor guidance
Vendor and platform documentation on building and governing AI agents.
24 resources
Amazon Bedrock Agents (user guide)
AWS user guide for Amazon Bedrock Agents, covering action groups, knowledge bases, prompt overrides, guardrails, and multi-agent collaboration. Walks through IAM setup, tracing via CloudWatch, and invocation patterns for production agent deployments.
Amazon Bedrock AgentCore
AWS product page for Bedrock AgentCore, presenting its runtime, gateway, memory, identity, observability, and browser-tool components. Positions AgentCore as framework-agnostic infrastructure for deploying agents built with any SDK at enterprise scale.
Introducing Amazon Bedrock AgentCore: Securely deploy and operate AI agents at scale
AWS News blog announcing AgentCore's general availability, detailing session isolation, identity-aware tool access, and observability primitives. Covers use cases, pricing model, and integrations with Bedrock Agents, Strands, LangGraph, and CrewAI.
Microsoft Foundry Agent Service
Microsoft Learn documentation for Azure AI Foundry Agent Service, covering agent definition, threading, tool invocation, and content safety. Describes deployment options, Entra ID integration, and differences from the legacy Azure OpenAI Assistants API.
Application Card for Microsoft Copilot Studio
Microsoft's service card for Copilot Studio documenting system purpose, intended uses, capabilities, performance, limitations, and responsible-AI considerations. Serves as the transparency artefact for customers evaluating Copilot Studio for agent-building.
Platform Card and Responsible AI FAQs for Copilot Studio
Microsoft's responsible AI overview and FAQs for Copilot Studio agent builders, covering grounding, content filters, prompt shields, user consent, data boundaries, and mitigation guidance for common failure modes in custom agents.
Introduction to the Agentic AI adoption maturity model
Microsoft's five-level agentic AI adoption maturity model spanning initial pilots through autonomous fleets. Details governance, security, data readiness, and change-management milestones at each level, with self-assessment and Copilot Studio-specific practices.
AutoGen: A programming framework for agentic AI
Microsoft's open-source AutoGen framework for multi-agent applications, offering a layered API (Core, AgentChat, Extensions) with async messaging, tool use, and group chat patterns. Includes AutoGen Studio, a no-code designer for multi-agent workflows.
Building AI Agents with Vertex AI Agent Builder
Google Cloud codelab walking developers through building agents with Vertex AI Agent Builder, covering tool definition, reasoning loops, conversation management, and deployment. Uses Gemini models and integrates with Google Search and Dialogflow components.
Gemini API Additional Terms of Service
Google's additional terms for the Gemini API governing developer use, covering acceptable use, user protections, restricted applications, prompt and output handling, and agentic use cases like browsing and transaction execution.
Anthropic Usage Policy (with agentic provisions)
Anthropic's announcement of its updated Usage Policy with dedicated agentic AI provisions, covering authorisation, impersonation, scope boundaries, and user-consent expectations when Claude takes actions on a user's behalf through tools and computer use.
Using Agents According to Our Usage Policy
Anthropic support article translating the Usage Policy into operational guidance for agent builders, covering attribution, human oversight, prohibited autonomous actions, and how policy applies to long-running, tool-using deployments of Claude.
Use Claude Cowork safely
Anthropic's safety guide for Claude Cowork, covering scope of autonomy, credential handling, approval checkpoints, monitoring, and rollback when letting multiple Claude instances collaborate on tasks inside a user's environment.
Using ChatGPT agent in line with our policies
OpenAI policy page for ChatGPT agent capabilities (browsing, terminal, computer use), detailing acceptable use, restricted actions (payments, sensitive accounts, account creation), and user-confirmation requirements for high-impact steps.
Codex: Agent approvals and security
OpenAI developer documentation for Codex agent approval modes (auto, read-only, full auto) and security settings, covering sandboxing, network egress controls, secret handling, and configuring approval prompts for tool execution in coding workflows.
Einstein Trust Layer and Agentforce
Salesforce developer guide explaining how Agentforce uses the Einstein Trust Layer - zero-retention prompts, dynamic grounding, toxicity detection, PII masking, and audit trails - to govern agents that act inside customer CRMs.
Agent Bricks: unified control plane for AI agents
Databricks product page for Agent Bricks presenting it as a unified control plane for building and governing enterprise agents, with Unity Catalog permissions, AI Gateway policies, Mosaic AI evaluation, and observability tied to Lakehouse data.
Anthropic Usage Policy (with agentic AI provisions)
Anthropic's acceptable use policy, which includes dedicated provisions governing how Claude and Claude-powered agents may be deployed, with specific constraints on high-risk agentic use cases.
OpenAI Usage Policies
OpenAI's usage policies setting out permitted and prohibited uses of its models and agent products, including rules that apply when ChatGPT agent and other autonomous capabilities act on a user's behalf.
Agentic AI Adoption Maturity Model: AI Governance and Security Pillar
Microsoft's governance and security pillar within its Agentic AI Adoption Maturity Model for Copilot Studio, describing staged controls organizations should put in place as they scale agent deployments.
AWS Responsible AI Policy
AWS’s responsible AI policy setting expectations for safe, fair, and accurate use of its AI and ML services, including the controls and governance customers are expected to apply when building and deploying agents on AWS.
Agentic AI frameworks, platforms, protocols, and tools on AWS
AWS prescriptive guidance surveying the agentic AI frameworks, platforms, protocols, and tools available on AWS, with guidance on choosing and governing them when building agent workloads.
Safety (Responsible AI) in the Gemini Enterprise Agent Platform
Google Cloud’s responsible-AI and safety documentation for the Gemini Enterprise Agent Platform, covering content safety, prompt-injection protection via Model Armor, and the governance controls available for enterprise agent deployments.
Salesforce Agent Fabric: governance control plane for multi-vendor AI agents
Salesforce’s Agent Fabric announcement, a governance control plane that brings agents running across multiple platforms and vendors under one layer with deterministic orchestration and centralized agent, tool, and LLM governance.