Resources

Implementation library

Resources for agent permission design

Practical guides, tutorials and software for deciding what an agent may do, enforcing those limits and testing what happens when something goes wrong.

Start with one customer task. Use the Permission Plan Builder to document Inform, Recommend, Act within limits, Request approval and Not permitted. Then share the relevant implementation resources with the people responsible for your systems.

Customer confirmation and employee approval serve different purposes. Missing evidence should pause execution; approval does not automatically supply that evidence or override a prohibited action.

43 selected resources · Reviewed October 6, 2026

How these resources were selected

The external links favor original guidance, official documentation and maintainers’ repositories. Descriptions explain the intended use, not a product endorsement or a hands-on security assessment. These are direct links without affiliate tracking added by PermissionByDesign.

Documentation is generally publicly readable, but software, hosted services, courses, model calls and infrastructure may require accounts or payment. Check current access terms, licensing, version support and data handling before using a resource. A framework, worksheet or guardrail does not guarantee enforcement, security or compliance.

Planning tools and worked examples

Begin with the business task and the decisions the implementation team will need to enforce.

  • Permission Plan Builder

    PermissionByDesign · Browser tool · Business teams

    Document actions, evidence, approval routes, recovery decisions and review triggers. The builder records intended authority; it does not grant or enforce system access.

  • Printable and editable permission worksheets

    PermissionByDesign · PDF and Word · Business teams

    Blank worksheets and a completed fictional refund plan for teams that prefer a document-based planning process.

  • Permission planning guides

    PermissionByDesign · Article collection · All readers

    Plain-language guides to authority, handoffs, correction, uncertain outcomes and permission ownership. Read these before selecting implementation software.

  • Refunds and Returns worked guide

    PermissionByDesign · Worked example · CX and implementation teams

    Follow one fictional policy through routine refunds, approval exceptions, prohibited actions and evidence requirements. Its limits are illustrative, not industry standards.

  • Illustrative Permission Plan Review

    PermissionByDesign · Annotated example · Business owners

    Compare an incomplete refund plan with review findings and a revised plan. Useful preparation for your own cross-team review.

Back to categories

Governance guides and frameworks

Use these to assign responsibility, assess risk and decide when permissions need another review.

  • NIST AI Risk Management Framework

    NIST · Framework · Business and risk owners

    A voluntary framework for governing, mapping, measuring and managing AI risk. Use it to connect a permission plan to wider organizational responsibilities.

  • NIST AI RMF Playbook

    NIST · Practical guidance · Business and risk owners

    Suggested actions supporting the framework. Select the actions relevant to your context; NIST explicitly says this is not a checklist to follow in its entirety.

  • Generative AI Profile, NIST AI 600-1

    NIST · PDF guide · Risk and implementation teams

    Companion guidance for generative AI risks and suggested management actions. Useful when extending an existing AI review process to agents.

  • Apply responsible AI to an agent practice

    Microsoft · Governance guide · Team leads

    Connects design choices, release reviews, human oversight and continuing governance. Useful for preparing the questions a business owner should ask before launch.

Back to categories

Security and permission-boundary guides

Authorization means deciding whether a particular actor may perform a particular action. These resources explain why it belongs in the executing system, not only in a prompt.

  • AI Agent Security Cheat Sheet

    OWASP · Implementation guide · Engineering and security

    A starting reference for scoped tools, approval validation, execution controls and abuse-case tests. Useful for turning an action inventory into technical requirements.

  • Excessive Agency

    OWASP · Risk guide · All readers

    Explains how unnecessary functions, permissions and autonomy enable harm. Its examples help teams challenge broad tool access and remove unused capabilities.

  • Top 10 for Agentic Applications for 2026

    OWASP · Risk reference · Engineering and risk teams

    A shared vocabulary for reviewing agent-specific risks. Use it to broaden test discussions, not as proof that completing ten checks makes an agent secure.

  • LLM Prompt Injection Prevention Cheat Sheet

    OWASP · Implementation guide · Engineering and security

    Covers hostile instructions arriving through prompts and external content. Useful when customer messages, retrieved documents or tool results could influence actions.

  • Authorization Cheat Sheet

    OWASP · Implementation guide · Developers

    Guidance on least privilege, denying by default and validating access. Apply it to the business API or tool that executes the agent's request.

  • Transaction Authorization Cheat Sheet

    OWASP · Implementation guide · Developers

    Guidance for authorizing a specific transaction and protecting the authorization sequence. Useful for approval scope, changed details and checks immediately before execution.

  • MCP security best practices

    MCP project · Living draft guidance · Integration engineers

    Reviews risks at the Model Context Protocol boundary, including confused-deputy and token-handling problems. Check the guidance against the protocol version your integration uses.

Back to categories

Tutorials and approval workflows

Human-in-the-loop means a workflow pauses for a person. Your implementation must still distinguish customer confirmation from employee approval and verify that the person has the right authority.

  • Human-in-the-loop middleware

    LangChain · Tutorial · Developers

    Configure review of selected tool calls and handle approval, editing or rejection. Add your own checks for reviewer authority, exact action details and approval validity.

  • LangGraph interrupts

    LangChain · Tutorial · Developers

    Learn how to pause and resume a workflow with saved state. Pay attention to replay behavior so code around a pause does not repeat an external action.

  • Function tools with human approvals

    Microsoft · Tutorial · Developers

    Shows an agent returning a request for approval and resuming with the response. Useful for separating the proposed tool call from its execution.

  • ADK action confirmations

    Google ADK · Tutorial · Developers

    Examples of confirmation before tool execution. Treat the confirmation mechanism as one component; business approval rules still need explicit enforcement.

  • Understanding authorization in MCP

    MCP project · Tutorial · Integration engineers

    Walks through authorization for remote MCP servers. Model Context Protocol connects agents with tools; connection authorization is not a substitute for checks on each business action.

  • AI Agents Course

    Hugging Face · Course · Technical learners

    A broader introduction to agents, tools and frameworks. Useful background before implementing permission boundaries, but not an authorization or security certification.

Back to categories

Authorization software and policy languages

These components can support enforceable decisions. They require integration: a policy engine's answer only helps if the tool or application obeys it.

  • Open Policy Agent

    OPA · Open-source policy engine · Engineers

    Evaluate structured requests against policies written in Rego. Consider it when multiple tools need a shared, testable policy decision layer.

  • Cedar policy language

    Cedar · Policy language and engine · Engineers

    Express whether a principal may perform an action on a resource under specified conditions. Useful for explicit permit and forbid rules.

  • OpenFGA getting started

    OpenFGA · Open-source authorization · Engineers

    Model relationships between users, teams and resources and check access. Useful for customer or account boundaries; transaction-specific limits need appropriate additional policy checks.

  • SpiceDB

    AuthZed · Open-source authorization database · Engineers

    Stores and queries fine-grained authorization relationships. Evaluate it for resource access boundaries, not as a ready-made refund approval system.

  • Cerbos authorization platform

    Cerbos · Authorization software · Engineers

    Policy-based authorization documentation covering the decision point and associated platform. Review deployment, licensing and integration requirements for your use case.

  • Policy in Amazon Bedrock AgentCore: Cedar policies

    AWS · Managed platform documentation · AWS engineers

    Shows how Cedar policies control access to AgentCore Gateway tools. Its sample amounts belong to the vendor example and are not a recommended business policy.

Back to categories

Testing tools and guardrails

Test in a controlled environment using fictional records. Red teaming deliberately probes failure and misuse; a passing result is evidence about those tests, not a guarantee of safety.

  • Promptfoo red teaming

    Promptfoo · Testing software and guide · Engineering and security

    Generate and evaluate adversarial tests for an application. Include your own unauthorized-action, missing-evidence and approval-bypass scenarios rather than relying only on stock tests.

  • PyRIT

    Microsoft · Open-source testing framework · Security specialists

    Automates risk-identification exercises for generative AI systems. Useful for repeatable adversarial testing alongside deterministic checks of tool permissions.

  • garak

    NVIDIA · Open-source vulnerability scanner · Security specialists

    Probes language-model behavior for potential weaknesses. Pair model-level findings with tests of the actual customer workflow and connected systems.

  • NeMo Guardrails

    NVIDIA · Guardrail library · Developers

    Adds configurable controls around conversational applications. Assess how these controls interact with tool authorization; response filtering alone does not grant or revoke permission.

  • Testing policies with OPA

    OPA · Testing tutorial · Developers

    Write tests for policy decisions. Include permitted requests, boundary values, missing attributes and prohibited actions before connecting a policy to a live tool.

Back to categories

Evidence, tracing and observability

Observability helps a team see what happened. It does not replace approval controls or a protected record from the system that completed the transaction.

  • Logging Cheat Sheet

    OWASP · Implementation guide · Engineering and security

    Guidance on useful event records, sensitive-data exclusions and log protection. Use it when deciding what evidence to retain and who may read or alter it.

  • Langfuse documentation

    Langfuse · Observability and evaluation software · Developers

    Inspect application traces and evaluation workflows. Review hosting, access and data-capture settings before sending customer content to an observability service.

  • Arize Phoenix documentation

    Arize · Observability and evaluation software · Developers

    Trace and evaluate AI application behavior. Useful for investigating where a workflow diverged, alongside authoritative business-system records.

Back to categories

Retries, identity and reliable execution

A timeout does not prove that an action failed. Duplicate-action protection must cover the actual operation, and any retry must remain within current evidence, permissions and approval.

  • Stripe idempotent requests

    Stripe · API reference · Payment integration engineers

    Explains Stripe's rules for repeating a request with an idempotency key. Use the documented rules for the same operation; creating a new key can defeat duplicate protection.

  • Stripe advanced error handling

    Stripe · Integration guide · Payment integration engineers

    Distinguishes error types and discusses uncertain outcomes. Useful for designing status investigation, bounded retries and accurate pending-versus-completed messages.

  • Making retries safe with idempotent APIs

    AWS Builders' Library · Engineering article · Developers

    Explains request identifiers and the design choices behind safe repeated operations. Apply the ideas with the guarantees of your actual provider.

  • OAuth 2.0 security best current practice

    IETF · RFC 9700 · Identity specialists

    Technical guidance for securing delegated access. Useful when agents act through user-authorized integrations; identity and token checks still need action-level business rules.

Back to categories

Architecture articles and further reading

Read these for design trade-offs and provider-specific patterns, then test their relevance to your own system.

  • Building effective agents

    Anthropic · Engineering article · Product and engineering

    Compares workflows and agents and explains common implementation patterns. Helpful when deciding whether a task needs autonomous action at all.

  • Advanced tool use on the Claude Developer Platform

    Anthropic · Engineering article · Developers

    Explores tool discovery and execution patterns. Use it to understand the capabilities you must constrain; more capable tool use is not the same as broader business authority.

  • Safety and security for AI agents

    Google ADK · Architecture guide · Developers

    Discusses identity, authorization, guardrails, sandboxing and evaluation in ADK. Useful for mapping a written plan to several complementary implementation controls.

Back to categories

Turn reading into a reviewable plan

Choose one action and record its evidence, routine limits, approval route, prohibited behavior, failure handling and recovery owner. Ask your implementation team which system will enforce each boundary and how they will test it.

Build a permission plan or explore the Permission Plan Review service. Found a broken link or a useful original source? Send a resource suggestion.