v1.0 — Now Available

Guardrails

The conscience layer for autonomous agents.

A structured, queryable REST API that gives AI agents access to a user's beliefs, worldview, values, and faith-based preferences — so agents can make decisions aligned with who that person actually is.

Agents don't know who you are.

AI agents are making decisions on behalf of humans — without understanding what those humans believe, value, or practice.

✈️

Sabbath Observance

An agent booking travel doesn't know about Shabbat. It optimizes for price, not for arriving before sundown on Friday.

🥩

Dietary Laws

An agent ordering groceries doesn't know about halal restrictions. It picks the cheapest option, not the permissible one.

💰

Islamic Finance

An agent managing investments doesn't know about riba prohibition. It maximizes returns without regard for ethical screens.

⚖️

Moral Framework

An agent making ethical trade-offs doesn't know if you're a deontologist or utilitarian. It has no moral compass to reference.

Guardrails fills this gap.

A complete map of what matters.

Every Guardrails profile organizes a person's values across seven structured domains — queryable independently or together.

🕌

Faith & Religious Practice

Prayer schedules, holy days, dietary laws, tithing rules, and sacred time boundaries.

⚖️

Moral Framework

Ethical orientation, moral foundations scores, and decision-making principles.

🌍

Cultural Identity

Heritage, language preferences, cultural celebrations, and community obligations.

🧘

Lifestyle Commitments

Veganism, minimalism, sustainability pledges, and daily routines.

📊

Financial Ethics

Interest policies, investing screens, charitable giving, and debt philosophy.

🏥

Medical & End-of-Life

Advance directives, blood transfusion preferences, organ donation, and care priorities.

🗳️

Political & Social Values

Social issue stances, policy priorities, activism, and civic engagement.

Seven endpoints. One conscience.

Simple, predictable REST endpoints. JSON in, JSON out. Authenticated with bearer tokens and user consent.

Method Endpoint Description Cost
GET /v1/profiles/{user_id} Get Full Profile $0.05
GET /v1/profiles/{user_id}/domains/{domain} Query Single Domain $0.01
GET /v1/profiles/{user_id}/check Compatibility Check $0.005
POST /v1/profiles/{user_id}/decide Decision Support $0.10 at base tier
GET /v1/profiles/{user_id}/calendar Faith-Aware Calendar $0.02
POST /v1/profiles Create Profile $0.005
GET /v1/taxonomies/{domain} Get Taxonomies $0.005

Try it. Right now.

Click "Run Request" to see how Guardrails responds. These are realistic mock responses showing the API in action.

Request

GET /v1/profiles/usr_demo/check?query=halal&item=beef_jerky_brand_x

Response

Click "Run Request" to see the response
200 OK · 47ms

Request

POST /v1/profiles/usr_demo/decide

Body

Response

Click "Run Request" to see the response
200 OK · 132ms

Request

GET /v1/profiles/usr_demo/domains/financial_ethics

Response

Click "Run Request" to see the response
200 OK · 23ms

Request

GET /v1/profiles/usr_demo

Response

Click "Run Request" to see the response
200 OK · 89ms

How agents consume Guardrails.

Guardrails is a standard REST API with a comprehensive OpenAPI specification. Any AI agent — regardless of platform — can use it.

OpenAI / GPT

Function Calling

Import our OpenAPI spec as function definitions. GPT agents call Guardrails endpoints via tool-use.

Anthropic / Claude

Tool Use

Define Guardrails endpoints as tools. Claude's tool-use calls our REST API directly.

Salesforce Agentforce

External Service

Register Guardrails as an External Service via our OpenAPI spec. Available to any Agentforce topic.

Any Agent

REST + JSON

If your agent can make HTTP requests, it can use Guardrails. No SDK required. No protocol lock-in.

Why REST + OpenAPI? We chose REST + OpenAPI because it's the universal layer. MCP, A2A, ACP, and future protocols are all consumption wrappers around HTTP APIs. By building on REST, Guardrails is automatically compatible with every current and future agent protocol.

The spec is the product.

A well-documented OpenAPI 3.1 spec that any agent platform can consume directly.

openapi.yaml YAML
openapi: 3.1.0 info: title: Guardrails API version: 1.0.0 description: The conscience layer for autonomous agents. servers: - url: https://api.useguardrails.com/v1 paths: /profiles/{user_id}: get: operationId: getProfile summary: Get a user's full Guardrails profile /profiles/{user_id}/domains/{domain}: get: operationId: getDomain summary: Query a single domain /profiles/{user_id}/check: get: operationId: checkCompatibility summary: Quick compatibility check /profiles/{user_id}/decide: post: operationId: getDecision summary: Values-aligned decision support /profiles/{user_id}/calendar: get: operationId: getCalendar summary: Faith-aware calendar /profiles: post: operationId: createProfile summary: Create a new profile /taxonomies/{domain}: get: operationId: getTaxonomy summary: Get domain options

Pay per call. No subscriptions.

Every API call is metered. The more you use, the less you pay per call. No monthly fees, no commitments.

Monthly API Calls Per-Call Rate Estimated Monthly Cost
1 – 10,000 $0.02 $0.02 – $200
10,001 – 100,000 $0.015 $150 – $1,500
500,001 – 1,000,000 $0.007 $3,500 – $7,000
1,000,001+ $0.005 Contact us

How it works

Every API call is billed at the rate for your current monthly volume tier. As your usage grows within a billing cycle, your per-call rate automatically decreases.

Decision support calls

The /decide endpoint uses AI reasoning and costs 5x the standard per-call rate for your tier (e.g., $0.10 at the base tier).

Enterprise

Need custom volume pricing, SLAs, on-prem deployment, or dedicated support? contact@useguardrails.com

Every domain, endpoint, and use case.

Deep-dive into how Guardrails works across 7 value domains, 7 API endpoints, and 12 real-world use cases.

Value Domains

🕌

Faith & Religious Practice

Prayer schedules, holy days, dietary laws, tithing rules, and sacred time boundaries.

⚖️

Moral Framework

Ethical orientation, moral foundations scores, and decision-making principles.

🌍

Cultural Identity

Heritage, language preferences, cultural celebrations, and community obligations.

🧘

Lifestyle Commitments

Veganism, minimalism, sustainability pledges, and daily routines.

📊

Financial Ethics

Interest policies, investing screens, charitable giving, and debt philosophy.

🏥

Medical & End-of-Life

Advance directives, blood transfusion preferences, organ donation, and care priorities.

🗳️

Political & Social Values

Social issue stances, policy priorities, activism, and civic engagement.

API Endpoints

GET

Get Full Profile

Retrieve a user's complete Guardrails profile across all permitted domains.

GET

Query Single Domain

Retrieve data from one specific domain of a user's profile.

GET

Compatibility Check

Quick yes/no check if a product, service, or action is compatible with a user's values.

POST

Decision Support

Pass a scenario with options and get a values-aligned recommendation.

GET

Faith-Aware Calendar

Get a user's upcoming religious observances, blocked times, and holy days.

POST

Create Profile

Create a new Guardrails profile for a user.

GET

Get Taxonomies

Retrieve the structured taxonomy of options for a specific domain.

Use Cases

🛒

Halal Grocery Shopping

An AI grocery agent that automatically filters products by halal certification.

✈️

Shabbat-Aware Travel Booking

A travel agent that respects Sabbath boundaries when booking flights and hotels.

💰

ESG Investment Screening

A financial agent that screens investments against the user's ethical filters.

🏥

End-of-Life Care Planning

A healthcare agent that honors patient values in advance directive decisions.

🥗

Vegan Meal Planning

A meal-planning agent that respects dietary philosophy and sustainability goals.

📅

Prayer-Aware Scheduling

A calendar agent that blocks prayer times and religious observances automatically.

💬

Culturally Sensitive Communication

An AI assistant that adapts tone, greetings, and formality to cultural norms.

🛡️

Ethical AI Content Moderation

A content moderation agent that applies the user's personal moral standards.

❤️

Charitable Giving Automation

A giving agent that schedules donations aligned with faith and financial commitments.

♻️

Sustainable Shopping Agent

A shopping agent that enforces sustainability pledges on every purchase.

🎉

Multi-Faith Event Planning

An event-planning agent that respects every attendee's dietary and scheduling constraints.

📰

Values-Aligned News Curation

A news agent that curates content based on the user's actual values, not engagement metrics.