# Regulatory Intelligence API - AI Compliance Radar (`ai_solutionist/regulatory-intelligence-api`) Actor The compliance radar AI agents trust. Extract structured requirements, deadlines, and compliance checklists from Federal Register, regulations.gov, and state regulations. - **URL**: https://apify.com/ai\_solutionist/regulatory-intelligence-api.md - **Developed by:** [Jason Pellerin](https://apify.com/ai_solutionist) (community) - **Categories:** AI, Lead generation, Developer tools - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 1 bookmarks - **User rating**: No ratings yet ## Pricing from $2.00 / 1,000 results This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Regulatory Intelligence API **The compliance radar AI agents trust.** Extract structured requirements, deadlines, penalties, and compliance checklists from the Federal Register, regulations.gov, and state regulatory sources. Built for **Colorado SB 25B-004** compliance and AI agent workflows. [![Apify Actor](https://img.shields.io/badge/Apify-Actor-blue)](https://apify.com/ai-solutionist/regulatory-intelligence-api) [![License](https://img.shields.io/badge/License-ISC-green)](LICENSE) --- ### Why Regulatory Intelligence API? #### The Problem AI Agents Face AI agents providing business advice operate in a **regulatory blind spot**: - Federal Register publishes **70,000+ pages annually** of rules, notices, and guidance - Regulations.gov hosts **millions** of documents across **300+ agencies** - State regulations add another layer of complexity (50 states, 50 systems) - **Training data is stale** - new regulations appear daily - **Hallucination risk** - without grounded data, AI gives dangerous compliance advice #### The Solution: Grounded Regulatory Intelligence Regulatory Intelligence API transforms raw regulatory data into **structured, citation-ready intelligence** that AI agents can trust: ✅ **Grounded Facts** - Every requirement has a citation ✅ **Compliance Checklists** - Actionable items, not legal jargon ✅ **Deadline Tracking** - Never miss an effective date or comment period ✅ **Penalty Intelligence** - Know the stakes ✅ **RAG-Ready Chunks** - Optimized for vector databases ✅ **Bluebook Citations** - Legal-standard sourcing --- ### Colorado SB 25B-004 Compliance Ready **Effective June 30, 2026**, Colorado's AI Transparency Act requires AI systems to: - Disclose when AI is being used in high-risk decisions - Provide explanations of how AI reached conclusions - Enable human review of AI-assisted decisions - Maintain audit trails of AI decision-making Regulatory Intelligence API helps you comply by: - **Tracking SB 25B-004** and related state AI regulations - **Providing citation chains** for every extracted requirement - **Generating audit-ready provenance** for all data - **Creating compliance checklists** for implementation --- ### Task Modes Choose the right mode for your workflow: | Mode | Description | Best For | |------|-------------|----------| | `federal_register` | Track proposed and final rules from the Federal Register | Monitoring federal rulemaking | | `regulations_gov` | Extract dockets, comments, and supporting materials | Deep regulatory research | | `agency_guidance` | Collect guidance documents from specific agencies | Understanding agency interpretation | | `compliance_monitor` | Diff-based change detection against baseline | Ongoing compliance surveillance | | `deadline_tracker` | Extract all dates and compliance deadlines | Calendar and project planning | | `impact_analysis` | Analyze who/what is affected by regulations | Risk assessment | | `state_regulations` | Multi-state regulatory tracking | Multi-jurisdictional compliance | | `full_intelligence` | Comprehensive extraction (all features) | Complete regulatory picture | --- ### Output Schema Every run produces a **Regulatory Intelligence Pack** with structured data: ```json { "runId": "abc123def456", "taskMode": "federal_register", "extractedAt": "2026-01-28T12:00:00.000Z", "regulation": { "id": "2026-01234", "title": "Artificial Intelligence Transparency Requirements", "agency": "Federal Trade Commission", "agencyAcronym": "FTC", "documentType": "proposed_rule", "status": "proposed", "federalRegisterNumber": "2026-01234", "cfrReferences": ["16 CFR 314"], "publicationDate": "2026-01-15", "effectiveDate": null, "commentDeadline": "2026-03-15", "sourceUrl": "https://www.federalregister.gov/documents/2026/01234" }, "requirements": [ { "id": "REQ-202601234-001", "requirement": "Covered entities must disclose to consumers when AI is used in consequential decisions.", "legalText": "Each covered entity shall provide clear and conspicuous disclosure...", "citation": "16 CFR 314.5(a)", "category": "disclosure", "mandatoryLevel": "required", "deadline": "180 days after effective date", "affectedParties": ["corporations", "small businesses"], "exceptions": ["Entities with fewer than 50 employees"], "confidence": 0.92 } ], "deadlines": [ { "date": "2026-03-15", "dateType": "comment_deadline", "description": "Public comment period closes", "context": "Comments must be received on or before March 15, 2026", "isEstimated": false }, { "date": "2026-07-01", "dateType": "effective_date", "description": "Rule becomes effective", "context": "This rule is effective July 1, 2026", "isEstimated": false } ], "penalties": [ { "penaltyType": "civil_monetary", "amount": "$50,000", "amountNumeric": 50000, "perViolation": true, "maxPenalty": "$1,000,000 per proceeding", "triggeringViolation": "Failure to provide required disclosure", "enforcementAgency": "FTC", "citation": "16 CFR 314.10" } ], "affectedParties": { "industries": ["Technology (51)", "Finance (52)", "Healthcare (62)"], "entityTypes": ["corporations", "small_business"], "employeeThresholds": { "minimum": 50, "description": "50 or more employees" }, "geographicScope": "national", "exemptions": ["Nonprofits", "Government entities"], "estimatedAffectedEntities": 125000 }, "complianceChecklist": [ { "checklistId": "CHK-001", "action": "Conduct gap analysis comparing current AI disclosure practices to new requirements", "category": "audit", "priority": "high", "deadline": "2026-07-01", "responsibleRole": "Compliance Officer", "relatedRequirements": ["REQ-202601234-001"], "verificationMethod": "Gap analysis report" }, { "checklistId": "CHK-002", "action": "Implement AI disclosure process for consumer-facing decisions", "category": "process", "priority": "critical", "deadline": "2026-07-01", "responsibleRole": "Legal/Compliance Officer", "relatedRequirements": ["REQ-202601234-001"], "verificationMethod": "Review disclosure documents and processes" } ], "citations": { "bluebook": "FTC, Artificial Intelligence Transparency Requirements, 91 Fed. Reg. [page] (proposed Jan. 15, 2026) (to be codified at 16 C.F.R. pt. 314).", "apa": "Federal Trade Commission. (2026). Artificial Intelligence Transparency Requirements. Federal Register. Retrieved January 28, 2026, from https://www.federalregister.gov/documents/2026/01234", "mla": "\"Artificial Intelligence Transparency Requirements.\" Federal Trade Commission, January 15, 2026, https://www.federalregister.gov/documents/2026/01234. Accessed January 28, 2026.", "chicago": "Federal Trade Commission. \"Artificial Intelligence Transparency Requirements.\" Federal Register. January 15, 2026. Accessed January 28, 2026. https://www.federalregister.gov/documents/2026/01234.", "inline": "[AI Transparency Requirements](https://www.federalregister.gov/documents/2026/01234) (accessed 2026-01-28)", "bibtex": "@misc{fr_2026_01234, title={Artificial Intelligence Transparency Requirements}, author={{Federal Trade Commission}}, year={2026}, journal={Federal Register}, volume={91}, url={https://www.federalregister.gov/documents/2026/01234}, type={Proposed Rule}}" }, "chunks": [ { "id": "2026-01234_summary", "text": "# Artificial Intelligence Transparency Requirements\n\n**Agency:** Federal Trade Commission...", "tokenCount": 687, "chunkType": "summary", "metadata": { "regulationId": "2026-01234", "title": "Artificial Intelligence Transparency Requirements", "agency": "Federal Trade Commission", "section": "Summary", "position": 0, "totalChunks": 12 } } ], "quality": { "overallScore": 88, "completeness": 92, "extractionConfidence": 87, "citationCoverage": 95, "requirementsCoverage": 78 }, "agentSummary": { "oneLiner": "FTC proposed rule requiring AI transparency disclosures for consumer-facing decisions, effective July 2026.", "keyRequirements": [ "Disclose AI use in consequential decisions", "Provide explanation of AI decision factors", "Maintain audit trail of AI decisions" ], "criticalDeadlines": [ { "date": "2026-03-15", "description": "Comment deadline" }, { "date": "2026-07-01", "description": "Effective date" } ], "riskLevel": "high", "actionRequired": true, "recommendedActions": [ "Submit comments before March 15, 2026", "Conduct compliance gap analysis", "Brief legal/compliance team" ], "topicTags": ["ai", "consumer", "privacy"] }, "langchainMetadata": { "source": "https://www.federalregister.gov/documents/2026/01234", "regulation_id": "2026-01234", "agency": "Federal Trade Commission", "document_type": "Proposed Rule", "effective_date": null, "status": "proposed", "topics": ["ai", "consumer", "privacy"], "requirements_count": 5, "has_penalties": true, "quality_score": 88, "content_hash": "sha256:a1b2c3d4..." }, "provenance": { "fetchedAt": "2026-01-28T12:00:00.000Z", "sourceUrl": "https://www.federalregister.gov/documents/2026/01234", "httpStatus": 200, "contentHash": "sha256:a1b2c3d4...", "extractionVersion": "1.0.0" } } ```` *** ### Use Cases #### 1. GovCon Compliance Intelligence Government contractors need to track regulatory changes affecting their contracts: ```javascript const input = { taskMode: "federal_register", searchQuery: "government contractor disclosure", agencies: ["GSA", "DOD", "OMB"], topics: ["government_contracts"], dateRange: "30d", generateChecklist: true }; ``` #### 2. AI Compliance Monitoring Track AI-related regulations across federal agencies: ```javascript const input = { taskMode: "full_intelligence", searchQuery: "artificial intelligence machine learning algorithmic", agencies: ["FTC", "EEOC", "HHS", "DOL"], topics: ["artificial_intelligence", "data_privacy"], dateRange: "90d", extractRequirements: true, extractPenalties: true }; ``` #### 3. Multi-State Regulatory Tracking Monitor state regulations affecting your operations: ```javascript const input = { taskMode: "state_regulations", searchQuery: "AI transparency disclosure", states: ["CO", "CA", "NY", "TX"], topics: ["artificial_intelligence", "consumer_protection"] }; ``` #### 4. Compliance Change Detection Monitor for changes to regulations you're already tracking: ```javascript const input = { taskMode: "compliance_monitor", searchQuery: "16 CFR 314", baselineRunId: "previous-run-id", extractRequirements: true }; ``` #### 5. Legal Research RAG Pipeline Feed regulatory data into your vector database: ```javascript const input = { taskMode: "federal_register", searchQuery: "healthcare data privacy HIPAA", outputFormat: "rag_only", ragChunkSize: 750, includeLegalCitations: true }; ``` *** ### Integration Examples #### LangChain Integration ```python from langchain.document_loaders import ApifyDatasetLoader from langchain.vectorstores import Pinecone from langchain.embeddings import OpenAIEmbeddings ## Load regulatory data from Apify loader = ApifyDatasetLoader( dataset_id="your-dataset-id", dataset_mapping_function=lambda item: Document( page_content=item["chunks"][0]["text"], metadata=item["langchainMetadata"] ) ) docs = loader.load() ## Index in Pinecone vectorstore = Pinecone.from_documents( docs, OpenAIEmbeddings(), index_name="regulatory-intelligence" ) ``` #### n8n Workflow Integration Use with our companion n8n node for automated compliance workflows: 1. Install: `npm install n8n-nodes-regulatory-intelligence` 2. Configure Apify credentials 3. Add to your compliance monitoring workflow #### Direct API Usage ```bash curl -X POST "https://api.apify.com/v2/acts/ai-solutionist~regulatory-intelligence-api/runs" \ -H "Authorization: Bearer YOUR_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "taskMode": "federal_register", "searchQuery": "artificial intelligence", "maxResults": 10 }' ``` *** ### Supported Sources #### Federal Sources - **Federal Register** - All document types (rules, proposed rules, notices) - **Regulations.gov** - Dockets, comments, supporting materials - **Agency Websites** - Guidance documents, FAQs, enforcement actions #### State Sources (Expanding) - **Colorado** - SB 25B-004 and related AI regulations - **California** - CCPA, CPRA, AB 2013 - **New York** - NYC Local Law 144, proposed AI regulations - **Texas** - Data privacy and AI-related rules - **Florida** - Consumer protection regulations #### International (Coming Soon) - **EU AI Act** - Risk-based AI requirements - **UK AI Framework** - Pro-innovation approach - **Canada AIDA** - AI and Data Act *** ### Pricing | Feature | Free Tier | Pro | Enterprise | |---------|-----------|-----|------------| | Federal Register | 10/month | Unlimited | Unlimited | | Regulations.gov | 5/month | Unlimited | Unlimited | | State Regulations | - | 3 states | All states | | Change Detection | - | ✓ | ✓ | | API Access | - | ✓ | ✓ | | Priority Support | - | - | ✓ | *** ### Quality & Accuracy #### Extraction Quality Metrics Every result includes quality scores: - **Completeness** - Percentage of expected fields populated - **Extraction Confidence** - Average confidence of requirement extraction - **Citation Coverage** - Percentage of requirements with source citations - **Requirements Coverage** - Estimated completeness vs document content #### Validation - Cross-reference with official Federal Register API - Citation verification against CFR - Continuous monitoring for extraction accuracy *** ### Support & Resources - **Documentation**: [Full API Documentation](https://apify.com/ai-solutionist/regulatory-intelligence-api) - **GitHub**: [Source Code & Issues](https://github.com/aisolutionist/regulatory-intelligence-api) - **Discord**: [Community Support](https://discord.gg/aisolutionist) - **Email**: jason@jasonpellerin.com *** ### Built By **AI Solutionist** - Building the infrastructure for trustworthy AI *"The compliance radar AI agents trust"* *** ### License ISC License - See [LICENSE](LICENSE) for details. *** ### Keywords `regulatory compliance` `federal register` `regulations.gov` `AI compliance` `SB 25B-004` `Colorado AI law` `FTC regulations` `SEC compliance` `HIPAA` `GovCon` `government contractor` `RAG` `LangChain` `vector database` `compliance automation` `regulatory monitoring` `legal citations` `Bluebook` `CFR` `rulemaking` # Actor input Schema ## `taskMode` (type: `string`): Optimized presets for different regulatory intelligence workflows. Each mode extracts different data and structures output for specific use cases. ## `searchQuery` (type: `string`): Keywords to search for in regulations. Supports boolean operators (AND, OR, NOT). Examples: 'artificial intelligence', 'AI transparency disclosure', 'healthcare data privacy' ## `agencies` (type: `array`): Filter by specific federal agencies. Common agencies: FTC, FDA, SEC, HHS, DOL, EPA, FCC, CFPB, OSHA. Leave empty for all agencies. ## `regulationTypes` (type: `array`): Filter by type of regulatory document ## `dateRange` (type: `string`): How far back to search for regulations ## `states` (type: `array`): US states to include for state regulation tracking. Use 2-letter codes (CO, CA, NY, TX, FL). Currently supports select states with more coming. ## `topics` (type: `array`): Filter by regulatory topic areas ## `baselineRunId` (type: `string`): Previous run ID to compare against for change detection. Leave empty for first run. ## `maxResults` (type: `integer`): Maximum number of regulations to extract per source ## `extractRequirements` (type: `boolean`): Parse and structure specific compliance requirements from regulation text ## `extractDeadlines` (type: `boolean`): Extract all dates, deadlines, and effective dates with context ## `extractPenalties` (type: `boolean`): Extract penalty amounts, enforcement mechanisms, and violation consequences ## `extractAffectedParties` (type: `boolean`): Identify who/what entities are affected by the regulation ## `generateChecklist` (type: `boolean`): Create actionable compliance checklist from requirements ## `ragChunkSize` (type: `integer`): Target token count for RAG chunks. Optimized for embedding models and vector databases. ## `includeLegalCitations` (type: `boolean`): Generate Bluebook-style legal citations for all regulations ## `includeAgentSummary` (type: `boolean`): Generate one-liner summaries optimized for AI agent consumption ## `outputFormat` (type: `string`): Structure of the output data ## `proxyConfiguration` (type: `object`): Configure proxy for accessing regulatory sources (advanced) ## Actor input object example ```json { "taskMode": "federal_register", "searchQuery": "artificial intelligence", "agencies": [], "regulationTypes": [ "proposed_rule", "final_rule" ], "dateRange": "30d", "states": [ "CO", "CA", "NY" ], "topics": [ "artificial_intelligence" ], "maxResults": 50, "extractRequirements": true, "extractDeadlines": true, "extractPenalties": true, "extractAffectedParties": true, "generateChecklist": true, "ragChunkSize": 750, "includeLegalCitations": true, "includeAgentSummary": true, "outputFormat": "full" } ``` # Actor output Schema ## `runId` (type: `string`): Unique identifier for this extraction run ## `taskMode` (type: `string`): Task mode used for extraction ## `regulationTitle` (type: `string`): Official regulation title ## `agency` (type: `string`): Issuing agency name ## `documentType` (type: `string`): Type: proposed\_rule, final\_rule, notice ## `publicationDate` (type: `string`): Date published ## `effectiveDate` (type: `string`): When the regulation takes effect ## `commentDeadline` (type: `string`): Deadline for public comments ## `sourceUrl` (type: `string`): Direct URL to official source ## `summary` (type: `string`): Official agency summary ## `bluebookCitation` (type: `string`): Bluebook legal citation format ## `apaCitation` (type: `string`): APA format citation ## `inlineCitation` (type: `string`): Inline markdown citation ## `qualityScore` (type: `string`): Overall quality score (0-100) ## `oneLinerSummary` (type: `string`): AI agent one-liner summary ## `riskLevel` (type: `string`): Compliance risk level: low, medium, high ## `actionRequired` (type: `string`): Whether immediate action is required ## `requirementsCount` (type: `string`): Number of requirements extracted ## `deadlinesCount` (type: `string`): Number of deadlines found ## `chunksCount` (type: `string`): Number of RAG chunks generated ## `contentHash` (type: `string`): SHA-256 hash for change detection ## `processingTimeMs` (type: `string`): Processing time in milliseconds # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "searchQuery": "artificial intelligence", "agencies": [], "states": [ "CO", "CA", "NY" ] }; // Run the Actor and wait for it to finish const run = await client.actor("ai_solutionist/regulatory-intelligence-api").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "searchQuery": "artificial intelligence", "agencies": [], "states": [ "CO", "CA", "NY", ], } # Run the Actor and wait for it to finish run = client.actor("ai_solutionist/regulatory-intelligence-api").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "searchQuery": "artificial intelligence", "agencies": [], "states": [ "CO", "CA", "NY" ] }' | apify call ai_solutionist/regulatory-intelligence-api --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=ai_solutionist/regulatory-intelligence-api", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Regulatory Intelligence API - AI Compliance Radar", "description": "The compliance radar AI agents trust. Extract structured requirements, deadlines, and compliance checklists from Federal Register, regulations.gov, and state regulations.", "version": "1.0", "x-build-id": "gZFyqugmLE7RUuXK3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ai_solutionist~regulatory-intelligence-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ai_solutionist-regulatory-intelligence-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ai_solutionist~regulatory-intelligence-api/runs": { "post": { "operationId": "runs-sync-ai_solutionist-regulatory-intelligence-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ai_solutionist~regulatory-intelligence-api/run-sync": { "post": { "operationId": "run-sync-ai_solutionist-regulatory-intelligence-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "taskMode" ], "properties": { "taskMode": { "title": "Task Mode", "enum": [ "federal_register", "regulations_gov", "agency_guidance", "compliance_monitor", "deadline_tracker", "impact_analysis", "state_regulations", "full_intelligence" ], "type": "string", "description": "Optimized presets for different regulatory intelligence workflows. Each mode extracts different data and structures output for specific use cases.", "default": "federal_register" }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Keywords to search for in regulations. Supports boolean operators (AND, OR, NOT). Examples: 'artificial intelligence', 'AI transparency disclosure', 'healthcare data privacy'" }, "agencies": { "title": "Agencies", "type": "array", "description": "Filter by specific federal agencies. Common agencies: FTC, FDA, SEC, HHS, DOL, EPA, FCC, CFPB, OSHA. Leave empty for all agencies.", "items": { "type": "string" } }, "regulationTypes": { "title": "Regulation Types", "type": "array", "description": "Filter by type of regulatory document", "items": { "type": "string", "enum": [ "proposed_rule", "final_rule", "notice", "guidance", "enforcement", "advisory" ] }, "default": [ "proposed_rule", "final_rule" ] }, "dateRange": { "title": "Date Range", "enum": [ "7d", "30d", "90d", "180d", "1y", "all" ], "type": "string", "description": "How far back to search for regulations", "default": "30d" }, "states": { "title": "States (for state_regulations mode)", "type": "array", "description": "US states to include for state regulation tracking. Use 2-letter codes (CO, CA, NY, TX, FL). Currently supports select states with more coming.", "items": { "type": "string" } }, "topics": { "title": "Topic Categories", "type": "array", "description": "Filter by regulatory topic areas", "items": { "type": "string", "enum": [ "artificial_intelligence", "data_privacy", "cybersecurity", "healthcare", "financial_services", "employment", "environmental", "consumer_protection", "telecommunications", "government_contracts" ] }, "default": [ "artificial_intelligence" ] }, "baselineRunId": { "title": "Baseline Run ID (for compliance_monitor)", "type": "string", "description": "Previous run ID to compare against for change detection. Leave empty for first run." }, "maxResults": { "title": "Maximum Results", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of regulations to extract per source", "default": 50 }, "extractRequirements": { "title": "Extract Requirements", "type": "boolean", "description": "Parse and structure specific compliance requirements from regulation text", "default": true }, "extractDeadlines": { "title": "Extract Deadlines", "type": "boolean", "description": "Extract all dates, deadlines, and effective dates with context", "default": true }, "extractPenalties": { "title": "Extract Penalties", "type": "boolean", "description": "Extract penalty amounts, enforcement mechanisms, and violation consequences", "default": true }, "extractAffectedParties": { "title": "Extract Affected Parties", "type": "boolean", "description": "Identify who/what entities are affected by the regulation", "default": true }, "generateChecklist": { "title": "Generate Compliance Checklist", "type": "boolean", "description": "Create actionable compliance checklist from requirements", "default": true }, "ragChunkSize": { "title": "RAG Chunk Size (tokens)", "minimum": 200, "maximum": 2000, "type": "integer", "description": "Target token count for RAG chunks. Optimized for embedding models and vector databases.", "default": 750 }, "includeLegalCitations": { "title": "Include Legal Citations", "type": "boolean", "description": "Generate Bluebook-style legal citations for all regulations", "default": true }, "includeAgentSummary": { "title": "Include Agent Summary", "type": "boolean", "description": "Generate one-liner summaries optimized for AI agent consumption", "default": true }, "outputFormat": { "title": "Output Format", "enum": [ "full", "compact", "rag_only", "checklist_only" ], "type": "string", "description": "Structure of the output data", "default": "full" }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Configure proxy for accessing regulatory sources (advanced)" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```