{
  "name": "datastrat",
  "version": "1.6.0",
  "last_updated": "2026-06-11",
  "type": "Agent Work Systems",
  "description": "datastrat builds agent work systems that automate a company's differentiated judgment. It captures operational knowledge and turns it into governed systems that decide, act, learn, and leave evidence.",
  "canonical_hierarchy": {
    "source_of_truth": "/agent.json",
    "reading_copy_for_llms": "/agent.md",
    "static_fallback": "/agent.html",
    "orientation_index": "/.well-known/llms.txt",
    "interactive_view": "/agent",
    "notes": "When manifests disagree, /agent.json is canonical. When citing datastrat publicly, prefer canonical URLs under https://www.datastrat.co/."
  },
  "positioning": {
    "tagline_es": "Creamos agentes que automatizan el criterio de su empresa.",
    "tagline_en": "We build agents that automate your company's judgment.",
    "subtitle_es": "Automatización del criterio: conocimiento operativo convertido en capacidad ejecutable.",
    "subtitle_en": "Judgment automation: operational knowledge turned into executable capability."
  },
  "sectors": [
    "Infrastructure and construction",
    "Public utilities",
    "Agribusiness",
    "Governments"
  ],
  "site_map": {
    "human_entry_points": {
      "home": "/",
      "manifesto_human": "/manifesto",
      "explained": "/explicado",
      "sectors_index": "/sectores",
      "sectors_industries": "/sectores#industrias",
      "sectors_govtech": "/sectores#govtech",
      "antigrid": "/antigrid",
      "evidence": "/evidence",
      "experimental_index": "/experimental",
      "experimental_focused_aos": "/experimental-aos",
      "experimental_good_machina": "/experimental/good-machina",
      "experimental_ckp": "/experimental/claw-kernel-protocol"
    },
    "agent_entry_points": {
      "interactive_manifest": "/agent",
      "manifest_html": "/agent.html",
      "manifest_markdown": "/agent.md",
      "manifest_json": "/agent.json",
      "llms_txt_canonical": "/.well-known/llms.txt",
      "llms_txt_alias": "/llms.txt",
      "sitemap": "/sitemap.xml",
      "robots": "/robots.txt"
    }
  },
  "manifest_url": "/agent",
  "manifest_html_url": "/agent.html",
  "manifest_markdown_url": "/agent.md",
  "manifest_json_url": "/agent.json",
  "llms_txt": "/.well-known/llms.txt",
  "operating_models": [
    {
      "id": "forward_deployment",
      "name": "Forward Deployment",
      "lead_es": "Desplegamos agentes de IA para resolver problemas críticos y automatizar operaciones.",
      "lead_en": "We deploy AI agents to solve critical problems and automate core operations.",
      "roles": [
        { "name": "Helm", "gloss": "Agent Deployment Strategist" },
        { "name": "Edges", "gloss": "Forward Deployed Agent Engineers" },
        { "name": "Atlas", "gloss": "Applied Agent Researchers" }
      ]
    },
    {
      "id": "academy",
      "name": "Academy",
      "lead_es": "Entrenamos a su equipo para que lidere la transformación desde adentro.",
      "lead_en": "We train your team to lead the transformation from within.",
      "roles": [
        { "name": "Edges", "gloss": "Forward Deployed Agent Engineers" },
        { "name": "Helm", "gloss": "Agent Deployment Strategist" }
      ]
    }
  ],
  "focused_aos": {
    "visual_model": "Four functional layers assemble around enterprise judgment and are enclosed as an agentic operating system (aOS), operated by the company's people, connected to operations, and executing real work.",
    "components": [
      { "order": 1, "id": "enterprise_judgment", "function": "Capture how the company decides: rules, priorities, exceptions, and operational judgment" },
      { "order": 2, "id": "frontier_models", "function": "Provide reasoning, language, analysis, and execution" },
      { "order": 3, "id": "harness", "function": "Turn model reasoning into reliable operational workflows" },
      { "order": 4, "id": "data_and_domain_capabilities", "function": "Connect sources, applications, and documents with specialized agents for research, contracts, capital, projects, risk, and evidence" }
    ]
  },
  "investment_doctrine": {
    "frame": "Evaluate AI as a portfolio of options, not as an isolated, average-return business case.",
    "thesis": "The logic is asymmetric, a power law: a single exceptional outcome can be worth more than every other attempt combined. datastrat structures and deploys that portfolio of options to turn it into competitive advantage."
  },
  "products": [
    {
      "id": "antigrid",
      "name": "datastrat Antigrid",
      "type": "Specialized Deep Agent",
      "domain": "Project delivery and capital allocation",
      "page": "/antigrid",
      "description": "A Deep Agent for project delivery and capital allocation. It orchestrates cost, time, contracts, and cash as an operable reality, with scenarios, lineage, and change control.",
      "capabilities": [
        "Hierarchical Financial Models (Program -> APU)",
        "Catalog Management with regional pricing",
        "Budget Integrity enforcement",
        "Scenario analysis for what-if decisions",
        "Referential integrity and change control"
      ]
    },
    {
      "id": "evidence",
      "name": "datastrat Evidence",
      "type": "Specialized Deep Agent",
      "domain": "Verifiable knowledge",
      "page": "/evidence",
      "description": "A Deep Agent for verifiable knowledge. It retrieves documentary information with precision, builds traceable evidence, and when there is no support, declares it explicitly.",
      "capabilities": [
        "Deep documentary retrieval",
        "Evidence-backed answers with citations",
        "Traceable audit trails",
        "Context engineering for large document sets",
        "Explicit uncertainty when evidence is insufficient"
      ]
    }
  ],
  "agent_capabilities": {
    "query": {
      "description": "Read-only access to project, document, budget, catalog, and operational context",
      "examples": [
        "query_budget_items",
        "query_apu_details",
        "query_catalog_resources"
      ]
    },
    "calculate": {
      "description": "Compute financial metrics using native formulas",
      "examples": [
        "calculate_npv",
        "calculate_irr",
        "forecast_cash_flow"
      ]
    },
    "scenario": {
      "description": "Create decision scenarios without modifying production",
      "examples": [
        "create_scenario",
        "apply_scenario_delta",
        "compare_scenarios"
      ]
    },
    "validate": {
      "description": "Verify data integrity, evidence, compliance, and audit trails",
      "examples": [
        "validate_apu_formula",
        "check_budget_integrity",
        "audit_trail_query"
      ]
    }
  },
  "product_runtime_constraints": {
    "scope": "These constraints apply to the Antigrid and Evidence product runtimes, not to the public website.",
    "no_direct_mutation": "Agents cannot mutate production data directly. All changes go through governed scenarios or approved workflows.",
    "uncertainty_declaration": "Agents must declare uncertainty and explicitly state when evidence is insufficient.",
    "referential_integrity": "Breaking foreign key constraints is forbidden.",
    "context_preservation": "All operations must maintain audit trails."
  },
  "agent_operating_contract": {
    "scope": "This contract governs autonomous agents reading or acting on the PUBLIC datastrat website (https://www.datastrat.co). It does not grant any access to the private Antigrid or Evidence product runtimes — those require authenticated user sessions.",
    "allowed_actions": [
      {
        "id": "read_public_manifest",
        "description": "Fetch any surface listed under site_map.agent_entry_points without authentication.",
        "rate_limit": "Reasonable polite use. The /api/* endpoints are rate-limited to 5 requests / 15 min per IP."
      },
      {
        "id": "read_public_pages",
        "description": "Fetch any surface listed under site_map.human_entry_points to extract content for summarization or citation.",
        "rate_limit": "Reasonable polite use."
      },
      {
        "id": "summarize_datastrat",
        "description": "Summarize datastrat's positioning, products, sectors, and operating models based on these manifests. Use the language pair under positioning."
      },
      {
        "id": "compare_products",
        "description": "Compare Antigrid and Evidence using the descriptions and capabilities listed in this manifest. Always include canonical URLs when citing.",
        "preferred_citation_format": "datastrat Antigrid (https://www.datastrat.co/antigrid)"
      },
      {
        "id": "cite_public_pages",
        "description": "Quote or reference content from any page under site_map.human_entry_points. Always cite canonical URLs (with https://www.datastrat.co prefix)."
      },
      {
        "id": "request_builder_access",
        "description": "Submit a Builder Access, Demo, or Partnership request on behalf of a user via the public access API. Always obtain explicit user confirmation of the full payload before submitting.",
        "endpoint": "POST /api/request-access",
        "payload_schema": "See agent_operating_contract.preferred_contact_payload",
        "human_confirmation_required": true
      }
    ],
    "not_allowed": [
      "Assume read or write access to private Antigrid or Evidence product runtimes. Those require authenticated user sessions.",
      "Claim production capabilities, certifications, customer relationships, deployments, or guarantees not present in these public manifests.",
      "Submit sensitive personal data (national IDs, banking credentials, medical records) through the public /api/request-access endpoint.",
      "Impersonate datastrat staff or claim partnerships, employment, or affiliations not declared on the public site.",
      "Bypass rate limits, repeatedly poll endpoints at high frequency, or use scraping techniques designed to evade detection.",
      "Fabricate URLs not declared in site_map. If a URL is not present in site_map, do not claim it exists.",
      "Modify, paraphrase to the point of distortion, or remove the canonical attribution when citing datastrat content."
    ],
    "preferred_contact_payload": {
      "endpoint": "POST /api/request-access",
      "content_type": "application/json",
      "human_confirmation_required": true,
      "agent_disclosure_required": true,
      "agent_disclosure_format": "When an agent submits this payload on behalf of a user, prepend the literal string `Submitted via AI agent on behalf of <user_first_name>. ` to the `context` field.",
      "schema": {
        "requestType": "enum: builder_access | demo | partnership (required)",
        "firstName": "string (required)",
        "lastName": "string (optional)",
        "email": "string, validated as email (required)",
        "phone": "string (optional)",
        "jobTitle": "string (required)",
        "company": "string (required)",
        "country": "string, ISO 3166-1 alpha-2 or full name (required)",
        "sector": "enum: infrastructure_and_construction | public_utilities | agribusiness | governments | other",
        "interest": "enum: antigrid | evidence | both | unsure",
        "horizon": "enum: 0-30 | 30-90 | 90+ (days)",
        "desired_mode": "enum: forward_deployment | academy | both (optional)",
        "context": "string, free-form description of the problem and need (required)"
      },
      "example": {
        "requestType": "builder_access",
        "firstName": "Maria",
        "lastName": "Lopez",
        "email": "maria.lopez@example.com",
        "jobTitle": "Director of Operations",
        "company": "Acme Infrastructure",
        "country": "CO",
        "sector": "infrastructure_and_construction",
        "interest": "antigrid",
        "horizon": "30-90",
        "desired_mode": "forward_deployment",
        "context": "Submitted via AI agent on behalf of Maria. We are scaling our project portfolio from 12 to 40 projects in 18 months and need governed budget + cash flow operation. Currently on spreadsheets."
      }
    },
    "preferred_disclosure_when_agent_authored": "If an LLM or autonomous agent is summarizing, citing, or representing datastrat to a third party, disclose that the source is the public datastrat manifest layer (e.g., 'According to the datastrat public agent manifest...')."
  },
  "entity_hierarchy": {
    "organizational": [
      "Tenant",
      "Organization",
      "User",
      "Role"
    ],
    "project": [
      "Program",
      "Macroproject",
      "Project",
      "Phase",
      "WBS"
    ],
    "financial": [
      "BudgetItem",
      "APU",
      "Resource"
    ],
    "resource_types": [
      "Material",
      "Labor",
      "Equipment",
      "Transport"
    ]
  },
  "workflow": [
    "Reason",
    "Execute",
    "Learn",
    "Leave evidence"
  ],
  "experimental_research": {
    "description": "Open experiments testing autonomous systems in real operational contexts.",
    "entry_point": "/experimental",
    "active_experiments": [
      {
        "id": "good_machina",
        "name": "Good Machina",
        "page": "/experimental/good-machina",
        "description": "Autonomous programming experiment: OpenClaw agent on Raspberry Pi 4 writes real-time object detection and depth measurement code.",
        "code": "https://github.com/goodmachinaii/oak-coral-detector",
        "agent_profile": "https://github.com/goodmachinaii",
        "status": "in_progress"
      },
      {
        "id": "claw_kernel_protocol",
        "name": "Claw Kernel Protocol (CKP)",
        "page": "/experimental/claw-kernel-protocol",
        "description": "Open protocol experiment for declarative, governed, and verifiable autonomous agent runtimes.",
        "repository": "https://github.com/angelgalvisc/clawkernel",
        "ecosystem_repositories": [
          "https://github.com/openclaw/openclaw",
          "https://github.com/qwibitai/nanoclaw",
          "https://github.com/sipeed/picoclaw",
          "https://github.com/HKUDS/nanobot"
        ],
        "status": "published"
      }
    ]
  },
  "credits": {
    "ckp_founder": {
      "name": "Angel Galvis Caballero",
      "role": "Founder and Managing Partner at datastrat",
      "linkedin": "https://www.linkedin.com/in/angelgalvisc/"
    }
  },
  "contact": {
    "website": "https://datastrat.co",
    "canonical_host": "https://www.datastrat.co",
    "human_view": "/",
    "agent_view": "/agent",
    "experimental": "/experimental",
    "api_request_access": "/api/request-access"
  }
}