datastrat — Agent Manifest

version: 1.6.0 · last_updated: 2026-06-11

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

When manifests disagree, /agent.json is canonical. The other surfaces are derived views.

RoleURLType
Source of truth/agent.jsonJSON
Reading copy for LLMs/agent.mdMarkdown
Static fallback (this)/agent.htmlHTML, no-JS
Orientation index/.well-known/llms.txttext/plain (alias: /llms.txt)
Interactive view/agentReact, requires JS

Entry Points

Human-facing pages

/
/manifesto
/explicado
/sectores
/sectores#industrias
/sectores#govtech
/antigrid
/evidence
/experimental
/experimental-aos
/experimental/good-machina
/experimental/claw-kernel-protocol

Agent-facing surfaces

/agent
/agent.html
/agent.md
/agent.json
/.well-known/llms.txt
/llms.txt
/robots.txt
/sitemap.xml

Target Sectors

Operating Models

01 · Forward Deployment

We deploy AI agents to solve critical problems and automate core operations.

02 · Academy

We train your team to lead the transformation from within, led by Edges and directed by Helm.

Focused aOS Architecture

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.

  1. Enterprise judgment — how the company decides: rules, priorities, exceptions, operational judgment
  2. Frontier models — reasoning, language, analysis, execution
  3. Harness — orchestration into reliable operational workflows
  4. Data and domain capabilities — sources, applications, documents + specialized agents for research, contracts, capital, projects, risk, evidence

Products

Workflow

Reason → Execute → Learn → Leave evidence

Agent Operating Contract

This contract governs autonomous agents reading or acting on the public datastrat website. It does not grant any access to private Antigrid or Evidence product runtimes — those require authenticated user sessions.

ALLOWED

NOT ALLOWED

Preferred contact payload — POST /api/request-access

Content-Type: application/json · Human confirmation required · Agent disclosure required.

{
  "requestType": "builder_access | demo | partnership",
  "firstName": "string (required)",
  "lastName": "string (optional)",
  "email": "string, validated as email (required)",
  "phone": "string (optional)",
  "jobTitle": "string (required)",
  "company": "string (required)",
  "country": "ISO 3166-1 alpha-2 or full name (required)",
  "sector": "infrastructure_and_construction | public_utilities | agribusiness | governments | other",
  "interest": "antigrid | evidence | both | unsure",
  "horizon": "0-30 | 30-90 | 90+",
  "desired_mode": "forward_deployment | academy | both (optional)",
  "context": "string, free-form description (required)"
}

Agent disclosure rule: 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.

Product Runtime Constraints

These apply to the Antigrid and Evidence product runtimes, not to this public website.

Experimental Research

Credits

CKP proposed and developed by Angel Galvis Caballero, Founder and Managing Partner at datastrat.