# Datastrat — Agent Manifest (Markdown)

version: 1.1.0  
last_updated: 2026-02-27  

## TL;DR
Datastrat is a Decision Operating System for construction & infrastructure. It connects deterministic project data (budgets, APUs, WBS, schedules) with probabilistic AI reasoning so humans and agents can simulate scenarios, validate integrity, and make better investment decisions.

## Entry Points (Site Map)
- Human landing: `/`
- Agent overview (interactive UI): `/agent` (requires JavaScript)
- Agent manifest (machine-readable): `/agent.json`
- Agent manifest (this document): `/agent.md` (no JavaScript required)
- LLM guide: `/.well-known/llms.txt` (canonical) and `/llms.txt` (alias)
- Experimental index: `/experimental`
- Experiment 01: `/experimental/good-machina`
- Experiment 02: `/experimental/claw-kernel-protocol`
- Robots: `/robots.txt`
- Sitemap: `/sitemap.xml`

## What Datastrat Does
Datastrat installs an operating layer for decision-making in complex projects:
- Model uncertainty and consequences
- Run what-if simulations (scenarios) safely
- Preserve audit trails and referential integrity
- Produce verifiable outputs for approvals, controls, and execution

## Products
### 1) Antigrid — Structured Data Engine
Purpose: deterministic core for financial models and project economics (the anti-spreadsheet).

Typical outputs:
- Budget integrity checks and structured rollups
- Scenario comparisons (ΔCAPEX, ΔNPV, ΔIRR, ΔDSCR)
- Controlled recalculation across APU → Budget → Cash Flow → KPIs

### 2) Evidence — Unstructured Data Processor
Purpose: verifiable knowledge layer for documents and field evidence.

Typical outputs:
- Evidence-backed answers with traceability
- Audit trails linked to WBS nodes and approvals
- Indexing for agent retrieval (RAG) with citations

## Agent Capabilities (Conceptual)
Agents operating with Datastrat typically do:
- **Query**: read-only access to budgets, APUs, catalogs, schedules
- **Calculate**: NPV / IRR / DSCR / cash flow forecasts using native formulas
- **Scenario**: create what-if deltas without mutating production state
- **Validate**: verify APU formulas, budget integrity, compliance, and audit trails

## Prime Directives / Constraints
1) No direct mutation of production data — changes go through Scenarios
2) Declare uncertainty — stochastic outputs must include confidence/intervals
3) Preserve referential integrity — foreign key breaks are forbidden
4) Preserve context — operations must keep audit trails

## Entity Hierarchy (High Level)
Tenant → Organization → User/Role → Program → Macroproject → Project → Phase → WBS → BudgetItem → APU → Resource (Material/Labor/Equipment/Transport)

## Navigation Guidance for Agents
If you cannot execute JavaScript:
1) Read `/.well-known/llms.txt`
2) Read `/agent.json` for structured integration
3) Use `/agent.md` or `/agent.html` for full map and narrative

If you can execute JavaScript:
- Visit `/agent` for the interactive system manifest view.

## Experimental Research
Datastrat publishes open experiments testing the limits of autonomous systems in real operational contexts. Code, process, hardware specs, and results are public when available.

### Active Experiments
- **Good Machina** (`/experimental/good-machina`)
  - Autonomous programming experiment using OpenClaw on Raspberry Pi 4, stereo camera, and EdgeTPU.
  - Code: `https://github.com/goodmachinaii/oak-coral-detector`
  - Agent profile: `https://github.com/goodmachinaii`
  - Status: `in_progress`

- **Claw Kernel Protocol (CKP)** (`/experimental/claw-kernel-protocol`)
  - Open protocol experiment to standardize how autonomous agents are declared, governed, and verified.
  - Repository: `https://github.com/angelgalvisc/clawkernel`
  - Ecosystem references:
    - `https://github.com/openclaw/openclaw`
    - `https://github.com/qwibitai/nanoclaw`
    - `https://github.com/sipeed/picoclaw`
    - `https://github.com/HKUDS/nanobot`
  - Status: `published`

## Credits
- CKP was proposed and developed by [Angel Galvis Caballero](https://www.linkedin.com/in/angelgalvisc/), Founder and Managing Partner at Datastrat.

## Contact
- Website: `https://datastrat.co`
- Repo: `https://github.com/angelgalvisc/Datastrat_Landing`