Open-source infrastructure for AI-enabled project delivery.
This project is a fork of https://github.com/PDA-Task-Force/pda-platform originally developed by the PDA Task Force. This fork is maintained independently by https://github.com/antnewman and is not affiliated with the original creators.
The PDA Platform provides the data infrastructure needed for AI to improve project delivery. Built to support the NISTA Programme and Project Data Standard trial.
This work was made possible by:
- The PDA Task Force White Paper identifying AI implementation barriers in UK project delivery
- The NISTA Programme and Project Data Standard and its 12-month trial period
NISTA compliance scores generated by this tool are indicative assessments against the trial standard and do not constitute formal certification. This tool is provided as-is under the MIT licence; see LICENSE for full warranty and liability terms. The paper this tool accompanies describes the intended scope and known gaps: https://doi.org/10.5281/zenodo.18711384
UK major infrastructure projects have a success rate of approximately 0.5%. The Government Major Projects Portfolio shows 84% of projects rated Amber or Red. AI has potential to help, but lacks standardised data infrastructure.
| Component | Description | Status |
|---|---|---|
| pm-data-tools | Universal PM data parser (8 formats + NISTA) | v0.2.0 ✅ |
| agent-task-planning | AI reliability framework | v1.0.0 ✅ |
| pm-mcp-servers | MCP servers for Claude integration | Phase 1 ✅ |
| Specifications | Canonical model, benchmarks, synthetic data | Published ✅ |
| Longitudinal Compliance Tracker | Compliance score trend analysis and threshold alerting | v0.3.0 ✅ |
| Cross-Cycle Finding Analyzer | AI extraction, deduplication, and cross-cycle recurrence detection | v0.3.0 ✅ |
# Install the core library
pip install pm-data-tools
# Parse any PM file
from pm_data_tools import parse_project
project = parse_project("schedule.mpp")
# Validate NISTA compliance
from pm_data_tools.validators import NISTAValidator
result = NISTAValidator().validate(project)
print(f"Compliance: {result.compliance_score}%")Universal parser and validator for project management data.
- Formats: MS Project, Primavera P6, Jira, Monday, Asana, Smartsheet, GMPP, NISTA
- Features: Parse, validate, convert, migrate
- Install:
pip install pm-data-tools
AI reliability framework with confidence extraction and outlier mining.
- Features: Multi-sample consensus, diverse alternative generation
- Install:
pip install agent-task-planning
MCP servers enabling Claude to interact with PM data.
- Unified server:
pda-platform-serverexposes all 41 tools through a single endpoint - Modules: pm-data (6 tools), pm-analyse (6), pm-validate (4), pm-nista (5), pm-assure (20)
- Remote access:
pda-platform-remoteadds SSE transport for use with Claude.ai - Install:
pip install pm-mcp-servers
All specifications are in the specs/ directory:
| Spec | Description |
|---|---|
| Canonical Model | 12-entity JSON Schema for PM data |
| MCP Servers | 5 modules, 41 tools for AI integration |
| Benchmarks | 5 evaluation tasks for PM AI |
| Synthetic Data | Privacy-preserving data generation |
pda-platform/
├── specs/ # Technical specifications
├── packages/ # Python packages (each publishable to PyPI)
│ ├── pm-data-tools/
│ ├── agent-task-planning/
│ └── pm-mcp-servers/
├── docs/ # Documentation
└── examples/ # Usage examples
If you use this platform in your research or work, please cite:
Newman, A. (2026) From Policy to Practice: An Open Framework for AI-Ready Project Delivery.
London: Tortoise AI. DOI: https://doi.org/10.5281/zenodo.18711384
MIT License - see LICENSE
Original authors: Members of the PDA Task Force
Fork maintained by: Ant Newman (github.com/antnewman), CEO and Co-Founder, Tortoise AI
- PDA Task Force White Paper on AI implementation barriers
- NISTA Programme and Project Data Standard
- The open-source community
- This platform accompanies the publication From Policy to Practice: An Open Framework for AI-Ready Project Delivery (Newman, 2026)
- Lawrence Rowland — requirements and conceptual design for the confidence extraction and outlier mining capabilities in
agent-task-planning - Malia Hosseini — implementation of the outlier mining module
Built to support the NISTA trial and improve UK project delivery.