🧭 Onboarding & Pathways

Start Here: Three Delivery Pathways

Choose the right starting path based on how your team delivers projects.

Pathway 1: Project Practitioners & PMO Directors

Templates & Governance

For Project Managers, PMO Leaders, and Delivery Directors looking to establish structured governance, avoid blank-document paralysis, and tailor deliverables to organizational risk.

  1. Step 1 — Assess Project Sizing Tier: Classify your project into Tier 1 (> $10M / Mega), Tier 2 ($1M–$10M / Standard), or Tier 3 (< $1M / Lean). See the Tailoring Profiles Manual.
  2. Step 2 — Select Initiation Deliverables: Download foundational templates starting with PMO-03.01 Project Charter, PMO-03.03 Assumption Log, and PMO-03.04 Stakeholder Register.
  3. Step 3 — Review the 12 Core Lifecycle Manuals: Align stage gates and RACI authority before proceeding to detailed baseline planning in Stage 04.

Pathway 2: Technical Teams & Automation Engineers

CLI & Python SDK

For software engineers, DevOps practitioners, and automation leads integrating Tasleemat deliverables directly into GitOps pipelines, CI/CD validations, or internal portals.

  1. Step 1 — Install the Verified Python Package:
    pip install tasleemat
  2. Step 2 — List Tailored Deliverables via CLI:
    tasleemat list --tier 2 --pack agile
  3. Step 3 — Export Templates & Validate Data:
    tasleemat asset PMO-04.14 template --lang en > risk_plan.md
    tasleemat validate PMO-04.14 completed_data.json

Pathway 3: AI Assistants, LLMs & Multi-Agent Systems

Model Context Protocol (MCP)

For teams pairing with AI assistants (Claude Desktop, Cursor, Antigravity) or building multi-agent systems that draft, audit, and validate project governance documents deterministically.

  1. Step 1 — Configure the Stdio MCP Server: Add the Tasleemat MCP tool server to your client configuration:
    {
      "mcpServers": {
        "tasleemat": {
          "command": "tasleemat",
          "args": ["mcp"]
        }
      }
    }
  2. Step 2 — Deterministic Artifact Fetching: Instruct your LLM to fetch the official prompt, guide, and Draft 2020-12 schema using get_artifact_asset rather than hallucinating deliverable structures.
  3. Step 3 — Closed Self-Correction Validation Loop: Pass drafted JSON data to validate_artifact_data. If errors occur, provide schema error paths back to the LLM for autonomous self-correction before human sign-off.