IVD — Intent-Verified Development

Without IVD

You: "Add CSV export"
AI:  [builds with wrong columns]
You: "No, these columns, ISO dates"
AI:  [rewrites, still wrong]
You: "Still not right..."
AI:  [rewrites again]

→ Many turns. Many hallucinations.

With IVD

You: "Add CSV export for compliance"
AI:  [writes intent.yaml with constraints]
You: "Yes, that's what I meant"
AI:  [implements against intent]
AI:  [runs constraint tests → pass]

→ One turn. Zero hallucinations.

// workflow

How IVD works

You describe

Natural language. No templates, no special syntax. Just say what you want.

AI writes the intent artifact

Structured YAML with goal, constraints, success criteria, and test paths. Clarification happens here — before any code is written.

You review

"Is this what I meant?" One read. No ambiguity. The intent is explicit — columns listed, formats named, permissions stated.

AI stress-tests the intent

Adversarial completeness check — constraint gaps, implementation decisions not addressed, implicit assumptions, conflicts.

AI implements against the intent

Constraint-segmented: implement segment → re-read constraints from disk → verify segment → repeat. No drift from intent.

AI verifies

Full sweep — does every constraint pass? Hallucinations are caught before you review. AI self-corrects against the artifact.

intent.yaml — the artifact the AI writes

# AI writes this from your description
intent:
  summary: "Export user data to CSV for admin compliance reporting"
  goal:    "Enable admins to download user data in compliant format"

constraints:
  - name:  "admin_only"
    rule:  "Request must include valid admin session token"
    test:  "tests/test_csv_export.py::test_admin_required"
  - name:  "column_schema"
    rule:  "Columns: [user_id, email, created_at, last_login, status]"
    test:  "tests/test_csv_export.py::test_column_schema"
  - name:  "date_format"
    rule:  "All dates in ISO 8601 format"
    test:  "tests/test_csv_export.py::test_iso_dates"

// mcp server

15 tools for your AI agent

IVD ships as a Model Context Protocol server. Works with Cursor, Claude, VS Code, and any MCP-compatible IDE. 14 of 15 tools work with zero configuration — no API key, no setup beyond pip install.

context

ivd_get_context

Full IVD context for the agent — principles, resources, when to use

scaffold

ivd_scaffold

Create a new intent artifact at the correct canonical location

validate

ivd_validate

Check structure, required sections, constraint completeness

recipes

ivd_load_recipe

Load proven patterns for agents, workflows, infra, and more

discovery

ivd_discover_goal

Propose candidate goals when you're not sure what to ask

ivd_search

Semantic search across the IVD knowledge base

Hosted server available. Prefer not to run it locally? A hosted MCP server runs at mcp.ivdframework.dev/sse. Request access: leo@leocelis.com

// quickstart

Up in 5 minutes

// 1. Clone and setup

git clone https://github.com/leocelis/ivd.git
cd ivd
./mcp_server/devops/setup.sh  # creates .venv, installs deps
      

// 2. Add to Cursor

Settings → Features → MCP → add server:

{
  "servers": {
    "ivd": {
      "type":    "stdio",
      "command": "python",
      "args":    ["-m", "mcp_server.server"],
      "cwd":     "/path/to/ivd"
    }
  }
}
      

// 3. Use it

Ask your agent:

"Use ivd_get_context to learn IVD, then scaffold an intent for [your feature]"

Full docs on GitHub →

// framework

8 principles

Intent First

Write what the system must do before writing code. Intent is the source of truth.

Executable Understanding

Prose can be wrong silently. Executable understanding fails loudly.

Continuous Verification

Verify alignment at every stage. Drift is caught before it compounds.

Context Layering

System → Workflow → Module → Task. Right level of context for every task.

Knowledge Portability

YAML and MCP. Same intent works with Claude, GPT, Cursor, Copilot.

Discovery Before Intent

When you don't know what to ask — propose options first, then write intent.

Implementation Independence

Intent describes what, not how. The AI chooses the implementation.

Innovation Through Inversion

Challenge dominant assumptions. Inversion surfaces non-obvious solutions.

Stop correcting AI.Make it verify itself.