Agent-assisted product initiatives · MIT · on npm

Run a product initiative,
end to end.

AI-assisted projects move fast — and rot fast. Blueprint is a working method for running a product initiative with an AI agent — research through deployment. The agent does the building; the method supplies the checkpoints and the paper trail. What ships is researched, prototyped, fact-checked, and documented.

$ npx @nino-chavez-labs/blueprint-cli init --name=my-initiative
Quickstart ↓ Watch the demo → What is this? ↓ npm ↗ github ↗

plain language

The 30-second version.

Just the strip. Everything below goes deeper.

What it is

A method for doing product work with an AI carrying the heavy lifting. The AI researches, prototypes, and drafts the documents; Blueprint is the set of checkpoints that keeps the work verifiable.

Why it exists

AI-built work is fast and convincing — and that's the problem. Confident claims nobody verified, decisions nobody wrote down. Blueprint forces the receipts: every claim traced, every decision recorded, every stage checked before the next one starts.

Who it's for

Anyone shipping product work with an AI agent — solo or in a team. Solo, it's quality control: fast doesn't mean sloppy. In a team, it's the harder problem: everyone has their own way of keeping AI honest, and none of them line up. Blueprint is one way the whole team can share.

the thinking behind it — The kitchen I'm looking for ↗

how it works

One pipeline. Seven stages.

Each stage produces artifacts that feed the next. The insight: prototype and documents are built simultaneously — the prototype tests the decision, the docs capture the rationale.

  1. 01 Research

    competitive analysis, codebase, comparables

  2. 02 Design

    define scope — what the prototype will and won't do

  3. 03 Prototype

    HTML pages matching the real product

  4. 04 Fact-check

    every claim validated against source

  5. 05 Document

    strategy, feasibility, integration plans

  6. 06 Deploy

    one portal — docs + prototype + chat

  7. 07 Iterate

    stakeholder feedback, triaged

proof

This site is Blueprint output.

Every page here was generated from a single blueprint.yml by the same pipeline you’d run. The CLI is live on npm; the portal deploys from one config. Blueprint runs on itself — the methodology, applied to productizing the methodology.

85gated updates
13decision records
17automated reviewers
13projects running Blueprint
7CLI commands
1config → whole portal
Open the portal →

get started

Up and running in five steps.

Five steps. The choices you make are written out below — every command runs as printed.

  1. 1

    Prerequisites

    Node 18+ and Claude Code. That’s it — there’s no server to stand up and nothing to host.

  2. 2

    Scaffold your initiative

    Generates a portal you own, validated against your config. --name is the only required flag — everything else defaults and is echoed back. Two starting points:

    New idea — nothing exists yet. That’s all greenfield (the default) means.

    $ npx @nino-chavez-labs/blueprint-cli init --name=my-initiative

    Existing app — run it from that repo. That’s brownfield.

    $ npx @nino-chavez-labs/blueprint-cli init --name=my-app --variant=brownfield --target=.
  3. 3

    Configure

    Set the three things that matter in blueprint.yml — the rest has sane defaults.

    variant: brownfield   # greenfield | midstream | brownfield
tier: 1               # deliverable sophistication 0–2
portal_pattern: A     # A = platform portal · B = redesign review
  4. 4

    Run the pipeline

    In Claude Code, the stages are skills. Run them in order — each gate is enforced by a reviewer.

    /blueprint-research → /blueprint-prototype → /blueprint-validate → /blueprint-docs → /blueprint-deploy
  5. 5

    Ship & check

    Push and your portal deploys. Verify conformance — doctor is honest about what it didn’t check.

    $ npx @nino-chavez-labs/blueprint-cli doctor

Want the whole thing — stage by stage, every reviewer gate, on a real initiative? → Run your first initiative, or start at Learn.

reference

The CLI

7 commands, all real. npx @nino-chavez-labs/blueprint-cli <command> — zero install.

blueprint init

Scaffold a new initiative and its portal — your variant, tier, and pattern choices validated before anything is written.

blueprint review

Run a stage gate: an automated reviewer that checks a stage is actually done. --list shows built-in + your own.

blueprint cost

Per-stage effort/model configuration and telemetry — dial spend up or down.

blueprint fleet

One report across every project running Blueprint: which are current, which have fallen behind.

blueprint upgrade

Move a project to the latest methodology version — preview first, dry-run by default.

blueprint doctor

Health check: loads the config, every reviewer, and the portal — and says what it didn’t check.

blueprint hive

Set up the shared workspace a team of agents coordinates through. hive setup shows its plan first — nothing is provisioned until you pass --execute.

ecosystem

Stay current. Feed back upstream.

Updates flow down without breaking you; your fixes and gaps flow back up.

Pull updates

blueprint upgrade reads the methodology version your project is pinned to, shows what changed, and updates it — non-breaking, dry-run by default. blueprint fleet shows which of your initiatives have fallen behind.

$ npx @nino-chavez-labs/blueprint-cli upgrade

Report & request upstream

Hit a gap, a bug, or a feature need? File an amendment or RFC. Triage routes it automatically — substantial change → RFC first, bug-fix → straight PR.

How to contribute →

further reading

Go deeper

Learn — run your first initiative

Getting started, the full end-to-end tutorial, and role-routed paths.

Watch the demo

35-second sizzle or the step-through walkthrough — real transcripts, real artifacts.

Methodology

The first principles, the seven stages, how variant and tier get picked.

Decisions

13 architecture decision records — the why behind every primitive.

The live portal

Discover · Try · Build · Operate · Inspect · Roadmap — the deeper reference.

FAQ — the honest objections

The questions a skeptic asks first, answered straight.

How it compares

A source-level read of 14 spec-driven tools — what each one's gates actually do.

Source on GitHub

The methodology, the CLI, the template, the reviewer set.