git404hub

what is meta-project-poc fr?

asnowwolf/meta-project-poc — explained in plain English

Analysis updated 2026-05-18

15ShellAudience · developerComplexity · 3/5Setup · moderate

tl;dr

A proof of concept process for structuring how a person guides an AI through building software stage by stage.

vibe map

mindmap
  root((Meta Project))
    What it does
      Structures AI dev process
      Stage by stage artifacts
      Human review gates
    Tech stack
      Shell scripts
      Gemini API
    Use cases
      Multi stage AI workflow
      Requirements to code
      Model per stage
    Audience
      Developers
      AI tool builders

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

what do people make with this?

VIBE 1

Structure a multi stage AI assisted development process instead of one long open ended chat.

VIBE 2

Insert human review checkpoints between requirements, design, and coding stages.

VIBE 3

Assign different AI models to different stages based on cost and strength.

VIBE 4

Study an example of combining design thinking, domain driven design, and TDD around LLM calls.

what's the stack?

ShellGemini API

how it stacks up fr

asnowwolf/meta-project-pocaduskelebe/diffpilotamrit-regmi/immich_edge
Stars151515
LanguageShellShellShell
Setup difficultymoderateeasyhard
Complexity3/52/54/5
Audiencedeveloperdeveloperops devops

Figures from each repo's GitHub metadata at analysis time.

how do i run it?

Difficulty · moderate time til it works · 1h+

Requires a Gemini API key set as an environment variable to run the stage scripts.

in plain english

Meta Project Demo is a proof of concept for organizing how a person uses large language models to build software, rather than being a tool that writes code by itself. The idea behind it is that a single open ended conversation with an AI, relying only on whatever fits in its context window, tends to lose track of decisions, produce inconsistent quality, and drift away from the original goal as a project grows. This project tries to fix that by borrowing established software engineering methods and turning the overall process, not the code itself, into something structured and repeatable. The workflow moves through a sequence of stages that mirror real development practice: design thinking for figuring out user needs, domain driven design for modeling the business concepts involved, an architecture stage for deciding how the system is structured, agile planning to break work into sprints, and test driven development for the actual coding, followed by a retrospective stage for reviewing what happened. Each stage produces a concrete document or artifact, such as a requirements write up or a domain model, which becomes an input to the next stage. A key design choice is that the big picture decisions, which methodology to use, what order stages happen in, which AI model handles which stage, are fixed in advance by the person running the process or by a script, while the fine grained details, like exactly how a class is implemented, are left for the AI to work out within those boundaries. Certain points in the process are marked as human checkpoints, where the person running it must review the output before the process continues, and these checkpoints can be configured to always pause, never pause, or only pause under certain conditions. Each stage also repeats automatically, generating output, checking it against a quality bar, and trying again with feedback until it passes or reaches a limit, at which point it waits for a person.

prompts (copy fr)

prompt 1
Explain how the human gate settings, auto, review, review_if, and override, change this workflow's behavior.
prompt 2
Walk me through how this project moves from a requirements document to a domain model.
prompt 3
Help me swap the Gemini API calls in this project for a different model provider.
prompt 4
Show me how the PDCA loop decides when a stage's output is good enough to move on.

Frequently asked questions

what is meta-project-poc fr?

A proof of concept process for structuring how a person guides an AI through building software stage by stage.

What language is meta-project-poc written in?

Mainly Shell. The stack also includes Shell, Gemini API.

How hard is meta-project-poc to set up?

Setup difficulty is rated moderate, with roughly 1h+ to a first successful run.

Who is meta-project-poc for?

Mainly developer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.