Anvil CoderLog in

Use cases

Greenfield project from a specification

From a requirement text to a running project: first a structured specification, then the repository scaffold, then epics that get worked story by story.

Illustration for the use case “Greenfield project from a specification” (decorative)

Case study in full

Example scenario

Stack profile: typescript-react-vite-spa · Example scenario with typical orders of magnitude.

A new project starts without code, but with a written requirement. Spec Studio turns it into a structured specification, after your approval the repository scaffold is created, and the specification becomes epics that the run works story by story.

What stays with your team: You set the direction of the specification; approval before the repository is created and the prioritisation of the epics stay with you.

What you need

How the run works

  1. A structured, sectioned specification emerges from the requirement text.
  2. After your approval, the repository scaffold is created.
  3. Epics are derived from the specification and taken into the tracker.
  4. Each epic is broken into slices and worked, as in the other scenarios.
  5. The results arrive as pull requests in the new repository, traceable per epic.

What you get

Key figures

Scope

Stories/tickets
5
Slices
22
Files/modules
64

Throughput

Validated slices
20
Retries
7
Human interventions
4

Quality

Checks run
Compile, Unit Tests, Guardrail-Prüfung
Gates passed
6
Gates failed
1

Resources

Prompt tokens
600000
Completion tokens
240000
Cache tokens
350000
Model calls
260
Sandbox runtime
100 minutes
Model/stack context
Stack: TypeScript with React, clean architecture (profile typescript-react-clean-architecture); flow Spec Studio → Foundation → Epics.

What stayed open

One epic is waiting for a clarification before its remaining slices start.