Anvil CoderLog in

Specify the outcome · Then implement

Spec-driven development with AI agents

Spec-driven development uses an explicit specification as the reference for planning, implementation and review. With Anvil Coder, you prepare requirements in Spec Studio, curate the resulting tickets and delegate selected tasks to AI coding agents.

Turn an idea into assessable work

  1. Clarify requirements

    Record the audience, goals, non-goals, behaviour and open questions. Decisions become an editable document.

  2. Define constraints

    Describe the stack, interfaces, quality rules and check commands. Write acceptance criteria against which the result can be assessed.

  3. Curate tickets

    Review the proposed epics and tasks. Creating tickets does not start a coding run; you decide which story is implemented.

  4. Review against the spec

    Compare changes and executed checks with the specification. Feed new findings back into requirements and subsequent tasks.

Make the specification concrete

Illustrative task · not a benchmark

Invite new team members

“We need invitations” names a feature. A useful specification also records decisions that would otherwise be made during implementation:

Review now has an explicit reference. If the team later changes the expiry period, update the specification, implementation and related tests together.

The specification becomes working context

Spec Studio guides you through vision and context, goals and non-goals, functional requirements, stack and constraints, quality requirements and guardrails, and epic slicing. You edit the actual text and decide which suggestions to accept.

A stack profile describes tools and verification commands. Their availability must be established in the execution environment. A specification and profile alone do not establish that tests passed.

Follow the path from Spec Studio to pull request

Your team remains responsible for requirements

Spec-driven AI development gives agents and reviewers a shared reference. It helps expose conflicting requirements and missing decisions early. An inaccurate requirement can still lead to an unsuitable solution.

Keep the specification current as you learn. Existing tests, new checks and human review examine different aspects of the result and complement each other.

Read the methodology guide and its limits

Questions before your first run

Do we need a complete specification before starting?
Spec Studio helps you develop it. Before implementing a story, clarify its goal, boundaries and assessable acceptance criteria. Keep unresolved decisions visible during preparation.
Does generating epics automatically start implementation?
The studio creates preparatory documents and tickets. A person decides which story actually runs. Preparation can also incur model usage charges.
Is Anvil an integration of GitHub Spec Kit?
Anvil provides its own starting point through Spec Studio. A shared methodology with other specification-driven tools does not imply an integration. The methodology guide explains the approach.