Vision¶
Wayloop exists to make agentic software development dependable at the scale of a whole project, not only of a single task.
The problem¶
Coding agents produce code quickly. Projects still fail in the work around the code: intent that was never written down, plans that drift from what is built, sessions that the next agent cannot resume, and costs that nobody measures. Spec-driven tools capture intent but stop at the plan file; agentic loops keep an agent working but do not know the plan.
The thesis¶
- The engine decides, agents write. A deterministic state machine runs the loop and verifies every step with checks, not with the word of a model.
- The tracker is the database. The plan lives where the team already works. Remove Wayloop and the project still reads.
- Humans at the gates. The loop runs unattended between approval states and stops at them.
- Cost is measured. Every phase has a token budget, and the ledger records the cost of every issue.
Who it is for¶
- Analysts and designers, who write intent and want to see it carried through to the code.
- Maintainers, who want agents to work while they are away and to find questions, not surprises, when they come back.
- Developers, who want a process that agents follow without being reminded.
Three tests of success¶
- Removal. Without Wayloop, the project is still understandable from the tracker and the repository.
- Hand-over. Any agent resumes the work from an issue and its specification alone.
- Cost. The cost per issue is measured and comparable with other approaches on the same work.
Out of scope¶
- Writing a coding agent: Wayloop drives existing agents.
- Semantic search with embeddings: see ADR 0004.
- Hosting: Wayloop is a local-first tool and a set of workflows; there is no server to run.