A Community Workflow for Requirements, Tests and Model Dialogue
A LocalLLaMA author says Qwen3.8-27B, running as a 6K unsloth quantization, helped complete a binary protocol build over a weekend. The author recommends beginning with goals and requirements, using Cucumber or EARS-style documentation and repeatable tests, and asking the model to present options before choosing a design. They also report using Claude to review the project, which found several missing security checks and two errors in a Python benchmark script.
The post offers a concrete agentic-coding workflow built around verifiable requirements and tests, but its evidence comes from one community user's project rather than a controlled evaluation.
Creating a list of requirements and documentation/tests (in Cucumber or EARS style) with your model is a great way to improve it's code. Just got through a weekend long binary protocol build with Qwen3.8-27B (6K unsloth quant).. and fired up claude to review and it found the foundation was well engineered, but only missed a few security checks and a couple of errors in the python benchmark script comparing the old protocol with the new one.
Really comes down to:
- Design first. Goals, requirements, problems. How is this going to be used.
- Observation, simulation and tests are verifiable vs. assumptions. Tests and processes can be reviewed for "ritual".
- Dialectic: If the model comes to a crossroads, have it present options and NOT just choose-and-go, but initiate a dialog about design.
- Frequent repeatable tests, and review of tests to see if they meet the spirit of the requirement
- Every risk is a requirement.
Here's my prompt set ("skills" I guess) and a tool to install for various local harnesses: https://github.com/bigattichouse/BluePrint