Menu

The Twin-Run Test: A 90-Minute Spike That Proves a Task Is Agent-Shaped
πŸ“°

The Twin-Run Test: A 90-Minute Spike That Proves a Task Is Agent-Shaped

DEV Community: productivityΒ·Emery YangΒ·13 days ago
#4RdC15cr
#devtoproductivity#devto#dev#pass#task
Long article (1365 words) β€” no AI summary yet.
Reading 0:00
15s threshold

Most AI spikes test the model. They should test the task. One run tells you a patch exists. Two runs tell you the task is stable enough to hand off. This post is a 90-minute protocol for the second question.

The core claim: if two independent agent runs on the same task disagree wildly, the problem is your task description, not the model. Ship-or-kill evidence should measure that disagreement, not how good one diff looks.

The hypothesis, written before you touch anything

One sentence. One falsifiable claim. Written in a file, committed before the first prompt.

spike/hypothesis.md

Hypothesis: "Add retry with backoff to the S3 uploader" is agent-shaped. Prediction: two independent runs from the same base commit change overlapping code regions and pass the same tests. Kill if: overlap < 0.15, or either run fails the existing suite.

Enter fullscreen mode

Exit fullscreen mode

If you cannot phrase the kill condition as a number, you are not spiking.…

Continue reading β€” create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.