One run, step by step

A run is one piece of work your AI team starts, such as "fix every broken link on the store" or "add gift notes to checkout". Plain code runs the six steps, checks the work and keeps the budget, with no model needed for that part. The top model plans and signs off, low-cost models do the bulk of the work side by side, and a mid-price model takes the harder fixes and reviews each one.

1. 1

   Plan the run · High

   The top model, claude-fable-5-1, writes the workflow script for the whole run: what to scan, what to fix, and which checks each fix must pass. Plain code checks the script's shape and asks for a new one when needed, up to five tries.

2. 2

   Scan, many at once · Low

   Low-cost models, gpt-4.1-mini or deepseek-v4-flash, read the work side by side. Each one returns its findings in the same fixed JSON shape, so the next step can act on them directly.

3. 3

   Fix, one copy per fix · Low, then Medium

   gpt-4.1-mini writes the first try at each fix, in its own isolated copy of the code. Tries two and three move up to glm-5.2 or deepseek-v4-pro. The higher price applies to that one fix, not the whole run.

4. 4

   Check every fix · Plain code

   Plain code runs the tests and checks for secrets, file limits and cost. A fix that passes moves on to review. After three tries, a fix is marked failed and kept in the record.

5. 5

   Review with a second model · Medium

   glm-5.2 or deepseek-v4-pro reads each passing fix. The reviewer is always a different model from the one that wrote the fix. Approved fixes are merged.

6. 6

   Sign off and ship · High

   claude-fable-5-1 reads a short summary: what passed, what failed, and the cost at each price tier. The run ships to ZB Cloud and you get a preview link. Every step, model and cost goes in the record.

#Price tiers