Limits and Usage
2 min read
These are the generator’s limits, so you can plan a run around them.
Per run
Section titled “Per run”| Limit | |
|---|---|
| Requirements in one brief | 10 |
| Documents attached | 3 |
| PDFs, of those documents | 1, up to 8 MB |
| Scenarios mapped | 40 (default 30) |
| Test cases written per run | 20, in batches of 10 |
These limits are fixed. If you need more, split the work: a run per feature area usually gives a better map than one run covering everything, because the scenario count is shared across everything you supply.
Source length
Section titled “Source length”Each source is capped at 20,000 characters, and the whole brief at 60,000.
If a source is too long, part of it is left out. The run tells you which source, and how many of its characters were used, so you always know whether the whole document was read.
The workspace AI allowance
Section titled “The workspace AI allowance”AI usage is metered in credits, and every plan includes an allowance: 50 a month on Free for the whole workspace, and 250 per member a month on Growth, pooled across everyone. Hawzu shows how much of it is left as a percentage rather than a running bill. Running out doesn’t cost money; you wait for the next month.
You can see it in:
- Workspace Settings, under general settings,
- the profile menu in the workspace and project headers,
- the project’s left rail,
- the generation modals themselves, while you work.
The allowance covers a calendar month and resets at the start of the next one. When it runs low the wording changes to say so; when it is exhausted, generation is unavailable until the reset and every other feature carries on as normal.
Two things spend it:
- Each generation: one coverage map is one generation, and each batch of ten written test cases is another. Mapping and then writing 20 test cases is three generations, not one.
- Attached PDFs: a PDF uses more of the allowance than the same content as text.
When a run does less than you asked
Section titled “When a run does less than you asked”The generator returns less rather than making things up. It returns less in three cases:
- Fewer scenarios than requested: the source didn’t support the number you asked for. The map says so instead of padding the list.
- Fewer test cases than scenarios ticked: the same, at the writing stage.
- Nothing at all: the source was too thin to write a single test case from, and the generator tells you instead of producing something that only looks right.