We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent cb45a99 commit 272ea26Copy full SHA for 272ea26
1 file changed
docs/prompts/quality.md
@@ -0,0 +1,26 @@
1
+# Prompt Quality
2
+
3
+Prompt quality in AI-OS is measured by whether the prompt produces safe, verifiable engineering behavior.
4
5
+## Quality loop
6
7
+```mermaid
8
+flowchart TD
9
+ A[Prompt] --> B[Run task]
10
+ B --> C[Collect output]
11
+ C --> D[Check evidence]
12
+ D --> E{Good?}
13
+ E -- No --> F[Improve prompt]
14
+ F --> B
15
+ E -- Yes --> G[Keep]
16
+```
17
18
+## Quality criteria
19
20
+- goal is clear
21
+- loop is selected
22
+- plan appears before work
23
+- verifier evidence is included
24
+- risks are explicit
25
+- docs are updated when needed
26
+- remaining work is stated
0 commit comments