You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/en/Community-Articles/2026-06-18-deep-dive-7-scopes/post.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -29,7 +29,7 @@ For me, that changes the feeling of using an AI agent. It is no longer "here is
29
29
30
30
An AI Scope **restricts which directories the agent can access during a session**.
31
31
32
-

32
+

33
33
34
34
Depending on the task, a scope can include:
35
35
@@ -56,7 +56,7 @@ The first message of a session locks the configuration that affects the system p
56
56
57
57
That matters when multiple sessions are active.
58
58
59
-

59
+

60
60
61
61
Imagine I have one session working on a Catalog module and another session answering questions about the whole solution. Those sessions should not accidentally share a changing boundary. Each one should keep the scope it started with.
62
62
@@ -114,7 +114,7 @@ Which parts of the system should stay out of this session?
114
114
- Scopes define **where** the agent can work.
115
115
- Workflows define **what deterministic actions** should happen around that work.
116
116
117
-

117
+

118
118
119
119
That combination is powerful. For example, I can scope the agent to the `Catalog` module and use a workflow that builds the affected package, regenerates proxies if contracts changed, and restarts the related application.
Copy file name to clipboardExpand all lines: docs/en/Community-Articles/2026-06-18-deep-dive-9-workflows/post.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -16,7 +16,7 @@ When I work alone, I can do those steps manually. When I work with an AI coding
16
16
17
17
That is the point of **ABP Studio AI Agent Workflows**.
18
18
19
-

19
+

20
20
21
21
Workflows let me define repeatable actions around an agent run. The model can focus on the ambiguous part, understanding the requirement and changing the code, while ABP Studio handles the deterministic parts that should happen before or after the work.
22
22
@@ -30,7 +30,7 @@ If the team always builds a package after an application service change, that sh
30
30
31
31
Workflows give ABP Studio a place to encode those repeatable steps.
32
32
33
-

33
+

34
34
35
35

36
36
@@ -45,7 +45,7 @@ and restart the app, and also add a migration if needed.
45
45
46
46
I can configure the workflow once and let the agent session carry that context.
47
47
48
-

48
+

49
49
50
50
That makes the prompt cleaner:
51
51
@@ -98,7 +98,7 @@ A generic coding tool can run shell commands, and that is useful. But ABP Studio
98
98
99
99
Workflows can be personal or shared.
100
100
101
-

101
+

102
102
103
103
- A **personal workflow** is stored locally under the solution workspace. It is useful for my own development habits. Maybe I like restarting a specific app after each agent turn. Maybe I have a local task that only makes sense on my machine.
104
104
- A **shared workflow** is stored with the active run profile. That makes it suitable for source control and team usage.
0 commit comments