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
Updating messaging to make it clear what the requirements are for
enabling agentic chat
<!-- Explain the changes introduced in your PR -->
## Pull Request approval
You will need to get your PR approved by at least one member of the
Sourcegraph team. For reviews of docs formatting, styles, and component
usage, please tag the docs team via the #docs Slack channel.
Copy file name to clipboardExpand all lines: docs/cody/capabilities/agentic-chat.mdx
+17-20Lines changed: 17 additions & 20 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
<pclassName="subtitle"> Learn about the agentic chat experience, an exclusive chat-based AI agent with enhanced capabilities.</p>
4
4
5
-
<Callouttype="info">Agentic chat is currently in the Experimental stage for Cody Pro and Enterprise and is supported on VS Code, JetBrains, Visual Studio editor extensions and Web. Usage may be limited at this stage.</Callout>
5
+
<Callouttype="info">Agentic chat (available in version 6.0) is currently in the Experimental stage for Cody Pro and Enterprise and is supported on VS Code, JetBrains, Visual Studio editor extensions and Web. Usage may be limited at this stage.</Callout>
6
6
7
7
Cody's agentic chat experience is an AI agent that can evaluate context and fetch any additional context (OpenCtx, terminal, etc.) by providing enhanced, context-aware chat capabilities. It extends Cody's functionality by proactively understanding your coding environment and gathering relevant information based on your requests before responding. These features help you get noticeably higher-quality responses.
8
8
@@ -17,21 +17,6 @@ The agentic chat experience leverages several key capabilities, including:
17
17
-**Iterative context improvement**: Performs multiple review loops to refine the context and ensure a thorough understanding
18
18
-**Enhanced response accuracy**: Leverages comprehensive context to provide more accurate and relevant responses, reducing the risk of hallucinations
19
19
20
-
## Enable agentic chat
21
-
22
-
Pro users can find the agentic chat option in the LLM selector drop-down. Enterprise customers must opt-in to access this agentic chat feature.
### Getting agentic chat access for Enterprise customers
27
-
28
-
For the experimental release, agentic chat is specifically limited to using Claude 3.5 Haiku for the reflection steps and Claude 3.5 Sonnet for the final response to provide a good balance between quality and latency. Therefore, your enterprise instance must have access to both Claude 3.5 Sonnet and Claude 3.5 Haiku to use agentic chat. These models may be changed during the experimental phase to optimize for quality and/or latency.
29
-
30
-
Additionally, enterprise users need to upgrade their supported client (VS Code, JetBrains, and Visual Studio) to the latest version of the plugin by enabling the following feature flags on their Sourcegraph Instance:
31
-
32
-
-`agentic-chat-experimental` to get access to the feature
33
-
-`agentic-chat-cli-tool-experimental` to allow [terminal access](#terminal-commands)
34
-
35
20
## What can agentic chat do?
36
21
37
22
Agentic chat can help you with the following:
@@ -48,7 +33,6 @@ It has access to a suite of tools for retrieving relevant context. These tools i
48
33
49
34
It integrates seamlessly with external services, such as web content retrieval and issue tracking systems, using OpenCtx providers. To learn more, [read the OpenCtx docs](/cody/capabilities/openctx).
50
35
51
-
52
36
<Callouttype="info">Terminal access is not supported on the Web. It currently only works with VS Code, JetBrains, and Visual Studio editor extensions.</Callout>
53
37
54
38
## Terminal access
@@ -69,8 +53,21 @@ Agentic chat can be helpful to assist you with a wide range of tasks, including:
69
53
-**Error resolution**: It can automatically identify error sources and suggest fixes by analyzing error logs
70
54
-**Better unit tests**: Automatically includes imports and other missing contexts to generate better unit tests
71
55
72
-
## Known limitations
56
+
## Enable agentic chat
57
+
58
+
### Getting agentic chat access for Pro users
59
+
60
+
Pro users can find the agentic chat option in the LLM selector drop-down.
### Getting agentic chat access for Enterprise customers
65
+
66
+
Enterprise customers must opt-in to access this agentic chat feature (reach out to your account team for access).
73
67
74
-
### Enterprise deployments
68
+
For the experimental release, agentic chat is specifically limited to using Claude 3.5 Haiku for the reflection steps and Claude 3.5 Sonnet for the final response to provide a good balance between quality and latency. Therefore, your enterprise instance must have access to both Claude 3.5 Sonnet and Claude 3.5 Haiku to use agentic chat. These models may be changed during the experimental phase to optimize for quality and/or latency.
75
69
76
-
All customers are required to have Claude 3.5 Sonnet and Claude 3.5 Haiku enabled on their Sourcegraph instance (this requires Sourcegraph v5.9 and new [model configuration](/cody/enterprise/model-configuration)).
70
+
Additionally, enterprise users need to upgrade their supported client (VS Code, JetBrains, and Visual Studio) to the latest version of the plugin by enabling the following feature flags on their Sourcegraph Instance:
71
+
72
+
-`agentic-chat-experimental` to get access to the feature
73
+
-`agentic-chat-cli-tool-experimental` to allow [terminal access](#terminal-commands)
0 commit comments