Skip to content

Commit 625e159

Browse files
committed
.
1 parent ab1eecc commit 625e159

File tree

8 files changed

+256
-110
lines changed

8 files changed

+256
-110
lines changed

docs/capabilities/analytics.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: "Analytics"
33
sidebarTitle: "Analytics"
4-
icon: "chart-line"
4+
icon: "chart-column"
55
---
66

77
<Frame caption="Cost analytics on codegen.com/analytics">

docs/capabilities/capabilities.mdx

Lines changed: 124 additions & 56 deletions
Original file line numberDiff line numberDiff line change
@@ -5,59 +5,127 @@ icon: "gear"
55
iconType: "solid"
66
---
77

8-
Codegen agents come equipped with versatile tools designed to integrate seamlessly into your development workflow.
9-
10-
## Integrated Tool Suites
11-
12-
Deep integrations with the tools your team already uses:
13-
14-
<CardGroup cols={3}>
15-
<Card title="GitHub" icon="github" href="/integrations/github">
16-
Create and manage pull requests, automated code reviews, run CI/CD
17-
workflows, sync repository changes.
18-
</Card>
19-
<Card title="Linear" icon="file-lines" href="/integrations/linear">
20-
Create and update issues automatically, track development progress, link
21-
code changes to tickets.
22-
</Card>
23-
<Card title="Slack" icon="slack" href="/integrations/slack">
24-
Chat directly in channels, get real-time notifications, share code snippets
25-
and updates.
26-
</Card>
27-
<Card title="Notion" icon="books" href="/integrations/notion">
28-
Access workspace documentation, update pages and databases, sync development
29-
information.
30-
</Card>
31-
<Card title="Figma" icon="figma" href="/integrations/figma">
32-
Access design specifications, extract design assets, convert designs to
33-
code.
34-
</Card>
35-
<Card title="CircleCI" icon="circle-play" href="/integrations/circleci">
36-
View broken checks, analyze build logs, automatically fix failing PRs and
37-
wake up on failures.
38-
</Card>
39-
<Card title="PostgreSQL" icon="postgres" href="/integrations/postgres">
40-
Execute SQL queries directly, analyze database schemas, generate data
41-
insights.
42-
</Card>
43-
</CardGroup>
44-
45-
## Core Features
46-
47-
Fundamental capabilities for comprehensive development support:
48-
49-
<CardGroup cols={2}>
50-
<Card title="Code Execution Sandbox" icon="box" href="/sandboxes/overview">
51-
Safely run code, install dependencies, and test changes in an isolated
52-
environment.
53-
</Card>
54-
<Card title="Web Search" icon="globe" href="/integrations/web-search">
55-
Access up-to-date information, research libraries, find documentation
56-
online.
57-
</Card>
58-
</CardGroup>
59-
60-
<Note>
61-
These capabilities allow Codegen agents to handle complex tasks across
62-
multiple systems, just like a human developer.
63-
</Note>
8+
Codegen agents follow a simple but powerful workflow: they're triggered from your existing tools, work in secure sandboxes to implement changes, create pull requests, and then monitor and fix any issues that arise. This creates a seamless development experience that integrates naturally with your team's existing processes.
9+
10+
## The Agent Happy Path
11+
12+
Here's how Codegen agents work from start to finish:
13+
14+
```mermaid
15+
graph TD
16+
A[Trigger from Integration] --> B[Work in Remote Sandbox]
17+
B --> C[Create Pull Request]
18+
C --> D[Monitor CI Checks]
19+
D --> E[Auto-fix Failed Checks]
20+
E --> D
21+
D --> D1[All checks pass ✓]
22+
D1 --> G[Ready for Review]
23+
G --> F[Respond to Follow-up Questions]
24+
F --> G
25+
26+
A1[Slack @mention] --> A
27+
A2[Linear issue assignment] --> A
28+
A3[GitHub issue comment] --> A
29+
```
30+
31+
### 1. Trigger `@codegen` from Your Tools
32+
33+
Agents activate seamlessly from the platforms you already use:
34+
35+
- **[Slack](/integrations/slack)** - Tag `@codegen` in any channel or send a direct message
36+
- **[Linear](/integrations/linear)** - Assign an issue to Codegen or mention it in comments
37+
- **[Jira](/integrations/jira)** - Assign an issue to Codegen or mention it in comments
38+
- **[ClickUp](/integrations/clickup)** - Assign a task to Codegen or mention it in comments
39+
- **[Monday.com](/integrations/monday)** - Assign an item to Codegen or mention it in comments
40+
- **[GitHub](/integrations/github)** - Comment on issues or PRs to request changes
41+
- **[API](http://localhost:3001/api-reference/agents/create-agent-run)** - Programmatically trigger agents for automated workflows
42+
43+
### 2. Work in Secure Sandboxes
44+
45+
Once triggered, agents work in **[isolated sandbox environments](/sandboxes/overview)** where they can:
46+
47+
- Execute code safely without affecting your systems
48+
- Install dependencies and run tests
49+
- Make changes and validate them before committing
50+
- Access your repository context while maintaining security
51+
52+
### 3. Create and Manage Pull Requests
53+
54+
Agents create **[GitHub pull requests](/integrations/github)** with:
55+
56+
- Detailed descriptions explaining the changes
57+
- Links back to the original request (Linear issue, Slack thread, etc.)
58+
- Clean, tested code ready for review
59+
- Proper commit messages following your conventions
60+
61+
### 4. Monitor and Auto-fix Issues
62+
63+
The **[Checks Auto-fixer](/capabilities/checks-autofixer)** ensures quality by:
64+
65+
- Monitoring CI/CD pipeline results in real-time
66+
- Automatically analyzing build failures and test errors
67+
- Pushing targeted fixes to resolve issues
68+
- Retrying up to 3 times before escalating to humans
69+
70+
### 5. Respond to Follow-ups
71+
72+
Agents remain active to handle questions and refinements:
73+
74+
- Respond to PR review comments with additional changes
75+
- Answer questions in the original Slack thread or Linear issue
76+
- Make adjustments based on feedback from team members
77+
- Provide explanations of their implementation decisions
78+
79+
## Configuration & Customization
80+
81+
Codegen agents can be customized to match your team's specific workflows and requirements:
82+
83+
### Model Selection
84+
85+
Choose from leading AI models and configure custom API keys to optimize performance and cost for your organization.
86+
87+
<Card
88+
title="Model Configuration"
89+
icon="brain-circuit"
90+
href="/settings/model-configuration"
91+
>
92+
Select LLM providers, configure custom API keys, and optimize performance
93+
settings.
94+
</Card>
95+
96+
### Agent Behavior
97+
98+
Control how agents interact with users and approach code modifications to ensure they align with your team's preferences.
99+
100+
<Card title="Agent Behavior" icon="robot" href="/settings/agent-behavior">
101+
Configure plan proposals, GitHub mention requirements, and interaction
102+
patterns.
103+
</Card>
104+
105+
### Security & Permissions
106+
107+
Define what actions agents are allowed to perform across your organization with fine-grained permission controls.
108+
109+
<Card
110+
title="Agent Permissions"
111+
icon="shield-check"
112+
href="/settings/agent-permissions"
113+
>
114+
Control PR creation, rules detection, and enforce security policies like
115+
signed commits.
116+
</Card>
117+
118+
<Tip>
119+
Start with conservative settings and gradually expand agent capabilities as
120+
your team becomes comfortable with AI assistance.
121+
</Tip>
122+
123+
## Learn More
124+
125+
Dive deeper into specific capabilities:
126+
127+
- **[Get started with the overview](/introduction/overview)** - Complete introduction to Codegen
128+
- **[Explore integrations](/integrations/integrations)** - See all available platforms and tools
129+
- **[Understand sandboxes](/sandboxes/overview)** - Learn about the secure execution environment
130+
- **[Configure settings](/settings/settings)** - Customize agent behavior and permissions
131+
- **[View analytics](/capabilities/analytics)** - Monitor agent performance and impact

docs/capabilities/checks-autofixer.mdx

Lines changed: 1 addition & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ sidebarTitle: "Checks Auto-fixer"
44
icon: "bell"
55
---
66

7-
When GitHub checks fail on a Codegen PR, Codegen agents will automatically "wake up", analyze the failure, and push fix commit.
7+
When GitHub checks fail on a Codegen PR, Codegen agents will automatically "wake up", analyze the failure, and push fix commits.
88

99
<video
1010
controls
@@ -106,10 +106,3 @@ The auto-fix system integrates deeply with GitHub:
106106
access and the feature is enabled. It respects your repository permissions and
107107
team workflows.
108108
</Note>
109-
110-
## Benefits
111-
112-
- **Reduced Context Switching:** No need to manually investigate and fix CI failures
113-
- **Faster Iteration:** PRs get fixed automatically, keeping development velocity high
114-
- **Learning from Failures:** Each fix improves Codegen's understanding of your codebase
115-
- **24/7 Monitoring:** Works around the clock to keep your PRs in good shape

docs/docs.json

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -41,7 +41,8 @@
4141
"settings/repo-rules",
4242
"settings/model-configuration",
4343
"settings/agent-behavior",
44-
"settings/agent-permissions"
44+
"settings/agent-permissions",
45+
"settings/team-roles"
4546
]
4647
},
4748
{

docs/introduction/overview.mdx

Lines changed: 18 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ icon: "robot"
55
iconType: "solid"
66
---
77

8-
Codegen provides intelligent AI agents designed to seamlessly integrate into your existing developer workflows.
8+
Codegen helps you run frontier code agents at scale. It provides the necessary building blocks (sandboxes, integrations, telemetry) for successful enterprise code agent deployments across thousands of teams today.
99

1010
Think of it as an AI coworker that can understand and solve coding challenges, access your codebase instantly, and interact directly with your development tools.
1111

@@ -109,3 +109,20 @@ Codegen is SOC 2 Type II certified, ensuring your code and data are handled with
109109
Learn how to use Codegen for common code transformation tasks.
110110
</Card>
111111
</CardGroup>
112+
113+
## Learn More
114+
115+
<CardGroup cols={2}>
116+
<Card
117+
title="Join the Community"
118+
icon="people-group"
119+
href="/introduction/community"
120+
>
121+
Connect with other developers, get help, and share your experiences in our
122+
active Slack workspace.
123+
</Card>
124+
<Card title="About Codegen" icon="building" href="/introduction/about">
125+
Learn about our mission to build fully-autonomous software engineering and
126+
meet the team.
127+
</Card>
128+
</CardGroup>

docs/settings/agent-permissions.mdx

Lines changed: 9 additions & 43 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,14 @@ icon: "shield-check"
66

77
Configure what actions the AI agent is allowed to perform across your organization. These permission settings provide fine-grained control over agent capabilities to ensure they operate within your security and workflow requirements.
88

9+
<Card
10+
title="Configure Agent Permissions"
11+
icon="shield-check"
12+
href="https://codegen.com/settings/permissions"
13+
>
14+
Control what actions agents are allowed to perform in your organization.
15+
</Card>
16+
917
## Available Permissions
1018

1119
### Enable PR Creation
@@ -28,7 +36,7 @@ Control whether the codegen agent is able to create pull requests in your reposi
2836

2937
### Enable Rules Detection
3038

31-
Allow the agent to automatically detect and apply rules from various rule files in your repositories.
39+
Allow the agent to automatically detect and apply rules from various rule files in your repositories. You can also configure manual repository rules at [codegen.com/settings/repo-rules](http://localhost:3001/settings/repo-rules).
3240

3341
**Supported rule file formats:**
3442

@@ -90,48 +98,6 @@ Access your agent permissions at:
9098
Control what actions agents are allowed to perform in your organization.
9199
</Card>
92100

93-
## Permission Combinations
94-
95-
### Development Teams
96-
97-
```
98-
✅ Enable PR Creation
99-
✅ Enable Rules Detection
100-
❌ Enforce Signed Commits (unless required)
101-
```
102-
103-
Standard setup for most development teams wanting full agent capabilities.
104-
105-
### Security-Conscious Organizations
106-
107-
```
108-
✅ Enable PR Creation
109-
✅ Enable Rules Detection
110-
✅ Enforce Signed Commits
111-
```
112-
113-
Maximum security with full agent functionality and commit verification.
114-
115-
### Read-Only Advisory Mode
116-
117-
```
118-
❌ Enable PR Creation
119-
✅ Enable Rules Detection
120-
❌ Enforce Signed Commits
121-
```
122-
123-
Agents provide analysis and suggestions without making direct code changes.
124-
125-
### Compliance-First Approach
126-
127-
```
128-
✅ Enable PR Creation
129-
❌ Enable Rules Detection
130-
✅ Enforce Signed Commits
131-
```
132-
133-
Strict control with manual rule management and required commit signing.
134-
135101
## Best Practices
136102

137103
**Start Conservative:**

docs/settings/settings.mdx

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -47,6 +47,15 @@ Configure Codegen to work perfectly with your development workflow. Customize ag
4747
</Card>
4848
</CardGroup>
4949

50+
## Team Management
51+
52+
<CardGroup cols={2}>
53+
<Card title="Team & User Roles" icon="users" href="/settings/team-roles">
54+
Manage team members and control access through hierarchical role permissions
55+
for admins, managers, and members.
56+
</Card>
57+
</CardGroup>
58+
5059
## Global Configuration
5160

5261
<CardGroup cols={2}>
@@ -67,6 +76,7 @@ Settings are organized into repository-level and organization-level configuratio
6776
- **Repository Rules** apply to specific repositories and help agents understand your coding standards and project-specific requirements
6877
- **Agent Behavior** controls how agents interact with users and approach code modifications
6978
- **Agent Permissions** defines what actions agents are allowed to perform across your organization
79+
- **Team & User Roles** manages team member access through hierarchical permissions (Member, Manager, Admin)
7080
- **Model Configuration** applies globally to your organization and controls which AI models power your agents
7181

7282
<Tip>

0 commit comments

Comments
 (0)