Tutorial: Creating Custom Agents
Create your own specialized AI agents that integrate with Bootspring's orchestration system.
What You'll Build
- A custom "code-reviewer" agent
- Custom prompts and personas
- Integration with Bootspring orchestrator
- Agent collaboration patterns
Prerequisites
- Bootspring Pro or higher
- Basic understanding of agent concepts
- Project with
bootspring.config.js
Understanding Custom Agents
Custom agents allow you to:
- Create domain-specific expertise
- Define custom prompts and behaviors
- Add project-specific knowledge
- Extend Bootspring's capabilities
Step 1: Agent Configuration
Create a custom agent in your Bootspring configuration:
Loading code block...
Step 2: Create the Agent Definition
Create a more detailed agent definition file:
Loading code block...
Step 3: Register the Agent
Register your custom agent with Bootspring:
Loading code block...
Step 4: Use the Custom Agent
Via CLI
Loading code block...
Via MCP
In Claude or your AI assistant:
Use the code-reviewer agent to review the authentication changes
Programmatically
Loading code block...
Step 5: Create Specialized Variants
Create variants for specific use cases:
Loading code block...
Step 6: Agent Collaboration
Configure how your custom agent collaborates with others:
Loading code block...
Step 7: Add Custom Tools
Create custom tools for your agent:
Loading code block...
Register the tool:
Loading code block...
Step 8: Add Context Providers
Create custom context providers:
Loading code block...
Step 9: Test Your Agent
Create tests for your custom agent:
Loading code block...
Step 10: Document Your Agent
Create documentation for your custom agent:
Loading code block...
PR Review
Loading code block...
Security Focus
Loading code block...
Example Output
Loading code block...
Collaboration
This agent automatically consults:
security-expertfor security issuesperformance-expertfor performance concernstesting-expertfor test coverage gaps
## Verification Checklist
- [ ] Agent configuration added to `bootspring.config.js`
- [ ] Agent definition file created
- [ ] Custom tools implemented (optional)
- [ ] Context providers configured (optional)
- [ ] Agent tests written
- [ ] Documentation created
- [ ] Agent accessible via CLI
- [ ] Collaboration patterns working
## What You Learned
- Creating custom agent configurations
- Defining agent personas and prompts
- Building custom tools
- Configuring context providers
- Setting up agent collaboration
- Testing custom agents
## Next Steps
- [Create domain-specific agents](/docs/agents)
- [Build agent workflows](/docs/tutorials/custom-workflows)
- [Integrate with external services](/docs/patterns/ai/agents)