Give AI a task.
Keep control of the work.
WhoseDev Agent is designed to help you work across your codebase by turning high-level development requests into a structured sequence of coding actions.
The agent works within the capabilities, permissions, models, and tools configured in your WhoseDev environment.
Understand
Start with a development request in natural language. The agent can use the available workspace context to understand what you are asking it to change.
Plan
Break a larger request into smaller actions so the intended changes can be reviewed as a sequence instead of treating the entire task as one opaque operation.
Build
Generate or modify code according to the task and the tools available to the agent, while keeping the developer in the loop.
From request to implementation.
Agentic coding becomes more useful when the system can reason about a task as a sequence of changes instead of treating every prompt as an isolated completion.
Task
Describe what you want to accomplish.
Context
Use the workspace information available to the agent.
Plan
Determine the changes required to address the task.
Execute
Create or modify files using the available capabilities.
Review
Inspect the resulting changes before accepting them.
$ agent task
Analyze authentication flow
✓ workspace context loaded
✓ task structure prepared
→ planning changes...
▌
Less prompt-by-prompt work.
More focus on the outcome.
Traditional code completion is useful when you already know what line you want to write. An agent is useful when the work itself spans multiple files, decisions, and implementation steps.
Work at the task level
Describe an objective instead of manually converting every step into separate prompts.
Keep the developer involved
Agentic workflows do not remove the need for engineering judgment. You remain responsible for reviewing and accepting changes.
Use your existing workflow
The agent is intended to complement your editor, codebase, models, and development process rather than replace them.
Make complex work easier to reason about
Breaking a larger task into visible stages makes it easier to understand what the system is attempting to accomplish.
AI should work with your development environment, not dictate it.
WhoseDev is built around giving developers control over how AI participates in their workflow. Depending on your configuration, that can include choosing models, controlling what context is available, and deciding how agentic actions fit into your development process.
Model choice
Use the models and providers supported by your WhoseDev setup.
Context control
Control the project information made available to AI features.
Developer review
Review generated work and remain responsible for changes made to your codebase.
Start with what you actually want done.
"Fix the authentication flow"Investigate the relevant implementation, identify the required changes, and work through the task.
"Add a new API endpoint"Describe the endpoint and expected behavior, then let the agent help implement the associated code.
"Refactor this module"Give the agent a broader engineering objective instead of manually requesting every individual edit.
A note on agent capabilities
Agent behavior depends on the version of WhoseDev, the configured model, available tools, workspace permissions, network configuration, and other settings. AI-generated changes can be incorrect, so developers should review generated code and validate important changes before relying on them.
Build with an agent.
Stay in the driver's seat.
Explore WhoseDev and see how agent-assisted development can fit into the way you already build software.