Bunny Redmine by Appar

Enterprise AI Governance

Control AI Employee identity, permissions, models, tools, approvals, audit logs, retention, and monthly budgets through Redmine.

Governed AI Employees

Treat every AI Employee as an accountable enterprise identity

Autonomous AI becomes useful when organizations can answer who acted, what it could access, which tools it used, what changed, who approved it, and how much it cost.

Identity

Bind each AI Employee to a Redmine account and its existing permissions.

Authority

Define tools, direct-write actions, confirmation points, schedules, and budgets.

Accountability

Retain a structured execution history that administrators can inspect and stop.

Enterprise controls

Govern the full AI execution surface—not only the model

Bunny places identity, tool access, model selection, memory, skills, scheduling, cost, and evidence under administrator control.

Illustrative product walkthroughConfigure each Employee before expanding autonomy.

Administrator settings

Example configuration

Give the project assistant only the model and tools required for this job.

Administrator-selected model

Cloud modelLocal model

Customer-provided API keys

Approved tools

create_issue

manage_wiki

create_project

Configured by system administrators

Review the configuration

Prepared result

The Employee has an explicit identity, model, and tool boundary.

Permissions and approval rules still apply. · Illustrative data

Illustrative product walkthrough

Begin with a Redmine identity and its existing permissions.Administrators choose an approved cloud or local model.Only expose the tools required for the Employee's work.Review approval rules, budgets, and logs before expanding the scope.

Account permissions

The Redmine account defines which projects, issues, and actions the AI may access.

Tool allowlists

Expose only approved Redmine, MCP, browser, communication, and enterprise tools.

Prompt and skill governance

Employees create private skills; administrators can govern all Employee behavior and notebook rules.

Model and API-key control

Use customer-provided keys, local models, or different approved models per Employee.

Approval boundaries

Choose which actions apply immediately and where human confirmation is mandatory.

Schedule control

Administrators can inspect or stop scheduled autonomous work; normal users cannot stop other Employees.

Controlled rollout

Expand autonomy only when the evidence supports it

Observe

Start with read-only analysis, project summaries, reports, and recommendations.

Approve

Enable tool use with explicit human confirmation at sensitive steps.

Automate

Allow trusted actions and schedules to take effect directly inside defined boundaries.

Audit, retention, and spend

A complete record of what the AI saw, did, changed, and spent

Bunny retains structured execution information permanently today, with configurable retention planned for organizations that need scheduled deletion.

ADMINISTRATOR CONTROLSGive AI a clear scope. Keep every action traceable.

AI EmployeeProject assistant

AI can access only what its Redmine account can access. Only the tools you allow are available to this Employee. At the monthly limit, the next job stops. See what ran, what was blocked, and why.

Bound Redmine accountProject manager · pm-teamSame project permissions as this account

Permitted projectAccessible

Restricted projectNot accessible

Tool allowlist

Only selected tools are available to this AI Employee.

create_issueAccessible

manage_wikiAccessible

create_projectNot accessible

Hard limit$50 USD

Budget reached. Execution stopped.

Start next scheduled jobBudget stop

Execution logs.json

ActionResult

Read permitted issueCompleted

Read restricted projectPermission denied

Start next scheduled jobBudget stop

View example JSON record

{
  "example": true,
  "account": "pm-team",
  "tool": "get_issue_content",
  "status": "completed",
  "monthly_budget_usd": 50,
  "next_execution": "budget_exceeded"
}

Monthly Employee budgetExample amounts

$32.40$50.00 / $50 USDUsage within budgetBudget stop

Configured by system administrators

Illustrative product walkthrough

Bunny inherits the bound account's access. Restricted projects stay restricted.Administrators choose the tools each AI Employee can use.A monthly hard limit stops execution when the configured budget is reached.Review the outcome and execution context in a structured JSON record.

Structured JSON history

Keep prompts, tool calls, results, modifications, errors, tokens, costs, and timestamps.

Evidence retention

Retain execution context and normal artifacts; large images can follow separate storage policies.

Per-run cost visibility

Employees can see the cost of their own AI work and understand resource consumption.

Company budget

Set a fixed monthly hard limit across the entire organization.

Employee budgets

Apply independent monthly limits to individual AI Employees.

Immediate stop

Administrators can stop active execution when required.

FAQ