← All workshopsRead What Should Botie Be Unable to Do?

Agent Guardrails and Secure Development

Put a control before each effect

BOTIE

Look up every effect in the application-owned policy. Keep the action IDs beside their requirements.
Ready to test
0 passed · 0 failed · 2 not run

An empty floor. Start with the information your machine needs.

Received result

Your answer will arrive here.

Examples, experiments and workspace controls
Live values

Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.

Try your own inputs

Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.

Start at an output arrow, then click or drag to an input. Drag empty space to pan. Delete removes a selection. Ctrl/Cmd+Z undoes a change.
Context for this challenge

Look up every effect in the application-owned policy. Keep the action IDs beside their requirements.

Botie can read a record and proposes publishing an answer. Publishing has additional requirements.

Inspect the component calculation
Find the required controls(
  Proposed effects: Proposed effects
  Application policy: Application-owned control policy
)
Examples and results
Proposed effects
[
  {
    "id": "read-7",
    "effect": "read"
  },
  {
    "id": "publish-7",
    "effect": "publish"
  }
]
Application-owned control policy
{
  "read": [
    "object-access"
  ],
  "publish": [
    "approval",
    "output-check"
  ]
}
Required result
[
  {
    "id": "read-7",
    "required": [
      "object-access"
    ]
  },
  {
    "id": "publish-7",
    "required": [
      "approval",
      "output-check"
    ]
  }
]
Proposed effects
[
  {
    "id": "read-7",
    "effect": "read"
  },
  {
    "id": "publish-7",
    "effect": "publish"
  }
]
Application-owned control policy
{
  "read": [
    "object-access"
  ],
  "publish": [
    "approval",
    "output-check"
  ]
}
Required result
[
  {
    "id": "read-7",
    "required": [
      "object-access"
    ]
  },
  {
    "id": "publish-7",
    "required": [
      "approval",
      "output-check"
    ]
  }
]
Try a fresh construction

This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.

Stuck? Inspect a worked construction

The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.

Assumptions and test precision

These are invented records and deterministic policy checks. The browser runs no agent, shell command, MCP server or network request. Passing these fixtures establishes only the stated policy behaviour. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.

Your last tested pieces can start the full construction. An existing draft there keeps its own pieces.

An unknown effect arrives with a reassuring control name

This check uses the pieces from “Stop the action with a gap”.

BOTIE

The request proposes erase, which is absent from policy. Installed names include unknown-effect. Predict whether that name can grant the missing permission.
Proposed effects
[
  {
    "id": "erase-1",
    "effect": "erase"
  }
]
Application-owned control policy
{
  "read": [
    "object-access"
  ]
}
Installed control names
  1. 0object-access
  2. 1unknown-effect

Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.

Build a construction in the workspace above first. This case will test those pieces.

What evidence would show that an installed check is enforced on every execution path?

Keep configuration coverage separate from observed enforcement.

These are invented records and deterministic policy checks. The browser runs no agent, shell command, MCP server or network request. Passing these fixtures establishes only the stated policy behaviour.

Work through the Python challenges →
Continue the courseCan Botie Fix the Bug Without Rewriting the Rules? →
← Repair Botie’s Maintenance Assistant