BLAST RADIUSAI STRATEGY PROTOTYPE

How much power should you give an AI agent?

AI agents get useful when they can access your actual work.

Your inbox.
Your calendar.
Your files.
Your CRM.
Your money.

But every new permission changes what happens when the agent gets something wrong.

Build an Executive AI Agent and see its blast radius.

AI Executive Assistant

CONNECTED TO

RREMAILCALENDARDRIVESLACKCRMFINANCEEXTERNAL WORLDAI AGENTEXEC CREDENTIALS
Agent configuration

Executive Assistant

PURPOSE — Help an executive prepare for meetings, manage communications, coordinate their calendar, and keep internal systems updated.

Step 1

Give your agent context

Agents need context to be useful. Choose what this agent can see.
EMAILLOW

Read inbox

Agent can search and summarize email.

CALENDARLOW

Read calendar

Agent can see meetings, attendees, locations, and descriptions.

DRIVEMEDIUM

Search company documents

Agent can retrieve files across approved folders.

SLACKMEDIUM

Read internal conversations

Agent can search approved Slack channels.

CRMMEDIUM

Read customer records

Agent can view accounts, contacts, opportunities, and notes.

Step 2

Let your agent take action

Reading information is one thing.
Changing the world is another.
EMAILLOW

Draft Email

Agent can write email drafts for the executive.

EMAILHIGH

Send Email

Agent can send messages without approval.

CALENDARMEDIUM

Create Calendar Events

Agent can schedule meetings.

CALENDARHIGH

Cancel Meetings

Agent can cancel existing meetings.

CRMHIGH

Update CRM

Agent can modify customer records and opportunities.

SLACKHIGH

Send Slack Messages

Agent can communicate internally as the executive.

Step 3

Give your agent a credit card

Some agent platforms are beginning to connect AI directly to purchasing and financial systems.
Would you?
FinanceHIGH

Make purchases

Allow agent to purchase approved goods and services.

Live blast radiusAI EXECUTIVE ASSISTANT
RREMAILCALENDARDRIVESLACKCRMFINANCEEXTERNAL WORLDAI AGENTEXEC CREDENTIALS
  • RREAD(solid thin)
  • WWRITE(solid arrow)
  • XEXTERNAL ACTION(dashed arrow)
  • $MONEY(double stroke)
ACCESS
2 systems
AUTONOMY
1 / 10
REVERSIBILITY
High
BLAST RADIUS
Low
Step 4

Looks useful.

Live blast radiusAI EXECUTIVE ASSISTANT
RREMAILCALENDARDRIVESLACKCRMFINANCEEXTERNAL WORLDAI AGENTEXEC CREDENTIALS
  • RREAD(solid thin)
  • WWRITE(solid arrow)
  • XEXTERNAL ACTION(dashed arrow)
  • $MONEY(double stroke)
ACCESS
2 systems
AUTONOMY
1 / 10
REVERSIBILITY
High
BLAST RADIUS
Low

Would I ship this agent?

Verdict

Yes, with monitoring.

Your agent currently combines:

  • 2 systems of access
  • 0 write permissions
  • 0 external actions
  • no financial authority
  • no approval gates

That combination determines how far a single incorrect interpretation can travel.

  • DATA EXPOSURELOW

    The agent can read 2 sources of context.

  • ACTION AUTHORITYLOW

    The agent cannot change anything yet.

  • REVERSIBILITYHIGH

    Nothing the agent does today is hard to undo.

  • FINANCIAL AUTHORITYNONE

    The agent has no spending authority.

  • FAILURE PROPAGATIONLOW

    A mistake stays close to where it started.

Chanel's recommendation

Don't ask, “Can the AI do this?”

Ask:

  1. 01What does it need to see?
  2. 02What should it be allowed to change?
  3. 03Which actions are reversible?
  4. 04Where should a human approve?
  5. 05What happens when it's wrong?

The goal isn't zero autonomy.

The goal is bounded autonomy.

Give AI enough authority to remove friction without giving one mistake unlimited consequences.

Try another agent

Same question, different authority

Switching the agent changes its systems, its permissions, and the way one bad Tuesday plays out.

This is how I think about AI systems before we build them.

Office Hours with Chanel

THINK CLEARLY. BUILD SAFELY. SHIP LIKE A SENIOR ENGINEER.

If you're deciding how much access an AI agent should have, evaluating an internal AI proposal, or figuring out where humans should stay in the loop, that's exactly what we can work through together.