Private pilot · sandbox and test mode only

Your AI agents can act. You stay in control.

Set what each agent may spend, send the purchases that matter to a person for approval, and keep a record of every decision. Built first for AI automation agencies and the businesses they serve.

We're choosing a small group of agencies as design partners. No real money moves through Fisher today.

Overview · Example clinic Sandbox · illustrative
Waiting for approval1
Denied this week1
Simulated spend$17.00
Team chat upgrade · $65.00/mo Needs approval

Rule: purchases over $40 need the clinic manager's approval.

Approve onceDeny
  • Design software, 1 month$17.00Allowed
  • Printing supplies invoice$240.00Denied
Illustrative sandbox screen. Not customer data, and no payment was made.
Today: policy decisions, approvals and audit in a sandbox No real money: Fisher does not move money or issue cards today Boundary: Fisher only controls actions that go through it
The problem

Agents can now spend. Few teams can say on what, up to how much, or who approved it.

Agents buy software, pay invoices and renew subscriptions. When you run them for several clients, the risk isn't one bad answer: it's an action nobody agreed to, and no record to show what happened.

No spending limits per agent

An API key or a saved card gives an agent the same authority as the person who set it up.

Approvals live in chat threads

"Is this OK?" in a message isn't a control: it's easy to miss, and hard to prove later.

No record you can show a client

When a client asks why their agent bought something, you need an answer with evidence.

What Fisher does

Four controls, one place.

Each card says what you can try in the sandbox today and what is still being built.

In the sandbox today

Spending policies

Per-agent limits per purchase and per month, and a list of approved vendors. Rules are written and testable. No AI model makes the allow/deny call, and anything not permitted is denied.

Vendor checks match by name today; verified payees are in development.

In the sandbox today

Human approvals

Purchases above a threshold wait for a signed-in approver using two-factor sign-in. An approval lets that exact request run once, and nothing else.

In the sandbox today

Agent controls

Each agent gets its own key and connects through an API or an MCP tool. Pause one agent, or all of them, at any time.

Hosted, sign-in-based connection for chat assistants is in development.

In the sandbox today

Audit trail

Every request, decision, approval and pause is recorded with the reason, and you can export it as a spreadsheet.

Sandbox walkthrough

One purchase request, start to finish.

An illustrative example. Fisher makes the decision; making a payment is a separate step, and in the sandbox no payment is ever made.

  1. 1

    The agent asks first

    A purchasing agent for an example clinic asks Fisher before buying.

    request_payment
      agent:   front-desk-assistant
      vendor:  "Team chat (Pro plan)"
      amount:  65.00 CAD / month
      reason:  "Free plan's message history is full"
  2. 2

    Fisher checks the policy

    • Pass Agent is active and its key is valid
    • Pass Vendor is on the approved list
    • Pass Within the $500 monthly limit
    • Rule Over $40: needs the clinic manager
  3. 3

    A person decides

    Needs approval · expires in 23 h

    Team chat (Pro plan), $65.00/month, requested by the front-desk assistant.

    Approving lets this exact amount run once.

  4. 4

    Decision and payment, kept apart

    DecisionApproved
    PaymentNot run · sandbox
    DecisionDenied
    PaymentNothing to run
  5. 5

    Everything is on the record

    • 20:39:02 Request received from front-desk-assistant
    • 20:39:02 Rule matched: over $40 needs approval
    • 20:51:47 Approved by clinic manager (two-factor sign-in)
    • 20:51:47 Payment step: not run (sandbox)

Illustrative sandbox example. Names, amounts and times are made up.

How Fisher works

Four steps.

01

Connect an agent

Give each agent its own key, through an API or an MCP tool.

02

Set its rules

Limits, approved vendors and when a person must approve.

03

Approve what matters

The right person sees what the agent wants and why, and decides.

04

Show the record

Every request and decision, ready to share with the client.

For agencies

Built for teams that run agents for many clients.

This is what we're building next, with design partners. Today's sandbox manages one business at a time.

  • A separate workspace, policy and record for each client In development
  • Approvals routed to each client's own approver In development
  • Policy templates you reuse across clients In development
  • A per-client report you can hand to the client Planned
Direction

Where payments fit, stated carefully.

Fisher's job is the decision. Over time we want approved decisions to connect to real payment rails. None of the later stages below is available today, and we have no partnerships to announce.

Now

Decisions in a sandbox

Policies, approvals and audit, tested with made-up requests and test-mode data only.

Exploring

Supported payment providers

Let an approved decision run once, exactly as approved, through providers we support. Subject to each provider's eligibility and terms.

Longer term

Cards and agent payment standards

Virtual cards through eligible infrastructure partners, and tokenized agent payments as industry standards mature.

What it controls

Clear about what Fisher can and can't do.

Fisher only controls actions that go through it. If an agent has its own direct access to a card, account or system and doesn't ask Fisher first, Fisher can't stop that action. Part of working with us is deciding together which actions to route through Fisher.

Fisher is in a private pilot and isn't generally available. It does not move money or issue cards today. Everything you see on this page runs in a sandbox with made-up or test-mode data.

Apply to be a design partner.

For agencies running action-taking AI agents for client businesses. You get early access to the sandbox and a direct line to the founder; we ask for a 30-minute conversation about how you control your agents today.

Apply by email

This opens your email app with a few short questions. Prefer to just say hello? Write to hello@fisherpay.ca.

  1. You email us with a few lines about your agency.
  2. We reply personally: no mailing list, no automated emails.
  3. We talk for 30 minutes and walk through the sandbox together.