Skip to content

AI agent governance

Nothing sensitive moves without your say so.

Every Machine-like agent starts in draft mode. Anything that spends money, reaches a customer, or changes a record you care about stops at a gate until a person signs.

Autonomy is earned one category of work at a time, and every action leaves a receipt. Machine-like enforces your rules on every action. You make the calls that need you.

Start for freeSee what waits for you

No credit card. Your operating policy is finalized with you on the scoping call.

Default
Draft mode on every new agent
Gated
Customer-visible writes and anything high risk
Silence
An unanswered request expires. It is never a yes.
Off
Pause any agent from your Terminal

Founder-led teams run on Machine-like agents

  • fitDEGREE
  • Lake
  • espresso.ai
  • Customer Science Group
  • Course Careers
  • Alarm New England

How does Machine-like decide what an agent may do?

Every action has a risk tier.

Machine-like sorts every action an agent can take into one of five risk tiers before the agent touches anything. The tier sets the default: the action runs, lands as a draft, follows your policy, waits for a person, or never happens.

Tier ladderSorted this week 1,284
  1. R0Read onlyLook something up. Nothing changes.Runs
  2. R1Draft onlyPrepare work that nobody sees yet.Lands as a draft
  3. R2Reversible writeAn internal change that can be undone.Your policy decides
  4. R3Customer-visible writeAnything a customer, lead, or the public would see.Waits for you
  5. R4High riskMoney, deletions, bulk sends, tracking, legal.Blocked by default
Gate tablePick a tool. Tighten any row.
Inbox · default gates
ActionTierDefaultAdjust
Read and sort new mailR0Runs
Draft a reply in your voiceLands in your drafts folderR1Draft
Label, file, or archive a threadR2Your policy
Send a reply to a customer or leadR3Waits for you
Email a list or send in bulkR4Blocked
Policy log
  1. Default table, set at scopingActive

Starting point. Common actions and their default tiers. Your exact table is set during scoping. Tighten any row whenever you like. Loosening one takes your signature.

Can an agent act on its own?

Autonomy gets earned.

A Machine-like agent acts on its own only in a category of work you have promoted, inside written limits. Every new agent starts at Assisted, where nothing applies until a person approves, and no category climbs without your signature.

Autonomy boardSupport agentIllustrative

Levels apply to a category of work, not to the whole agent. This agent sends order updates on its own and still asks before it quotes a price.

  1. L3TrustedRuns an approved category on its own, inside written limits. You review the exceptions.By promotion
  2. L2GuardedApplies low-risk, reversible changes itself. Anything customer-visible still waits.By promotion
  3. L1AssistedPrepares the exact change and the packet. Nothing applies until a person approves.Default
  4. L0ManualDrafts and recommends only. A person makes every change by hand.Available

How a category climbs.

Promotion is a proposal with evidence, never a setting someone flips. Revoking it takes one click, and the category drops back to draft mode on its next action.

  1. 1A clean record, attached.

    Machine-like proposes a promotion only for a category with a run of approvals you didn’t need to edit and exceptions routed correctly.

  2. 2Written limits.

    The proposal names the category and its ceilings: volume per day, who it may contact, records it may touch, and spend.

  3. 3Your signature.

    Nothing changes until you sign in the Terminal. Each signature is logged with the policy version it created.

Who checks an agent’s work before it reaches me?

Two keys turn during review.

Machine-like checks each gated packet against your policy and sources before it reaches you. You then approve, request changes, or reject it from your Terminal inbox, and your policy can require both keys on customer-visible and high-risk work.

Path of a gated action
  1. 01AgentDraftThe agent prepares the work from your rules and sources.
  2. 02SystemDry runA preview of the exact change, before and after. Nothing is touched yet.
  3. Key 1UsOur checkMachine-like reviews the packet against your policy and sources.
  4. Key 2YouYour approvalApprove, request changes, or reject from your Terminal inbox.
  5. 05SystemApply onceThe change is made a single time, even if a step retries.
  6. 06SystemVerifyThe agent confirms the change landed where it should.
  7. 07YouReceiptThe whole path, on the record.
Where it lands

Your Terminal inbox, with the full packet: the change, the reason, and the sources.

What you can do

Approve, request changes, or reject. Your note goes back to the agent with the packet.

If you’re away

The request waits until it expires. Nothing runs on silence, and the expiry is logged.

Who reviews first

Agents you build yourself

You are the first and only reviewer. You also find out what broke.

Machine-like

We check the work before it reaches you, and we own the fix when something goes wrong.

What record does an agent leave behind?

Every action prints a receipt.

Machine-like keeps a receipt for every agent run: what triggered it, what the agent did, who signed, and proof the change landed. Each receipt is written for a person and attached to the result it produced.

  1. 1
    The trigger and the inputs

    What started the run and exactly what the agent read.

  2. 2
    Every step, in order

    Each tool the agent used and what it produced.

  3. 3
    The preview

    The exact change before it happened, with a before and after.

  4. 4
    The gate and the decision

    Which approvals were required, who gave them, and when.

  5. 5
    The write, once

    Applied a single time. A retried step can’t send twice.

  6. 6
    The proof

    A check that the change is really there in your system.

“Our partners at Machine-like gave us a more responsive support operation without forcing a massive migration. The agents worked across our systems and kept me in the loop when something needed my attention.”

fitDEGREENick HaleCEO & Co-Founder, fitDEGREERead the fitDEGREE story

What happens if an agent makes a mistake?

If it runs off course, we get it back on track.

Machine-like halts a run when a change can’t be verified, is alerted first, reverses what can be reversed, and fixes and re-tests the workflow before the agent runs again. The risk of an unintended action is low but never zero, and handling it is Machine-like’s job, not yours.

  1. It stops.

    When a change can’t be verified, the run halts and holds. The agent doesn’t guess, and it doesn’t retry its way into a second mistake.

  2. We hear first.

    Machine-like is alerted. You get a plain-language note in your Terminal explaining what happened and what’s being done.

  3. It gets undone.

    Writes are built with a rollback path. A reversible change is reversed, and the reversal goes on the receipt.

  4. The rule gets fixed.

    We patch the workflow or the policy and test it again before the agent runs the next job. You never debug an agent.

Example agent

Your off switch.

Pause any agent from your Terminal. A paused agent refuses new work on its next action and stays paused until you turn it back on.

Who is in charge of the rules an agent follows?

We manage. You decide.

You decide the goals, limits, and approvals, and Machine-like enforces them on every action. Your rules become policy the platform checks before each action runs, not instructions an agent tries to remember, so an agent can’t talk its way past a gate.

You decideOwner

The goals and the limits.

  • What done looks like for each job
  • Which systems the agent may reach
  • Limits on volume, recipients, records, and spend
  • The off-limits list: actions that never happen
  • Who approves what, and how fast
  • How much autonomy each category has

We enforceMachine-like

On every action, every time.

  • Checks each action against your policy before it runs
  • Blocks off-limits actions outright, with no override from the agent
  • Walls off your data from every other customer’s, down to the database
  • Keeps your logins out of the agent’s hands; you can revoke any connection
  • Logs every decision and every change to your policy
  • Owns the fix when something breaks

Need the detail for a security review?See security policies

What will my agent’s rules look like?

Your rules are written down, never inferred.

Machine-like gives every customer a one-page operating policy in plain English, mapped to the same tiers and gates the agent runs under. Draft yours here in about two minutes with no account, then finalize it on the scoping call.

Tools it can reach
How carefully to start
Who approves
  1. 01
    It’s a real starting point.

    The draft maps to the same tiers and gates your agent runs under.

  2. 02
    It shortens scoping.

    We start the call from your limits instead of a blank page.

  3. 03
    It’s yours to change.

    Tighten anything now. Loosen it later, with evidence and your signature.

Operating policy · draftPOL-3740 · v1
Yours to keep
Tools in scope
Inbox, CRM.
Runs freely
Reading and sorting mail, drafting replies; filing and labeling threads; looking up records, writing account briefs; adding notes and tasks.
Waits for you
Replies to customers or leads; deal stage or owner changes.
Never
Bulk or list email; deleting or merging records.
Approver
You approve every gated action. Unanswered requests expire.
Autonomy
Starts at Assisted. Moves up only by proposal, with evidence and your signature.

No credit card. Your policy is finalized on the scoping call.

Questions

Asked before connecting anything.

The questions owners ask before they give an agent access to anything.

Will an agent ever email my customers without my approval?

Not by default. Any message to a customer, prospect, or lead is a customer-visible write, and it waits for a person. A category of messages can send on its own only after Machine-like proposes a promotion with evidence and written limits, and you sign it. Bulk sends are blocked by default.

If I have to approve things, what am I saving?

The work itself. Reading, researching, and drafting never wait for you, so an approval is one decision on finished work, not a task. Approval is the starting point, not the steady state: as a category builds a clean record, we propose moving it up, and you approve less over time.

What happens if I don’t answer an approval request?

Nothing. Every request carries an expiry. If it lapses, the action does not happen and the request is logged as expired. Silence is never treated as a yes.

Can I turn an agent off?

Yes. Pause any agent from your Terminal. A paused agent refuses new work on its next action and stays paused until you turn it back on. Revoking a promotion drops that category back to draft mode the same way.

Can Machine-like or the agent see my passwords?

You authorize each connection yourself, and your raw logins stay out of the agent’s hands. You can revoke any connection at any time. Your data is kept separate from every other customer’s at the database layer. Security policies have the detail.

Can I change the rules later?

Yes. You can tighten any rule at any time. Loosening a rule takes your signature, and every change creates a new policy version on the record.

Your first agent

Hand off the work. Keep the say so.

Machine-like offers a free 14-day evaluation of a scoped workload after the agent is built and deployed. Every new agent starts in draft mode, so you judge finished work before anything reaches a customer.

Bring one recurring job and the rules it has to follow. We write the policy with you on the scoping call, build the agent, and take responsibility for keeping it inside the lines.

Start for free