Consumer agent controls
Spend controls for personal assistants
Each user sets which merchants their assistant can use, how much, and when to ask.
Industries
Personal agents · Travel & events · Delivery & gig work · Hospitality
Best for
Assistants in iMessage, WhatsApp, and Telegram
Controls
Merchant rules, spend caps, approval thresholds, per user
Outcome
Users delegate spending because they set the boundary
How a user's rules reach the payment
Your user sets the rules once. Conto checks every attempt against them before money moves.
Step 1
Your user sets the rules
Merchants, spend limits, and the amount that needs their approval first.
Step 2
Conto checks every attempt
Merchant, amount, and category, weighed against that user's rules in the payment path.
Step 3
It clears, asks, or stops
Routine spending settles. Anything over the threshold goes back to them in one tap.
Rails
The same rules, on the card your user already carries
Controls are not tied to one rail. Your user connects the card they already have and Conto gates the credential, so the assistant spends under their rules without ever holding the card. Conto-issued cards for the assistant itself are in pilot.
Ask about the card pilotAvailable now
Connected cards. The credential is never stored by Conto or released to the agent.
Coming soon
Conto-issued cards, with each authorization decided against the same rules in real time.
Either way
The rules, the approvals, and the record do not change with the rail.
How each attempt is decided against the rules your user set
What your user set
36% spent · $320 left
Set by the user in your product, stored per user, enforced by Conto.
What the assistant tried
Blue Bottle
food · saved merchant
under the ask threshold
REI
shopping · saved merchant
Approve $214.00 at REI?
one-time link · Telegram, WhatsApp, email, or your webhook
over $100
unknown-store.co
not on the list
over $300 · merchant not allowed
Conto does not run the checkout. It holds the rules each user set and decides every attempt against them before money moves, so routine spending never interrupts anyone and only the cases the user asked about come back to them.
The dials you can hand your users
Each of these is set per user and checked at the payment. Expose as many as suit your product, from a single monthly cap to the full set.
Spend limits, per purchase and rolling
A ceiling on any single purchase, plus daily, weekly, and monthly budgets. A runaway loop or a misread instruction hits the cap, not the account balance.
Merchant and category rules
The user decides where the assistant can spend. Groceries and rides can be routine while gift cards, transfers, and unknown merchants stay off the table entirely.
Approval thresholds, and where the question lands
The user sets the amount that needs their approval. Above it, a signed one-time approve-or-decline link goes to Telegram, WhatsApp, Slack, email, or your own webhook, landing in a thread they already have open.
Guardrails the assistant cannot talk its way past
Velocity limits, repeat-charge detection, and hard stops sit under the user-facing dials. They are enforced in the payment path, so a prompt injection that reaches the model still meets the same wall.
Every decision, with the rule that made it
Every attempt carries the merchant, the amount, the rule that decided it, and the approval that released it, so a disputed charge is a lookup rather than an investigation.
Row L, two seats for Friday. That is $129, over the $100 you asked me to check with you on.
Ticketmaster
events · 2 tickets
one-time link · Telegram, WhatsApp, email, or your webhook
Cleared without asking
Blue Bottle Coffee
food · 8:02am
Target
shopping · yesterday
Demo
Your assistant spends up to the ceiling you set
Under $100 the checkout clears on its own, and anything higher sends the approval to your chat instead of the charge.
Conto products behind assistant spend controls
Human review
Approvals
Route only the payment requests that need judgment to a human reviewer, with the triggering policy, recipient, amount, and agent context already attached.
Explore productRuntime controls
Policy Engine
Define the rules for how agents spend, then evaluate every payment request before funds move. Conto keeps limits, categories, trust requirements, and approval rules in the transaction path.
Explore productFinancial visibility
Audit and Reconciliation
Attach agent, counterparty, policy, approval, and execution context to every transaction so finance can understand what happened without chasing separate systems.
Explore productWhat the control layer buys you
Users hand an assistant real spending power, because they set the limits themselves instead of trusting yours.
You ship granular spend controls without building a policy engine, a per-user limits ledger, or an approval system.
A compromised prompt cannot become an unbounded charge, because the rules are checked at the payment rather than in the model.
Support and trust teams can show which purchase happened, which rule allowed it, and who approved it.
Demos with consumer-style spend
Personal Agent
Personal agents
The assistant in your texts, spending only where you allow
ExploreTravel Booking Agent
Travel & events
Delegated booking agents with hard mandate and price-drift controls
ExploreDispatch Agent
Delivery & gig work
Instant driver payouts with policy-controlled tips and surge
ExploreGuest Recovery Agent
Hospitality
Guest-service agents can issue make-good credits without becoming a blank check
Explore