-
-
Sign in
-
Hybrid control: let SIKA confirm purchases within a per-purchase and daily limit, until a date you choose. Revocable anytime.
-
SIKA captures after a verified approval and shows "Paid" only for a COMPLETED capture with the expected amount.
-
“Honest” Payment Terms: The order is successfully placed, but payment is not processed until you approve it.
-
Natural Language Request and Agent Steps
-
Click “Confirm” to confirm your order. No amount will be charged until you confirm the order.
-
Home: Ask SIKA your questions, shop, compare products, pay for your subscriptions, and track the status of each payment in real time.
-
Above your authorized limit, the server refuses to let SIKA confirm, and the decision comes back to you.
-
Check before paying: SIKA distinguishes between what it has verified, what you have entered, and what it has assumed.
-
For products outside the store, SIKA compares real online offers through Channel3. You pay on the merchant's site. Brands blurred.
-
Architecture: Gemini decides what to do, the backend owns amounts and limits, and PayPal (sandbox) moves the money.
-
Products SIKA showed are followed automatically for 30 days.
-
Automatic following can be turned off in Settings.
-
-
Inspiration
Shopping with an AI assistant usually stops at advice: it finds a product, then leaves you alone with ten tabs, a budget to check and a payment form. Fully autonomous "agents that pay for you" go to the other extreme and ask for blind trust with your money.
I started SIKA at the Google "All Things Agentic" hackathon as a voice and chat assistant for Mobile Money users in West Africa. For the PayPal AI Hackathon, I rebuilt it into SIKA Pay: a conversational payment agent where the AI does the tedious work (searching, comparing, checking the budget, preparing the payment) and the user stays in control of every dollar. The whole payment layer was replaced by PayPal during the submission period, and the previous Mobile Money integration was removed.
What it does
You tell SIKA what you want, in English or French: "Help me buy an Excel course without going over 50 dollars."
- Buy from a partner store and pay with PayPal. SIKA searches the catalog of a demo merchant (SIKA Demo Store, fictional digital products) and prepares a PayPal checkout. The price and the budget check come from the server, never from the AI. You review a summary, confirm, approve on PayPal, and SIKA captures the payment server-side once PayPal confirms the approval. A payment is only shown as successful after a verified
COMPLETEDcapture with the expected amount. - Compare real products on the web. For products the store doesn't carry, SIKA searches real online merchants through the Channel3 product API and shows the three best matches with their best price. SIKA never pretends it can pay there: you open the merchant's page and pay on their site.
- Hybrid control. By default, you confirm every purchase. You can also grant SIKA a limited, revocable authorization (maximum per purchase, daily limit, expiry date). Within those limits SIKA can confirm a purchase for you; the server enforces the limits and refuses anything above them, and you still approve the order on PayPal.
- Log in with PayPal. Sign in with your PayPal account (OpenID Connect); a verified PayPal account marks your identity as verified.
- SIKA keeps an eye on prices for you. Every product SIKA shows you is followed automatically for 30 days, without asking. When the best offer changes (price drop or increase, back in stock, out of stock, a cheaper merchant, an offer removed), SIKA tells you in the app and with a push notification. You can still ask for a target price ("Tell me when these headphones drop below $50"). No spam: changes under 2% or $1 are ignored, at most one alert per product per day, nothing at night. Alerts never buy anything, and automatic following can be turned off in Settings.
- Subscriptions (beta). SIKA compares monthly plans from the demo store and prepares a PayPal subscription that you confirm and approve on PayPal. The plans were created on PayPal with the PayPal MCP server.
- Web dashboard (AG Studio). In the app, Settings > Web dashboard shows a single-use code; enter it on a computer to open a read-only dashboard of your own data: payments, the payment journey (prepared > waiting for PayPal > paid), who confirmed each purchase (you, or SIKA within your authorization), followed products and price changes. Ask its assistant in plain language, for example "What did SIKA pay for me?": it queries the data, filters the table and answers with the total.
All payments run on the PayPal sandbox: no real money moves.
How I built it
- Mobile app: Flutter (Android) with Riverpod, in English and French. The UI only displays statuses returned by the backend.
- Backend: FastAPI on Google Cloud Run with Cloud SQL (PostgreSQL) and Secret Manager, deployed by GitHub Actions only after the test suite passes.
- AI agent: Gemini on Vertex AI with function calling, in a bounded loop. Every tool call goes through a server-side registry: an allow-list of tools, the authenticated user ID injected by the server (the model never sees it), and no tool that can approve or capture a payment. The tool that confirms on the user's behalf is only exposed to the model while the user has an active authorization. The app shows the agent's observable steps, never its internal reasoning.
- PayPal: Orders v2 with
PayPal-Request-Ididempotency for creation and capture, server-side status verification before any capture, signed webhooks (verified with PayPal'sverify-webhook-signatureand deduplicated) as a second path to capture, error handling based on PayPal's payment-failure guidance, Log in with PayPal, the Subscriptions API, and the PayPal MCP server to create the subscription plans. - Channel3: product search, multi-merchant offers, and free product subscriptions (
offer.price.changed,offer.availability.changed,offer.created,offer.deleted) delivered by webhooks verified with Standard Webhooks signatures and deduplicated. - Push notifications: Firebase Cloud Messaging (HTTP v1), sent by the backend with the Cloud Run service account, so no key is stored in the code. Expired tokens are removed, and the phone is unregistered at log out.
- AG Studio (AG Grid): a React dashboard served by the backend, in the SIKA Pay theme, with two custom widgets (the authorization meter and the payment journey). Its assistant uses the Studio Agent Framework with Gemini swapped in as the model: a custom SIKA agent leads the conversation and delegates page work to Studio's built-in planning, data, page and widget agents. Each model turn goes through the backend to Gemini on Vertex AI, so no model key reaches the browser. The dashboard session uses a token limited to the dashboard's own routes: it cannot pay or change anything.
Challenges I ran into
- Letting an AI near money without trusting it with money. The model chooses a product and a quantity; the server computes the price, checks the budget and binds the confirmation to that exact checkout. Amounts and identity never come from the model.
- Honest payment states. "Order created", "approved" and "captured" are different things, and a network timeout is not a success. A lost response becomes
UNKNOWN_RESULTand is checked with PayPal instead of being shown as paid. - Avoiding double captures. Returning to the app and receiving the webhook can happen at the same time. Stable request IDs and server-side status checks make sure an order is captured once.
- Too many confirmations. My first flow asked the user to confirm four times. I reduced it to one confirmation in the app plus the approval on PayPal, with automatic capture after a verified approval.
- Mobile redirects. PayPal only accepts registered redirect URLs, so I added a server return page that hands the result back to the app.
Accomplishments that I'm proud of
- Complete purchases on the PayPal sandbox, from a sentence to a verified capture, tested on a device against the deployed backend: a user-confirmed purchase, an agent-confirmed purchase within an authorization, a purchase refused above the authorized limit, and a cancellation on PayPal.
- A safety model that does not depend on the AI behaving: server-side amounts, server-injected identity, a tool allow-list and limits enforced by the backend.
- 188 automated backend tests that never call PayPal (a test double replaces it), covering tampering, cross-user access, idempotency, declines, network failures and webhook signatures, plus a script that runs the real sandbox flow.
- A product that is honest about what it can and cannot do, for example that it cannot pay on third-party websites.
What I learned
- In agentic payments, the key decision is where to draw the line: the model is excellent at understanding intent and comparing options, and should never be the source of truth for an amount or a payment status.
- Idempotency and webhooks matter even in a demo: real payment flows fail in the middle.
- User control and convenience can coexist: a limited, revocable authorization gives speed without blind trust.
What's next for SIKA Pay
- Natural voice conversations (experimental). I am building a speech-to-speech mode with Gemini Live that uses the same tools and the same safety rules as the chat. It works end to end in my tests but is not released yet.
- Complete end-to-end testing of subscriptions on devices.
- Real merchants on PayPal checkout instead of a demo catalog.
- More currencies and an iOS release.
Built With
- ag-grid
- ag-studio
- agentic-ai
- alembic
- channel3
- fastapi
- firebase-cloud-messaging
- flutter
- google-cloud-run
- google-cloud-sql
- google-cloud-text-to-speech
- google-gemini
- google-secret-manager
- paypal
- paypal-mcp-server
- paypal-orders-v2
- paypal-subscriptions
- paypal-webhooks
- postgresql
- python
- react
- rest-api
- riverpod
- sqlalchemy
- vertex-ai