DEV Community: Geo Jacob

Building automatic credit top-ups with Off-Session charging

Geo Jacob — Thu, 24 Sep 2026 05:50:41 +0000

One of our customers recently came to us with an interesting requirement.

They are building an AI product where customers purchase credits and consume those credits while using the product.

The requirement sounded simple:

When a customer's credit balance reaches a certain threshold, automatically charge their saved payment method and add more credits.

For example:

A customer buys 1,000 credits.

They keep using the product, and eventually their balance reaches zero.

Instead of asking the customer to go through checkout again, the product should automatically charge, say, $10 to the customer's saved payment method and add another 1,000 credits.

Simple, right?

Not exactly.

The problem with charging later

The first payment is straightforward because the customer is actively going through checkout.

But the next charge could happen hours, days, or weeks later.

The customer isn't sitting on the checkout page anymore.

This is where off-session charging comes in.

The merchant needs to be able to charge a customer's saved payment method without requiring the customer to actively participate in every transaction.

For AI products, this becomes especially useful.

Think about products that charge based on:

AI tokens
API calls
Agent runs
Compute usage
Image generations
Credits
Storage
Other usage-based resources

You don't necessarily want the customer to manually purchase credits every time their balance gets low.

But there are more problems to solve

Once we started thinking about the requirement, it became clear that simply exposing a "charge customer" API wasn't enough.

There are several things that can happen.

What if the card gets declined?

What if the payment requires additional authentication?

What if the payment succeeds but the application doesn't receive the response?

What if the application retries the request and accidentally charges the customer twice?

When should the new credits actually be granted?

And how does the application know whether the payment eventually succeeded or failed?

The payment itself is only one part of the workflow.

How we approached it

We wanted the merchant's application to control when the charge should happen.

For example, the application might have logic like:

Credit balance < 100 → charge $10 → add 1,000 credits

The application already knows the customer's usage through Kelviq's metering and entitlement system.

Once the threshold is reached, it can initiate an off-session charge against the customer's saved payment method.

But importantly, the application shouldn't assume that initiating the charge means the payment succeeded.

The payment needs to go through its lifecycle.

Once the charge succeeds, the application can receive the corresponding webhook and grant the additional credits.

So the flow becomes:

Customer purchases → payment method saved → customer consumes credits → threshold reached → off-session charge initiated → payment succeeds → webhook received → credits added

This keeps payment processing and product access connected without requiring the customer to repeatedly visit checkout.

Beyond AI credits

While the initial requirement came from an AI credit use case, we realized the same mechanism can support many other scenarios.

For example:

Automatic credit top-ups

Automatically purchase another credit pack when the balance gets low.

Usage-based billing

Charge customers based on accumulated usage.

One-time add-ons

Allow applications to trigger purchases for additional features or resources.

Custom billing workflows

Build billing logic where the application determines when and how much a customer should be charged.

This was one of those features where a customer requirement initially looked very specific, but solving it properly opened up a much broader set of use cases.

Now available in Kelviq

Kelviq now supports off-session charging through our Charges API.

Merchants can charge a customer's saved payment method programmatically and combine it with Kelviq's usage metering, credits, and entitlements to build custom monetization workflows.

For us, this is also an interesting direction.

As AI products become increasingly usage-driven, billing can't always be modeled as just:

$20/month → unlock Pro plan

Sometimes the product itself needs to participate in the billing decision.

Usage happens → application evaluates it → billing action happens → entitlement changes.

That's the kind of billing infrastructure we're trying to build with Kelviq.

Freelancers Are Becoming Founders

Geo Jacob — Mon, 21 Sep 2026 04:29:14 +0000

Previously, people used freelancing platforms to bid on projects and work for clients.

But things are changing.

These platforms are flooded with freelancers.

Many of the people who previously hired freelancers to build prototypes are now vibe coding it.

So, what's next for freelancers?

A lot of them have multiple product ideas, but they are not working on it.

Some are already busy freelancing and making money.

Some are scared of company registrations, payments, taxes, compliance, etc.

And some start building, don't make money quickly, and lose interest.

As freelancing changes, I think we are going to see more freelancers choosing the founder path and building their own products.

But building the product is only one part of the journey.

Once they start thinking about monetization, they run into another set of problems: business setup, payments, subscriptions, taxes, compliance, and so on.

Earlier, Stripe was the default option for almost every product looking to monetize. But it generally requires a registered business, and access can also vary depending on the country. Like India and a few others, Stripe is not directly available.

AI has actually removed the friction of building a product, but monetizing it is still harder.

If you are starting your first SaaS or AI product today, Kelviq helps you monetize without having to deal with much of the friction around business setup, payments, taxes, and compliance.

Kelviq act as a monetization layer for your product, from your vibe coded app to the revenue stage.

AI made it easier to become a builder.

And Kelviq make it easier for those builders to become founders.

Merchant of Record for AI

Geo Jacob — Thu, 09 Jul 2026 04:37:25 +0000

With the rise of AI, more people are vibe coding, launching products, and getting paid.

They don't need to master every part of software development anymore, they use Claude Fable 5, Codex, and other AI tools to build faster.

Payments are just another integration.

Most AI products are built for a global audience, not just a local market.

When you sell a product internationally, taxes, compliance requirements, and risks vary across countries, and these regulations change over time.

This is where the Merchant of Record (MoR) model comes in.

What is Merchant of Record (MoR) model?

The MoR is the entity legally responsible for processing transactions and delivering goods or services to end customers.
It manages payment acceptance, compliance, taxes, and chargebacks/refunds, allowing sellers to focus on scaling their business instead of building regulatory and financial infrastructure.

How does it work?

The seller sells products/services to the MoR.
The MoR processes customer payments, ensuring taxes, compliance, and local regulations are handled.
End customers purchase from the MoR.
The MoR pays out the net amount to the seller after deducting taxes, fees, and associated costs.

Why modern AI products need a modern MoR?
AI products are moving beyond fixed monthly subscriptions. They use prepaid credits or pay-as-you-go (PAYG) pricing based on usage.

Modern MoR platforms, like Kelviq, combine billing, usage metering, payments, taxes, compliance, payouts, and support for prepaid credits and PAYG pricing in a single platform.

Instead of building billing infrastructure and navigating global regulations, AI companies can report customer usage, while the MoR handles the rest.

As AI makes it easier to build products, MoR will become the essential infrastructure for selling globally.

Free Trial vs Free Credits

Geo Jacob — Wed, 08 Jul 2026 06:30:43 +0000

In the early days of SaaS, most products relied on time-limited free trials.

The idea was simple:

Give users unrestricted access for a limited time. If they experience the product's value, many would convert into paying customers.

But, there is another side to it.

When users don't add a payment method during the trial, the chances of churn increase significantly. Many enjoy the trial and simply disappear once it ends.

Still, for many products, offering a free trial without requiring a credit card still makes sense. It reduces friction and encourages more people to experience the product.

Now, with the rise of AI products, the model is evolving again.

Instead of offering free trials, many AI products provide free credits. Users can explore the product based on usage rather than time.

So, does a free trial still matter?

Without a free trial, users often create an account because it's free. But they never actually use the product. Their free credits remain untouched. They never experience the value you're trying to deliver.

A free trial creates urgency.

It encourages users to actively explore the product and discover its value.
The expiry date also gives builders a natural opportunity to engage with users, gather feedback, understand their needs, and ultimately convert them into paying customers.

So the best approach depends on your product.

1. Traditional SaaS may benefit from time-based free trials.
2. AI products often fit usage-based credits.
3. Some products can combine both for better activation and conversion.

At Kelviq, we support both models, so you can choose the one that fits your business or combine them to maximize conversions.

Which pricing converts better: tax-inclusive or tax-exclusive?

Geo Jacob — Mon, 06 Jul 2026 03:39:49 +0000

Some products are built for B2C, some for B2B, and some serve both.

For B2C, tax-inclusive pricing generally leads to higher conversions.

Consumers care about the total price they pay. Seeing a higher price at checkout because tax was added can reduce trust. It can also lead to more abandoned carts.

For B2B, tax-exclusive pricing is often preferred.

Businesses can often recover VAT/GST as input tax. The tax is mainly an accounting item, not part of the actual cost. They also expect the base price and tax to be shown separately.

What if you sell to both B2C and B2B customers?

How do you maximize conversions without maintaining separate pricing for each audience?

The same question led us to add Tax Behavior Settings in Kelviq

Merchants can configure how prices are displayed and calculated for B2C and B2B customers, making it easier to optimize the buying experience while staying compliant with tax rules.

We learned there is no single right way to display taxes.

B2C merchants often optimize for a frictionless buying experience.

B2B merchants often optimize for accounting clarity.

After all, conversions should be the ultimate goal for every pricing strategy.

The Psychology of AI Credits and Rollovers

Geo Jacob — Fri, 03 Jul 2026 07:03:54 +0000

Many AI companies have adopted a credit-based pricing model.

Customers purchase credits, and each AI request consumes credits based on usage.

It's a simple model, but the real challenge lies in how those credits expire.

For example, imagine a company that:

Gives users a small number of free credits every day. (5 credits/day)
Resets purchased credits on a monthly billing cycle. (100 credits/month)

Why offer daily free credits?

It's not just generosity, it's psychology.

If users exhaust all their credits, they may start exploring other AI tools, increasing the risk of churn.

Daily free credits encourage users to return regularly, explore new ideas, and continue using the platform.

Once they are engaged in a workflow, they are also more likely to purchase additional credits if needed.

But there is another side to the story.

Many users feel frustrated when their purchased credits expire before they can use them.

It creates a sense of FOMO, and sometimes they end up spending credits on tasks that provide little or no value, just to avoid "wasting" them.

Is that really a good user experience?

This is where credit rollover becomes valuable.

Instead of letting unused credits disappear, businesses can allow a configurable portion of them to roll over into the next billing cycle.

This gives customers more flexibility while still allowing companies to maintain a sustainable business model.

This is exactly how we designed Kelviq.

With Kelviq, AI companies can:

Configure how many unused credits can roll over to the next cycle.
Define rollover policies that fit their pricing strategy.
Notify customers before they are about to run out of credits using configurable usage thresholds.

At the end of the day, customer retention improves when people feel they are getting the maximum value from every credit they purchase, not when they are racing against an expiration date.

Does Kelviq handle reverse-charge VAT for B2B sales?

Geo Jacob — Thu, 02 Jul 2026 05:47:10 +0000

That was one of the first questions we received when we launched Kelviq.

We weren't surprised.

In fact, we had already heard the same question months before launch while working closely with our design partners.

Here's why.

Sales tax can be configured in two ways:

Exclusive pricing
Product price: $10
At checkout:
- Base price: $10.00
- Tax (18%): $1.80
- Total: $11.80
Inclusive pricing
Product price: $10
At checkout:
- Base price: $8.41
- Tax (19%): $1.59
- Total: $10.00

Different countries have different tax rules. A merchant selling in India and Europe needs to collect and report taxes differently for each region.

But the real complexity begins with B2B sales.

In many countries, especially across Europe, if a business customer provides a valid VAT or tax ID, the sale may qualify for the reverse-charge mechanism, meaning the supplier generally does not charge VAT on the invoice, and the customer accounts for it.

With exclusive pricing, this is straightforward, you simply don't add tax.

With inclusive pricing, it's much more interesting.

Should the tax amount be deducted from the displayed price, reducing the amount charged? Or should the merchant keep the final price unchanged?

Different businesses expect different behaviors.

That's why gives merchants the flexibility to configure how inclusive pricing behaves when reverse-charge VAT applies.

These are the kinds of edge cases that rarely make it into product announcements, but they matter every single day for businesses selling globally.

Does Kelviq handle reverse-charge VAT for B2B sales?

Geo Jacob — Thu, 02 Jul 2026 05:30:15 +0000

That was one of the first questions we received when we launched Kelviq.

We weren't surprised.

In fact, we had already heard the same question months before launch while working closely with our design partners.

Here's why.

Sales tax can be configured in two ways:

Exclusive pricing
Product price: $10
At checkout:
- Base price: $10.00
- Tax (18%): $1.80
- Total: $11.80
Inclusive pricing
Product price: $10
At checkout:
- Base price: $8.41
- Tax (19%): $1.59
- Total: $10.00

Different countries have different tax rules. A merchant selling in India and Europe needs to collect and report taxes differently for each region.

But the real complexity begins with B2B sales.

With exclusive pricing, this is straightforward, you simply don't add tax.

With inclusive pricing, it's much more interesting.

Should the tax amount be deducted from the displayed price, reducing the amount charged? Or should the merchant keep the final price unchanged?

Different businesses expect different behaviors.

That's why gives merchants the flexibility to configure how inclusive pricing behaves when reverse-charge VAT applies.

These are the kinds of edge cases that rarely make it into product announcements, but they matter every single day for businesses selling globally.

Use Case: We automated our business vetting with OpenClaw

Geo Jacob — Fri, 20 Mar 2026 07:09:43 +0000

I've always wanted to build something with openClaw.

But it had to be genuinely useful for our business, not just another toy app for managing tasks.

Today, our Kelviq vetting system runs entirely on OpenClaw, handling initial screening and speeding up customer onboarding.

The Problem:

After launch, we saw a surge in business verification requests. Business verification is mandatory for us as an MoR platform. Every time a profile was submitted, we had to review the business in detail before approving it. This consumed a lot of time, caused constant context switching, and left us drained, especially when the outcome was a rejection.

So, we decided to automate it.

The Solution:

A profile is submitted, triggering a message to Discord that tags our Kelviq bot.
Our OpenClaw server picks up the request.
The AI agent analyzes the website, compares it against our policies, and makes a decision.

The bot instantly outputs an approval or rejection, a detailed reasoning statement, the appropriate category, and a confidence score.

The Stack:

– OpenClaw image deployed on a DigitalOcean
– OpenRouter subscription
– Discord for messaging

Here is the video + story behind building this over a weekend.

https://x.com/geojacobm6/status/2034127028329583111

Hope this is helpful! And happy to share more details if anyone's building something similar.

I quit my job to build my own startup

Geo Jacob — Wed, 27 Aug 2025 04:41:53 +0000

Three months ago, I left my job at PaloAlto Networks and started completely focusing on my own startup. It was not an easy decision for me. The job was very peaceful and flexible. But, building my own startup was always my dream and I can't hold it any more.

Around 3 years back, my friend Sachin Neravath shared an idea of implementing price localization for digital products. We started it as a side project. We developed and released the product.

Sachin quit his job and started concentrating completely on the product, that really worked. Within a short span of time we got good traction. Multiple payment providers reached out to us for integration and everything went well, we got many popular creators and some of the fastest growing SaaS companies as customers.

During this time, we talked to many customers and also helped them with their pricing setup. That's how we came to know how difficult it is for them to implement stripe, especially usage based billing, managing feature access, handling webhooks, and customers.

Other requirements were that PMs want to do pricing changes quickly, but they are always blocked on engineering which takes sprints for a simple change.

Last week ChatGPT launched a new pricing tier only for India. Imagine, how much engineering effort would have gone into this? What if they can get a new pricing plan up and running without code change in under 5 minutes?

We also came to know that there is no simple tool helps you do pricing experiments easily.

As AI is booming and most of the companies are moving their pricing models from their legacy fixed pricing models to usage based / outcome based pricing, we found that there is a need for this product. And we finally decided to go all in on this. Another co-founder (Alok Vats, who was design head at Branch) has also quit his full time job and joined us. Now we are completely focusing on our startup.

Last 3 months was very difficult for me and during this time, i was:
— working like 2 full time job at once (easily 16 hours a day)
— 5x stressed than before (feels as same as when i started my career in 2012)
— withdrawing zero salary (first time in last 14 years)
— no weekdays or weekends, everything is same. Sometimes I am exhausted like anything.
— on top of that, one day a production issue killed me, it actually taught me the real difference between as an employee and a founder.

But now i'm in a better position, the development is done, feedback from beta customers is in.

The wait is getting over, ParityDeals is going live tomorrow...

Feeling a little nervous and excited at the same time.

If you have any questions or would like to know more about the product or my personal journey, feel free to connect with me on twitter, as I will be inscribing my thoughts there very frequently.

Could age verification tech be the future of car safety?

Geo Jacob — Wed, 06 Aug 2025 08:57:45 +0000

I'm just thinking about the potential of implementing age verification technology in the automotive industry, where drivers would need to confirm their age through a selfie and government ID before starting a vehicle.

YouTube is currently adopting similar technology to identify teenagers in the U.S. and enforce additional safety measures.