DEV Community: Geo Jacob

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.