Skip to content
Blog23 articles · 4 topics

What we learn building custom software

Every article comes out of a project we shipped — with the number, the decision, and what did not work. No second-hand theory.

The latestChoosing and buying custom software

How your company gets recommended by ChatGPT and Google's AI answers

ChatGPT and Google's AI answers recommend the company that has the answer written on its own site and confirmed by third parties, in reviews, directories and lists. You can't pay your way into the answer, and an llms.txt file on its own changes nothing. On our site, appearances in Google's AI answers went from 262 to 1,482 in eight weeks and a manufacturer 900 km away reached us through ChatGPT, but contact through the site did not grow at the same pace.

Pedro CunhaPedro Cunha · CTO at Epicora · 19 min read
Read article
Where to start

Two paths, depending on what you want to do

I want to build a software product to sell

Turn an idea or your method into an app or platform: validate it, work out the cost and choose who builds it.

  1. 01When an app built on Lovable needs to leave Lovable, and when it doesn't15 min read
Topic 01

Choosing and buying custom software

When building is worth it, when to stay with off-the-shelf software, when to replace a legacy system and what decides the platform of a website. Written for buyers, not for developers.

6 articles
Open the topic page
Topic 02

Applied AI, responsibly

Where AI belongs in a serious process, where it does not, and how that boundary is enforced in practice.

9 articles

AI agent on WhatsApp Business: what you pay for, what is free and what changes between the official and an unofficial API

Choosing between the official WhatsApp API and an unofficial library such as Baileys is not only about price: on the official API, Meta's rules shape the service, with a 24-hour window, approved message templates, one integration per number and per-message billing; on an unofficial one those rules disappear and what remains is the risk of the number being banned, because the use breaks WhatsApp's terms. The official API is not just the expensive option, since every number gets 1,000 free replies a month, and the unofficial one is not free. On the WhatsApp customer service platform we run, we operate both and choose client by client.

18 min read

How much it costs to put AI to work inside a company system, and what makes the bill go up or down

When AI runs inside a company system, you pay per token, and a customer service conversation costs cents: on Balcão, our WhatsApp customer service platform, triage comes to about R$ 0.15 (roughly US$ 0.03) per conversation. What weighs most is the text the AI rereads on every reply, and prompt caching bills that part at 10% of the price or less; model size comes next, with up to a 100x gap between the largest and smallest model from the same company. The bill also changes when you measure the result: in the simulation of a sales agent, the model that cost four times more brought more leads to the call, and the math by result came out in its favor.

17 min read

Open the topic page
Topic 03

Apps and app stores

When a system needs an app, what changes for it to work offline, and the App Store and Google Play rules: account, commission and distribution.

5 articles
Open the topic page
Topic 04

How the system is designed

The design decisions the client feels in daily use: integrating with what already exists, keeping rules configurable, deciding every alert and protecting people who must not be identified.

3 articles
Pedro Cunha
Who writes here
Pedro Cunha
CTO at Epicora

Pedro Cunha leads engineering at Epicora, in Chapecó, Brazil. He writes about the technical decisions behind the systems the team puts into production — architecture, scope, estimation and applied AI.

Contact

Let's talk about your project

Tell us what you need to solve. We reply fast, with people who understand both technology and business.

Prefer to talk directly?

Pick the channel you prefer. We reply fast, during business hours.

From the first conversation to go-live: efficiency, security and innovation.