// Decision comparison
RET Promptbook vs security consulting
Quick answer
The RET Promptbook (R$147) is a set of prompts for reviewing your SaaS yourself using the AI you already use (Cursor, Claude Code, Copilot): it forces the AI to walk login, billing, data, uploads and permissions and flag where it releases wrong access. Security consulting is dedicated people, with a schedule, scope and report, costing thousands to tens of thousands. One is guided DIY and immediate; the other is a bespoke service.
Rule of thumb: start with the Promptbook to fix the obvious before paying for specialist hours. It handles the most common mistakes of AI-built products at an impulse price. When a serious signal appears (a B2B sale demanding proof, suspicion of improper access, sensitive data at scale), that is when consulting (or RET’s Manual Pentest) pays off.
What you get from each
The difference is not "cheap vs expensive". It is who does the work and what depth you need now. The Promptbook arms you to find the obvious yourself; consulting brings someone to chase the non-obvious for you.
| Dimension | RET Promptbook | Security consulting |
|---|---|---|
| Price | R$147, one time | Thousands to tens of thousands |
| Who does it | You, guided by AI | A dedicated consultant |
| Timeline | Immediate, at your pace | Agreed schedule and scope |
| Depth | The obvious and common mistakes | The non-obvious, chained |
| Report for B2B | No (it is for you to act) | Yes, formal |
| Best for | First review, early | Serious signal, sale, compliance |
Why starting cheap is not dumb economy
Paying a consultant to find that you forgot to check object ownership (IDOR) or to verify the webhook signature is too expensive for a mistake a R$147 playbook catches. The Promptbook exists so you do not burn specialist hours on the basics. When the specialist comes in, let it be for what only they can find, not for what you could have fixed yourself.
- Promptbook: fixes the common and cheap before scaling.
- Risk Review (R$2,997): middle ground, a human read of 1 to 3 flows.
- Manual Pentest / consulting: depth and proof when the risk demands it.
When the Promptbook is NOT enough
If you already have a concrete incident signal, a B2B customer demanding a pentest report, or you handle sensitive data at scale (health, financial, minors’ data), the Promptbook is a start, not a finish. In those cases, jump to Risk Review (a human read) or the Manual Pentest (proof with evidence). The Promptbook makes that next step cheaper and faster, because you arrive with the obvious already fixed.
Want to know whether this happens in your system?
Manual pentest for web applications, APIs and apps, from R$9,500, with the Sprint run within 7 business days. We refund 50% if we find no flaw.
Frequently asked questions
Does the Promptbook replace consulting?
For the first review and common mistakes, yes, it handles a lot for R$147. For the non-obvious, the formal report a B2B sale needs, or sensitive data at scale, no: that is where Risk Review or the Manual Pentest come in. It shortens and cheapens that next step.
Do I need to know how to hack to use the Promptbook?
No. It is made for founders and devs who build with AI. You paste the prompts into the AI you already use and it walks the flows flagging risk. The work is following the playbook and acting on what shows up.
What is the next step after the Promptbook?
If a signal showed up in login, billing, data or a B2B sale, Risk Review (R$2,997) does a human read of 1 to 3 flows and tells you what to fix and what to test deeply. Then the Manual Pentest proves what breaks.
Does it work for apps built in Lovable, Bolt, v0 or Replit?
Yes. The Promptbook inspects real product flows, not the tool that generated the code. It works for any AI-built SaaS.