Discovery + POC in 4 to 6 weeks.
We map a critical process, build a working pilot, and show the production plan with pricing. No lock-in.
Marfin Applied
AI engineers inside your operation, building what the Big Four only promise
Marfin Applied puts a technical squad inside your company to build, run and hand over AI agents that live in production. Measured by impact on your P&L, not by billable hours.
Book a discovery call (30 minutes)
We have run AI products in production since 2023.
Problem
Most companies your size already tried generative AI in 2024 and 2025.
ChatGPT enterprise, some AI agency, maybe an internal pilot. Almost nobody got an agent into production that moves the number. The barrier is not technology: it is wiring the model into your ERP, your workflow, your governance.
It takes someone writing the code that makes it part of the operation.
01
A POC that never ships. It looked good in the deck and went back in the drawer.
02
Agencies deliver slides, not operations. Contract ends, project ends.
03
Hiring an in-house AI engineer takes 6 months, costs double the salary in payroll charges, and the best candidate goes to a global startup.
Solution
Marfin Applied is the team that builds with you, runs it with you, and teaches your team to run it alone. It is the model Palantir, OpenAI and Anthropic use inside the Fortune 500, adapted to the Brazilian reality.
Agent in production in 8 to 16 weeks.
Integration with your systems, continuous evals, LGPD governance, training for your team.
Embedded squad, monthly.
1 to 3 engineers inside your operation, a rolling roadmap of new use cases, continuous improvement of the agents already running.
Evals, fine-tuning and MLOps.
The technical layer that separates a toy agent from an agent that survives an audit.
Process
Every phase with deadline, scope and deliverable defined before we start.
01Weeks 1 to 2
Discovery
Scope document, POC plan and go or no-go criteria.
02Weeks 3 to 6
POC
Working agent in staging and a report with the production decision.
03Weeks 7 to 14
Implementation
Agent in production, dashboards and initial handover.
04Month 4 onward
Operation
Continuous operation via embedded squad and progressive handover.
Platform
Marfin Agents is the platform we built to run our own AI products.
Orchestration, guardrails, observability. Ready-made connectors for the stack your operation already runs on.
Every engagement starts with it pre-installed. First agent in weeks, not months.
Marfin Agents
01
Orchestration
02
Guardrails
03
Observability
04
Connectors
Connects with
Google WorkspaceWhatsAppSlackLinearNotionGitHubSupabaseand more
Proof
Rankz, Wordz, Postz, Statz, Mantis. Five AI products in production since 2023.
SEO, LinkedIn content, social media, metrics, industrial maintenance. Each one with a live platform, active users, an in-house team.
When you hire Marfin Applied, you hire the team that built this. And the platform that ran it.
01
22k
Active users
02
14
Agents in production
03
50+
Active integrations
Pricing
Three entry points: discovery, fixed-scope project, embedded squad. You leave the first call with the price range settled, before any proposal scoping.
01 · Discovery + POC
We build a working pilot in 4 to 6 weeks.
R$ 80 mil
02 · Fixed-scope project
Agent in production in 8 to 16 weeks.
R$ 300 mil/ per use case
We map a critical process, build a working pilot, and show the production plan with pricing. No lock-in.
- 4 to 6 weeks
- Process mapping
- Working POC in staging
- Production plan with pricing
Integration with your systems, continuous evals, LGPD governance, training for your team.
- 8 to 16 weeks
- Integration with legacy systems
- Continuous evals and guardrails
- In-house team training
03 · Embedded squad
1 to 3 engineers inside your operation.
Rolling roadmap of new use cases, continuous improvement of the agents already running, access to the Marfin Agents platform and ongoing support. 3-month minimum contract. Starting at R$ 35 mil per month, per engineer.
FAQ
How is this different from a consultancy like Deloitte or EY?
Consultancies sell a diagnosis and a deck. We sell running code. We measure success by agents in production and impact on your business, not by billable hours or status reports.
Are you a software house?
No. A software house rents you devs by the hour, with no opinion on AI architecture. We have our own platform (Marfin Agents), we have run AI products for years, and this team has deep command of LLMs, evals and MLOps.
How long until I have an agent in production?
Between 8 and 16 weeks for the first use case, depending on integration complexity. Discovery + POC is ready in 4 to 6 weeks.
Who owns the code, us or you?
The agent code is yours. The Marfin Agents platform is licensed (or run in your own environment, if you prefer). You are never locked in with us.
What about LGPD?
Every engagement includes data flow analysis, consent modeling and audit documentation. We work with your legal team from Discovery onward.
How does it start?
You book 30 minutes with us. We learn the process, check whether it makes sense, and propose a Discovery. If it does not make sense, no friction.
Which sectors do you work in?
Today's priorities: manufacturing, agribusiness, retail, healthcare, mid-market finance, edtech and logistics. Outside that, case by case.
What if I already have an in-house team?
Even better. Our model includes capability transfer. We measure it every quarter. The goal is for your team to become autonomous, with us as the scaling partner.
Contact