An agency's expertise, turned into data infrastructure

Ponti Digital is a B2B marketing and sales agency and an RD Station Diamond partner. Its expertise lived in manual processes, with data scattered across dozens of sources and across many of the agency's own clients. In just over a month, much of it assembled by AI agents on top of Nekt's MCP, Ponti turned that expertise into infrastructure most enterprises take years to build.

What Ponti built on Nekt

• 26 connectors bringing in data from dozens of sources, from Google Ads, Meta and RD Station (Marketing, CRM and Conversations) to GA4, Search Console, Hotmart, CV CRM, Monday and Postgres.
• Offline conversions. Sales from RD Station CRM and Hotmart flow back to Google Ads and Meta, so the media learns from who actually bought, not just who clicked or became a lead.
• Everything isolated per client, each agency client with its own rules and its own governed space.
• Data that powers the clients' own apps, such as Voz do Hóspede, which turns Google reviews into a product experience delivered through Supabase.
• Built the AI-native way, much of it assembled by AI agents reading governed data over Nekt's MCP, with tools like Claude and Fireflies wired straight into the stack.

The systems behind it

Twenty-six connectors feed the layer, unified and modeled instead of left as raw exports. A representative slice:

Why it matters for an agency

For a services company, this changes the math: what you solve for one client becomes infrastructure to serve the next, scaling on the knowledge that already lives inside the company. It is the same principle behind context engineering for AI agents and a governed MCP server for data: the meaning travels with the data, so agents answer instead of guess. Learn more about Ponti Digital.