Making Sense has been named a Select partner in the Services Track of Anthropic’s Claude Partner Network.
The recognition rests on two projects: a Claude-powered assistant now running in thousands of customer accounts at a marketing platform, and a development workflow that cut a trading platform’s release cycles from months to about a week.
Anthropic’s Services Track, launched in June, scores implementation firms on certified practitioners, customers deployed in the past 12 months, and public customer stories.
To reach Select, a firm needs at least 10 certified practitioners and two production customers, according to Anthropic’s published requirements. Making Sense has 20 people certified through the Anthropic Partner Academy. Its team also holds certifications from other AI providers, including OpenAI.
The firm now appears in the Claude Partner Hub, a public directory where companies can compare partners by tier, team, deployments and references.
“Anthropic reviews each partner’s standing every quarter, based on its certified professionals and the customers it has taken live with Claude,” said Fernando Florez, chief revenue officer at Making Sense. “That gives clients a public, verifiable reference for what we’ve delivered, which makes choosing who to work with less of a leap of faith.”
The firm’s public case study is ECO IA, an assistant it built for Doppler, an email and marketing automation company that serves Latin America and Spain.
ECO IA runs on Claude Sonnet 4.5 inside Doppler’s platform, and pulls live account data, checks the health of each account and writes campaign drafts. Users edit and approve those drafts before anything goes out.
The assistant was ready within three months of kickoff. Doppler switches it on for every new account, and it now reaches more than 4,800 of them. Of the users who tried it, 95% kept coming back over several months, Making Sense said.
Running a model inside that many accounts gets expensive quickly. To keep the bill down, the engineers used prompt caching, which stores the parts of a request that rarely change, like system instructions, so Claude doesn’t have to process them again each time. When Anthropic launched the feature, it said caching could reduce costs by up to 90% on long prompts.
ECO IA’s cache hit rate holds at 97%, according to the firm, and each interaction costs about USD 0.066.
The team also built a dashboard that shows usage, spending, latency and errors as they happen, so Doppler can catch problems early.
At Viallion, an AI-powered trading automation platform, Making Sense rebuilt parts of the engineering workflow around Claude Code, Anthropic’s coding tool.
Projects that once took two to three months to develop, test and release now take about a week, the company said, and ideas get validated four times faster. Viallion’s engineers have kept using and adjusting the setup on their own.
“Claude has made building software dramatically faster. Knowing what a change will touch inside a company still takes people who understand that business: the system billing depends on, the data a regulator will ask about, the team that has to operate it the next morning,” said Cesar D’Onofrio, CEO and cofounder of Making Sense.
“We decide with our clients what is worth building, connect it to everything their operation runs on, keep it compliant and reliable, and answer for it once it’s live.”
In both projects, Making Sense engineers worked inside the client’s team and introduced practices like automated testing, so the in-house developers could keep building on Claude after the engagement ended.
Founded more than 20 years ago, the firm builds software mainly for mid-market and private equity-backed U.S. companies. Its work now centers on agentic AI and workflow automation, much of it in healthcare, fintech and logistics.
Featured image: courtesy of Making Sense
Disclosure: This article mentions a client of an Espacio portfolio company.
