A Palo Alto fintech pioneer had already started building AI support in-house. By building side by side with Notch, they turned tribal, employer-specific knowledge into dependable agents, and proved the system could handle their complexities at scale.
At a glance: Palo Alto · earned wage access pioneer · millions of users · hundreds of support reps · 1,000+ payroll documents processed weekly
About EarnIn
EarnIn is a U.S.-based financial technology company, based in Palo Alto, that lets people access the wages they have already earned before payday. Through a mobile-first platform, EarnIn serves millions of users with earned wage access and financial wellness products, including Cash Out, Early Pay, and savings tools, all built to smooth cash flow and reduce financial stress. EarnIn operates in a highly regulated financial environment that demands secure, data-driven infrastructure that holds up at scale.
EarnIn's support organization matches that ambition. With hundreds of customer support reps and a strong internal engineering culture, the company had already started building AI into its support operation on its own. This is a team that knows its product deeply and takes real care with its customers. With a strong internal engineering culture and deep operational expertise, the opportunity was to move even faster while maintaining the high bar EarnIn had already established.
The Challenge
Earned wage access is deceptively complex under the hood. Rules can vary by employer and bank. Eligibility, pay schedules, direct deposit behavior, and the documents customers provide all introduce different scenarios, while much of the expertise required to resolve those scenarios is built through thousands of real customer interactions.
EarnIn had already begun bringing AI into its support operation, backed by a strong internal engineering team and deep operational knowledge. As that work expanded, the opportunity was to take on increasingly complex use cases: capturing more of the situational knowledge experienced reps use every day, translating it into dependable guidance, and applying it consistently across a support organization operating at significant scale.
That is where EarnIn and Notch began building together. Notch joined that effort as an extension of EarnIn's team, working alongside its developers, systems, and existing AI initiatives to structure operational knowledge, expand coverage of nuanced scenarios, and move sophisticated workflows into production faster.
The Solution: building together with Notch
EarnIn did not have to choose between its own development and an external platform. Its team continued building, while Notch worked alongside its existing developers, systems, and pipelines.
Together, the teams created a faster loop for turning real operational knowledge into production-ready AI:
- Analyze real interactions to understand how experienced team members handle different scenarios and identify opportunities to make that knowledge reusable.
- Capture new rules and exceptions as they emerge, continuously expanding what the agents can handle.
- Deploy that knowledge as structured guidance and workflows that can be applied consistently across customer interactions.
EarnIn's team also uses ADAM, the part of the Notch platform designed to accelerate agent development and improvement. Alongside building agents, the team uses it to map JSONs and data extracts and quickly create and connect internal and external API endpoints.
This allowed integration work, knowledge development, and agent development to move together rather than as separate workstreams. EarnIn's engineering team remained closely involved throughout, while Notch provided additional leverage to move from an idea or newly discovered operational pattern to a working agent faster.
The partnership also created benefits beyond the agents themselves. EarnIn already had a well-organized operation, but like most sophisticated support organizations, some of its most valuable knowledge was situational and lived with experienced people. Working side by side, the teams turned more of that expertise into explicit, reusable guidance that could support both AI agents and human teams.
The result was not simply another AI layer. It was a way for EarnIn to extend the work its team was already doing and scale more of its operational knowledge across the organization.
"We already had an amazing internal team building AI. Notch worked alongside us, gave us leverage, helped us codify more of our expertise, and allowed us to scale sophisticated workflows faster."
Proof at scale: real-time payroll document ingestion
One of the clearest examples is payroll document ingestion. Verifying earnings means reading whatever a customer sends, and customers send everything. Mobile photos, blurry PDFs, screenshots of a banking app. Notch ingests these in real time, extracts the employer, pay schedule, and direct deposit data, validates it against the account record, and makes an automated eligibility decision.
The pipeline runs in five steps: ingest, segment, classify, extract, act. It handles this variability at a sustained rate of over 1,000 payroll documents per week, in a domain where every employer and every bank has different rules, and an eligibility decision directly affects whether a customer can access money they're counting on.
The Result
EarnIn kept ownership of its AI strategy and development while increasing the pace at which the team could bring sophisticated workflows into production. By building on top of Notch alongside its own initiatives, EarnIn expanded what its agents could handle, improved the consistency of operational knowledge, and created more leverage for both its engineering and support teams.
The result is a support organization that can serve more customers faster, while allowing its people to spend more time on the work where their experience and judgment create the most value.
Why They Chose Notch
EarnIn chose Notch because it could add leverage to what the team was already building. Notch provided a foundation for developing, integrating, and improving agents while allowing EarnIn's team to stay closely involved in how those agents worked. Together, the teams captured more of the operational knowledge that experienced reps use every day, translated it into reusable guidance, and continuously expanded what the agents could handle.
That combination gave EarnIn the speed of a purpose-built AI platform without giving up the flexibility and ownership of its internal development. For a highly regulated banking and fintech environment, that meant being able to move quickly while maintaining control over how AI was built and deployed.
"We needed an in-app concierge experience customers could truly rely on when accessing their hard-earned wages. The challenge was turning complex SOPs and tribal knowledge, with different rules for every employer and bank, into clear and dependable support. Notch broke it all down quickly and built agents that handled each interaction with real care. That has allowed our team to serve more customers, faster, while focusing on higher-leverage work."
Florencia Resnik, Vice President, Care and Agentic AI Operations, EarnIn
Bottom Line
EarnIn was already building. Notch gave its team a way to build faster and extend AI into increasingly sophisticated parts of the operation. Working side by side, the teams turned employer-specific operational knowledge into structured, reusable guidance, deployed dependable agents, and scaled real-time payroll document processing to hundreds of documents per week.
Today, that collaboration is part of the day-to-day operation. EarnIn’s AI agents communicate directly with Notch AI agents and hand over cases to each other, and the teams deploy new versions together on an ongoing basis. Every week, they add new workflows, implement additional SOPs, and expand the range of scenarios the agents can handle.
The larger story is not build versus buy. It is how strong internal teams can use Notch as a platform and development partner to increase what they can build, shorten the path to production, and continuously scale AI across complex operations.
