We built a team of AI agents that runs a lender’s back office, without a single file leaving the building.
B:Side Capital, an SBA 504 and CDFI lender, came to us with hundreds of process documents and one hard requirement: automate the repetitive work, but never give up control of the data or the decisions. We built MARCUS to do exactly that.
Private by design. Auditable by default. Built from their own process. Published with permission.
- Client
- B:Side Capital
- Sector
- SBA 504 / CDFI lender
- Footprint
- 7 departments
- The team
- 14 AI agents
- Runs
- In-house, on-prem
- Type
- SBA 504 · CDFI
- Touches
- Borrower financials
- Stakes
- Regulated · auditable
B:Side Capital is a mission-driven lender, an SBA 504 and CDFI institution whose work touches sensitive borrower financials at every step: intake, eligibility, underwriting support, funding, portfolio monitoring, and the high-stakes work of servicing distressed loans. It’s a business where a single mishandled document isn’t an inconvenience; it’s a compliance event.
That’s the kind of environment most AI tools quietly avoid. It’s the kind we build for.
Lending runs on preparation. That’s where the days disappear.
Before anyone can make a decision, someone has to gather the documents, pull the reports, run the checks, and draft the paperwork. The same steps, over and over, across seven departments. That preparation is where the bottlenecks form.
The obvious fix, feed it all to a cloud AI, was a non-starter. Borrower data can’t leave a controlled environment. Eligibility, credit, and pricing can’t be decided by a black box. And every action a regulator might ask about has to be provable, after the fact, down to the source.
The brief, in one line
Take the prep off our people’s plate, without ever taking them out of control.
Meet MARCUS.
MARCUS is not an app B:Side’s team had to learn. It’s a colleague that lives inside the tools they already use: Slack, their lending systems, the browser. It does the gathering, checking, and drafting, then hands finished, organized work to a person to approve.
Built entirely from B:Side’s own process documentation, every step MARCUS takes traces back to how the institution already works. Nothing was invented.
Four surfaces the team already knows
A chat front door
Ask a question, get findings back. The way the team already talks to each other.
In SlackAn approval queue
A simple list where a person says yes, sends it back, or escalates.
Human sign-offA browser assistant
Read-only. Answers questions about the screen in front of you, changes nothing.
On-screen, view-onlyThe systems of record
Once approved, work lands where it already belongs: their lending platform and tools.
Existing systems- AI agents
- 14
- one for each step of the lending lifecycle
- departments
- 7
- from intake to portfolio to distressed-asset servicing
- source documents
- ~840
- every action traced to a real B:Side process
We didn’t bring a template. We read everything.
Before we wrote a line of code, we reviewed roughly 840 files across every division of the business. From that, we mapped fourteen distinct agents, each one doing a specific, real job, each one citing the exact operations document it came from.
Every step in the blueprint cites the operations document it came from. That’s the difference between an AI demo and an AI system.
How it was built
We built it the way you’d actually want a system this consequential built: in order, one capability at a time, each piece proven on real files before the next one shipped.
Highest exposure, built last
The most delicate work, payment relief and loan resolution, was deliberately built last, once trust in the system was already established.
The whole system runs in-house. On purpose.
Most AI vendors ask you to trust their cloud. We did the opposite. MARCUS runs on a single secured machine in B:Side’s own server closet. The models that read borrower documents run right there, in the building.
Local by default
The AI lives on B:Side’s own hardware, not someone else’s cloud. In normal operation, nothing about a file is sent to an outside service.
PII stripped before the model ever sees it
Microsoft Presidio detects and removes names, SSNs, and account numbers first. The model sees the work, not the identity.
Encrypted and tamper-evident
Everything stored is fully encrypted, and every action writes to an append-only log secured as a tamper-evident chain. Compliance can prove nothing was altered.
Borrower document
Local model
Encrypted store & audit chain
This is what makes MARCUS usable in a regulated lending environment at all, and it’s the part most teams can’t build.
MARCUS prepares the work. People decide.
Nothing sends, files, posts, or pays until a person approves it. MARCUS never decides eligibility, credit, or price. Those numbers come from systems, never from memory. Every request arrives the same way.
It shows its work
Here’s what I did, here’s what I’m asking for, here’s the source I relied on.
A person chooses
Approve it, send it back with comments, or escalate it. While a request waits, nothing moves.
It escalates, never proceeds
If it waits too long, it escalates to a person automatically. It never proceeds on its own.
Numbers come from systems
Eligibility, credit, and price are looked up, never recalled from memory.
Every step is logged
Attributable and auditable, down to the source document.
It’s the design, not a limit
Humans in control isn’t a constraint we worked around. It’s the point.
B:Side’s people get their day back for the work only people can do.
With the preparation handled, the team is free for the relationships, the customer service, and the judgment calls that actually move a deal. The repetitive prep that used to create bottlenecks now arrives finished, organized, and named the way the team already does it, ready for a human to review.
The result is an institution that moves faster without giving up an ounce of control, compliance, or trust.
If you can document how your business works, we can build the machine that runs it.
MARCUS is what Main & Machine builds when the stakes are real: private, auditable, built from your own processes, and designed so your people stay in control the whole way through. If that’s the kind of system your business needs, let’s talk.
More client stories are clearing review as each client signs off on the numbers.