Booking Q4 deliverystart with a free workflow plan Denver · Phoenix · Remote
Client story · B:Side Capital

AI agents that prepare a lender’s back-office work. People own the decisions.

B:Side Capital, an SBA 504 and CDFI lender led by our founder Christopher Myers, needed to reduce repetitive preparation without giving up control of data or decisions. We built MARCUS around its process documents and existing tools: local document processing, filtered model access, and human approval of consequential actions.

Private by design. Auditable by default. Built from their own process. Published with permission.

Case file
MARCUS · 2026
Client
B:Side Capital
Sector
SBA 504 / CDFI lender
Footprint
7 departments
The team
14 AI agents
Runs
Local + hybrid
Updated
Reported operating results

What changed for the team.

1,240hrs

Estimated staff preparation hours returned during June–August 2026, calculated from B:Side’s initial workflow studies. This is operating capacity, not measured payroll savings.

93%

Reported weekly use by week six, across a staff of 45 employees. The percentage is rounded; an exact active-user count is not published.

0

Borrower identifiers reported as sent to outside models during the measurement window. Filtering is required; detection is not guaranteed to be perfect.

100%

Of consequential actions approved by a person during the reported window, before sending, filing, posting, or paying.

Reporting period: June–August 2026. B:Side reports these results for the stated period. Preparation hours are estimates calculated from its initial workflow studies; operational activity is reported from its audit log. Returned capacity is not measured payroll savings. Annualized equivalents are not measured annual results.

Who we built it for
B:Side Capital
Client facts
B:Side
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.

Sensitive documents, established processes, and accountable decisions shaped the build from the start.

The problem

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 team needed a defined boundary around borrower documents and a reviewable path from source records to prepared work. Eligibility, credit, and pricing remained with the people responsible for them. The system had to show its sources and record its actions.

The brief, in one line

Take the prep off our people’s plate, without ever taking them out of control.

The solution

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.

B:Side’s process documentation defined the workflows and the sources each agent should use. That made the work reviewable against the institution’s own operating rules.

Four surfaces the team already knows

01

A chat front door

Ask a question, get findings back. The way the team already talks to each other.

In Slack
02

An approval queue

A simple list where a person says yes, sends it back, or escalates.

Human sign-off
03

A browser assistant

Read-only. Answers questions about the screen in front of you, changes nothing.

On-screen, view-only
04

The 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
Built from their work, not our assumptions

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.

Intake→ Production→ Funding→ Portfolio→ Priority assets→ Across the institution
DEPT 01Lender Services2 agents
AGENT 01Intake agentcited to source
AGENT 02Eligibility agentcited to source
DEPT 02Loan Production4 agents
AGENT 03Document-prep agentcited to source
AGENT 04Due-diligence agentcited to source
AGENT 05Credit-analysis agentcited to source
AGENT 06Underwriting-support agentcited to source
DEPT 03Funding2 agents
AGENT 07Closing & funding agentcited to source
AGENT 08Disbursement agentcited to source
DEPT 04Portfolio2 agents
AGENT 09Portfolio-monitoring agentcited to source
AGENT 10Covenant & reporting agentcited to source
DEPT 05Priority Assets2 agents · built last
AGENT 11Payment-relief agentcited to source
AGENT 12Loan-resolution agentcited to source
DEPT 06–07Sales & Administration2 agents · cross-cutting
AGENT 13Outreach & pipeline agentcited to source
AGENT 14Compliance & audit agentcited to source

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 local processing path

Local processing. Defined data boundaries.

MARCUS processes borrower documents on a secured machine in B:Side’s own server closet. A privacy filter scans prompts and documents before model processing. Selected tasks can use a commercial model on filtered text, as described in the results and architecture detail.

L1

Local by default

Borrower-document processing runs on B:Side’s hardware. External model use is a separate routing decision for selected tasks on filtered text; local deployment does not make every downstream service local.

L2

Identifiers filtered before model processing

Microsoft Presidio detects supported identifiers for removal before model processing. Detection is imperfect; seeded tests, routing limits, and review are part of the control.

L3

Encrypted and tamper-evident

Stored documents and work products are encrypted. Actions are recorded in an append-only, hash-chained log so changes to recorded entries can be checked.

B:Side server closetOn-prem

Borrower document

raw · sensitive · stays put
↓ Presidio detects and removes identifiers

Local model

processes filtered text
↓ encrypt + log to chain

Encrypted store & audit chain

append-only · tamper-evident
⛌  Local document-processing path shown. Selected external tasks use filtered text.

The diagram shows the local processing path. Read the security review for deployment choices, filter limitations, and the questions to ask about your own workflow.

One rule behind everything

MARCUS prepares the work. People decide.

Consequential sending, filing, posting, and paying require a person’s approval. MARCUS does not decide eligibility, credit, or price. Those numbers come from systems, never from memory. Every request arrives the same way.

STEP 01

It shows its work

Here’s what I did, here’s what I’m asking for, here’s the source I relied on.

STEP 02

A person chooses

Approve it, send it back with comments, or escalate it. While a request waits, nothing moves.

STEP 03

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.

What changed

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 the stakes are real

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. Builds in this class are published on the price list as The Full Back Office — from $95,000, four taken per year. If that’s the kind of system your business needs, let’s talk.

The guarantee: If a scoped workflow is not live in your operation within 90 days, we keep building at no charge until it is.

The credit: Your audit fee can be credited toward a sprint signed within 60 days, up to 25% of the sprint price.

See the price list →