Work / JSE-listed broker · KYC automation
Fintech Compliance Document AI

67% faster KYC.
And it passed audit.

A JSE-listed broker was reviewing 1,200 onboarding packets a week by hand. We built a document agent that did 78% of it for them — auditably.

0%
Faster review time
R0
Annual labour cost saved
0 hrs
/ week reclaimed per analyst
5w
Discovery → production
— Context

A 14-person compliance team buried in PDFs.

The client is a JSE-listed broker offering FX and equity products to South African retail and institutional clients. Like every FSCA-regulated firm, they have to run full KYC on every new account — FICA, source-of-funds, PEP screening, sanctions, the lot.

Their onboarding flow was working. The compliance team behind it was not. Analysts were averaging 17 minutes per packet, 35 packets a day, and the queue kept growing. New hires took 6 weeks to ramp. Two senior analysts had resigned in the previous quarter, citing — verbatim — "the work is killing us."

— The problem

The work was repetitive, not simple.

Two prior vendors had attempted automation. Both failed. The first sold a no-code OCR product that broke on anything that wasn't a perfect bank statement scan. The second pitched a custom build but quoted 7 months and R3.2M — the client passed.

"We don't want a tool that solves 90% of the easy stuff and leaves the 10% that matters. We want something that knows what it doesn't know." — Compliance Lead, kickoff call
— What we built

A pipeline, not a chatbot.

Four agents in a Temporal workflow. Each agent owns one thing and outputs structured data with citations. If any agent's confidence falls below threshold, the packet goes to human review — with the agent's notes attached.

01

Ingest

Textract + custom layout model. Handles scans, photos, multi-page PDFs.

02

Classify

What is this? ID, proof of address, bank statement, payslip, deed of sale.

03

Extract & verify

Structured fields. Cross-check against application. Run PEP / sanctions API.

04

Decide

Pass / queue for human / hard-reject. Every decision linked to its evidence.

The hardest part wasn't the agent. It was the eval suite. We built it from 600 historical packets the compliance team had already reviewed, weighted toward the edge cases that had previously slipped through. By week 3, every code change ran the suite. By week 5, the system was matching senior-analyst accuracy on every category except source-of-funds — which we intentionally left to humans, because the cost of a false negative there is regulator-level.

— Results

Numbers, six months after launch.

78%of packets auto-approved (target was 60%)
17min → 4minaverage analyst time on the remaining 22%
0regulator findings on audit (vs. 3 the prior year)
14 → 8compliance headcount; redeployed to higher-value reviews
"They built in five weeks what our last vendor quoted six months for. And it actually works in production — which after three failed AI projects, was the part we'd stopped believing in." — Head of Operations
Got a similar problem?

Tell us where the
time goes.

If there's a workflow eating >20 hours a week, we can probably build it down by a third within 6 weeks.

Book a discovery call ← More case studies