Financial planning firm

A financial planning firm put Claude to work without exposing client data

The firm works under SEC rules and handles sensitive client information every day. They wanted the whole team using AI, on a setup that fit the AI policy their compliance attorney was drafting.

Industry: Financial planning and advisory
Engagement: FlexFlow, weekly sessions
Built with: Claude desktop app, custom skills, n8n

Try the scrubber on sample data

The firm's scrubber hides personal details before a spreadsheet goes anywhere near an AI model. The fields the AI actually needs stay readable.

Client	Email	Account no.	Risk profile	Target mix
Jordan Sample	jordan@example.com	4417-2209-8810	Moderate	60% stocks, 40% bonds
Casey Example	casey@example.com	5531-0047-1923	Conservative	35% stocks, 65% bonds

Showing the original sample records.

Made-up records for this page. The real tool runs on the firm's own computers and handles more than 2,000 files at once.

About 400 hrsof team time saved so far
About $20,000is what those hours are worth to the firm
9 skillsset up in the Claude desktop app
2,000+ filesscrubbed at once, on the firm's own computers

Rules first, then tools

Before building anything, we rated the firm's AI work green, yellow, or red by risk. Each workflow gets a task card that spells out what data goes in, what comes out, and where its limits are. The framework lines up with the draft AI policy from the firm's compliance attorney.

Nine skills, set up the way the firm works

We loaded 9 custom skills into the Claude desktop app, chose which local folders Claude can trust, tightened its security settings, and wrote custom system prompts so answers come back the way the team needs them.

Personal data stays on the firm's computers

The scrubber encrypts and hashes sensitive fields locally, so client details never reach an AI model in raw form. It matches the same client across files, so records still connect. The newest version finds sensitive fields on its own.

A second reviewer for financial plans

A QA tool now reviews financial plans automatically. We later moved it to a lower-cost model, and the firm confirmed the output quality held up.

What it added up to

AI usage runs inside the firm's current subscriptions and promotional credits.
A governance framework the firm can show its compliance counsel and extend to new workflows.
Client details are scrubbed on the firm's own computers before any AI model sees them.

Next on the list

An asset allocation skill is in testing, and a daily download automation is planned for November.

Client details are kept private. Figures come from the client's FlexFlow sessions.

Want help like this for your team?

Every FlexFlow engagement pairs you with an AI and Automation Strategist and an Architect. You own everything we build, and it runs month to month.

Book a discovery call