Skip to content
Thor Signia

Case study · Funds management · Australia

The fund assistant that will not guess.

A specialist fund manager with a small support team answered every investor email by hand. We built an assistant that answers investors at any hour using only approved fund documents. Today it resolves 80 to 85% of enquiries and sends the rest straight to the team.

The problem
A small support team answered every investor email by hand while figures were hard to find on the site.
What we built
A support assistant that answers only from approved fund documents.
The result
It resolves 80 to 85% of enquiries; the rest go to the team with details ready.
Status
Live in production.
Book an AI Kickoff

The same problem shows up in

  • Fund managers
  • Wealth platforms
  • Super funds
  • Insurers
  • Lenders
  • Private banks

Small support team. Numbers that must be right. Your assistant should answer only from documents you approve.

Before and after.

■ Before4 STEPS

Investors wanted a unit price, a year of returns or a statement. The figures were on the site but hard to find, so they emailed.

  1. 1Search the site
  2. 2Compare factsheets by hand
  3. 3Email the team
  4. 4Wait for a reply

When the team was busy, investors waited.

■ After2 STEPS

Investors ask in plain words and get the answer straight away, at any hour.

  1. 1Ask in plain words
  2. 2Get the answer, chart and source

No longer done by hand

  • Compare factsheets by hand
  • Email the team
  • Wait for a reply

Requests that need a person go to the team, details ready.

80–85%
Resolved

Enquiries answered without the team.

24/7
Coverage

Investors get answers at any hour.

50
Real questions

Marked right or wrong by the client, then tuned.

0
Forecasts

It shares data and never recommends or predicts.

The problem

What was at stake.

The firm holds a financial services licence. A wrong return or a stray forecast can mislead an investor and put that licence at risk.

1

Sourced

Every figure links back to an approved fund document.

2

From documents, not memory

Answers come from factsheets and research, never the model's memory.

3

No advice, no forecasts

It explains strategy and shares data but never recommends.

4

Honest about limits

If a figure is not in the documents, it says so and passes it to the team.

Before the build

How this started.

Nothing came before it

No chatbot, no in-house build and no vendors to compare against.

We came with something working

A working proof of concept built for another firm.

The demo did the explaining

Ask in plain words, get an answer with a chart and its source.

They wanted to be early

The goal was to be among the first managers with AI for investors.

Discovery to production

How we worked.

01

A few days

Discovery

Found the one job worth doing first and learned the documents investors ask about.

02

A few weeks

Proof of concept

One assistant built only on factsheets and research notes.

03

Two rounds

They marked it

Fifty real questions, each marked right or wrong with the reason, then tuned and run again.

04

Ongoing

Production

Live as the firm's virtual assistant, handing the rest to the support team.

Start with one process.

Tell us which part of your work takes the most time. We'll show you what an AI co-worker could take off your team's plate.

Contact us

📞 +91 90080 97780✉ info@thorsignia.in📍 Bangalore, Karnataka, India

We'll use your details to reply to your enquiry. See our Privacy Policy.

What to expect

We start with one process and put something real in front of your team within weeks, so you can judge it on your own work.

Thor Signia
How we start