Before · Manual
One person reads it
Find the deal by customer number. Work out what the email means. Create the follow-up task. Move the deal stage. Save the email on the record.
Slow, repetitive, and dependent on one person.
Case study · Agentic workflow
How Applicaa Streamlined Client Management with HubSpot–Xero Automation
Cloudify built an agent that reads every email from the providers this firm works with, does the matching work in HubSpot, and colour-marks each message so the team sees what still needs a person.
Trusted by 100+ creators & brands
How Applicaa Streamlined Client Management with HubSpot–Xero Automation
Cloudify built an agent that reads every email from the providers this firm works with, does the matching work in HubSpot, and colour-marks each message so the team sees what still needs a person.
System overview
AutomatedA closed loop for routine emails
Follow one email from the moment it lands to the moment the team can see it is done.
Shared inboxPension providerRe: Transfer of pension savingsNew
Pension providerTransfer completed
Pension providerQuestion about a policy
Ny Robot · AI agent
Waiting for new email
- ✓Read the email and attachment
- ✓Type: transfer rejected
- ✓Customer: one certain match
- ✓HubSpot updated
- ✓Marked green in Outlook
HubSpotPension transferDeal
No new activity yet
Routine emails are handled, logged and colour-marked before anyone opens the inbox.
What the agent does with every email
84% Of messages had the admin done without a person. Each dot is one message
What happened to each email
Every message ends in one of three outcomes, and the inbox shows which.
0messages handled in twelve weeks
0
Fully handled
Closed by the agent. Nothing left to do.
447 work done in HubSpot901 moved away automatically0
Pre-sorted for the team
Customer found and email saved on the deal; a person decides the next step.
0
Needs a person
The agent could not identify the customer, so it leaves the email to the team.
What our clients say after going live
Integrations and AI agents in daily use, in our clients’ own words.
“The AI agent has transformed how we manage our day-to-day operations.”
Customer & Administration Manager
Pension advice firm
“Add a short client quote here, ideally about a result they noticed.”
Client name
Role, Company
“Add a second client quote here. Keep it to two or three lines.”
Client name
Role, Company
Time saved
Give your team hours back every week
We estimated the time saved from two numbers we know: how long a person takes per message, and how many messages the agent did the admin for.
How the estimate works
Low end: count only the emails the agent finished completely on its own.
Emails countedClosed with nobody involved0
Time a person takes per emailMiddle of 4–5 min4.5 min
Time saved in total0 hours
Spread over the first12 weeks
Hours given back every week0hours a week
Not counted: The 403 emails left for a person, and the time a person still spends deciding on yellow ones.
A person and the agent, side by side
A personThe agent
- 0Messages handled in twelve weeks
- 0%With the admin done by the agent
- 0Actions in the connected systems
- 0Records linked to the wrong customer
Four in five messages now arrive with the work already done. The team reads a decision, not an inbox.
This is an estimate, not a timed measurement. Early in the rollout, the client counted about 11 hours saved at the 1,000-task mark.
The challenge
One shared inbox, dozens of emails, all by hand.
The firm helps private customers move their savings from one provider to another. Every provider replies into the same inbox, in its own wording, with no common format.
After · The agent
The team only handles judgement
Customer found. Task created in the right queue. Deal stage moved. Email saved on the record. Message colour-marked in Outlook.
The team only handles judgement.
Inbox rules could not solve this. The subject often says little, and the right action depends on reading the body and checking the deal in HubSpot.
Safe by design
When the agent isn’t sure, a person decides
A wrong update is worse than no update. Every message ends in one of three outcomes, and the inbox shows which.
How every message is decided
Four things it never does
Never guesses the customer
Anything short of one certain match goes to a person.
Never acts twice
Redelivered messages and open tasks are skipped.
Never answers for the advisor
When a provider asks a question, a person replies.
Never deletes anything
Messages are marked, never moved or removed.
Why it worked
Their process, not a template
Built on the firm’s own email types, queues, stages and rules.
Refined together
The colour model and stage rules were agreed before go-live.
- 292
Tested on real emails first
Real messages showed what to expect on day one.
- 403
Room to grow
New email types can be added. The unmatched messages are next.
If your process can be written as a rule, a conventional integration is cheaper and we will tell you so.
If someone has to read it first and decide what it means, that is a different job and it is the one this page is about.
System overview
AutomatedA closed loop for routine emails
Follow one email from the moment it lands to the moment the team can see it is done.
Shared inbox
Pension providerRe: Transfer of pension savingsNew
Pension providerTransfer completed
Pension providerQuestion about a policy
Ny Robot · AI agent
Waiting for new email
- ✓Read the email and attachment
- ✓Type: transfer rejected
- ✓Customer: one certain match
- ✓HubSpot updated
- ✓Marked green in Outlook
HubSpot
Pension transferDeal
No new activity yet
Routine emails are handled, logged and colour-marked before anyone opens the inbox.