The situation you are probably in
Some messages should not send themselves, and still eat the day. Confirmations, updates, answers to routine asks: each takes four minutes of looking up the record and typing the same shape again, and by late afternoon message thirty is curt in a way message three was not. Fully automated sending is wrong for these; fully manual is what you have.
What we do about it
The agent drafts in bulk from the live records, so each message carries the customer's actual details, order and history rather than mail-merge fields. The drafts queue for a person, who reviews, edits and sends, keeping judgement and relationships where they belong. Your team's edits are the feedback that sharpens the drafting. The four minutes becomes twenty seconds, and the thirtieth message is as good as the first.
Typical engagement. Two to four weeks over records that already exist, then a monthly line to add message shapes as the team finds them.
Where this already runs
Running inside a catering business: outgoing customer messages are composed in bulk from the live records of customers, events and orders, and queue for the team to review and send. The records themselves came from thirty years of paperwork we had already turned into a database, which is why every draft can quote the customer's actual history.
Most builds of this shape start with the two-week assessment: we map the process as it runs today, cost it, and write the scope. The fee is credited in full against the build.
Start with the two-week assessmentWhat you receive.
Concrete things, not outcomes on a slide. This list is the scope of the engagement.
- 1
Messages drafted in bulk from your live records, each personal to its thread
- 2
A review queue where a person edits and sends: nothing sends itself
- 3
Your tone and message shapes written down and applied consistently
- 4
Facts in every draft pulled from the record, never from the model's memory
- 5
Every draft, edit and send in one log
- 6
The message shapes editable by your team as the business changes
A good fit when
- The team sends many messages that are similar in shape but personal in detail
- The details live in a system the agent can read
- You want a person on the send button, and the drafting off their plate
The right starting point when
The routine messages could safely send themselves. Follow-up automation sends rule-based messages unattended; drafting is for the ones that deserve a human eye.
The messages are replies to inbound email. The email agent reads, files and answers the inbox under written rules, drafting where you set the line.
Customers want answers now, not a message later. The chatbot answers from your live records around the clock, graded on a test set before launch.
Not sure which of these is you? Describe the process and we will point you at the right one, on this page or another.
Price it before you commission it
Put the hours the task takes today, the salary of the person doing it and any quote you hold through the payback calculator. It shows the yearly saving, the payback period and the arithmetic behind both. Free, and nothing is stored.
Run the payback numbersThings you can check.
Figures from our own systems that this service draws on. Each one names its source.
- 719
- documents from thirty years of trading, searchable in weeks
- 120+
- tables of business data you could export tomorrow
- 380+
- working screens and system connections in daily use
Every figure names its source. How we count. The investing system runs on a broker paper account, not real money.
Make the next AI project one the business can measure.
Thirty minutes with the founder, no slides. You will know what the right solution looks like, what it would take to build, what it should return, and which part to start with.
Replies come from a named person in Dubai within one working day.