A qualified pipeline, researched and drafted for you.
Agents find the companies that fit, research each one and write a first message worth answering. Nothing is sent until you approve it, and every reply is read and sorted before you open your inbox.
| Company | Profile | Fit |
|---|---|---|
| Nordvik Logistics | Logistics, 40 staff | 86 |
| Brightline Dental | Clinics, 3 sites | 74 |
| Kestrel Foods | Distribution, 65 staff | 69 |
The research agent finds companies that match your ideal customer.
Selling time goes to everything but selling.
Finding companies, researching them, copying details into the CRM, writing first messages, following up and sorting the replies: a salesperson's week fills with work that happens before a single real conversation.
The work it takes off your team
- 01Finding companies that match your ideal customerBy hand today
- 02Researching each prospect before writingBy hand today
- 03Updating the CRM after every touchBy hand today
- 04Writing first messages and follow-upsBy hand today
- 05Sorting replies, interest and opt-outsBy hand today
- 06Keeping do-not-contact lists currentBy hand today
A team of agents and workflows, each with one job.
Each has only the tools its job needs and a budget checked every time it runs. None of them decides what a person should.
- Prospect research agentFinds companies that match your ideal customer and researches each one.
- Qualification scoringScores every prospect on evidence, and says why.
- Outreach drafting agentWrites a first message per prospect, in your voice.
- Reply classification agentReads replies, flags interest and handles opt-outs at once.
- CRM
- Calendar
- Company registers
- Web research
- Do-not-contact lists
The calls that stay yours.
The agents do the work. These are the decisions they bring to a person, with the evidence beside each one.
- 01
Every first message
Each draft waits for you, with the research that shaped it.
- 02
Replies that need you
Interest, objections and anything unclear come to you. Opt-outs are honoured immediately.
Controls built into the work.
Not policies in a document: properties of how this department runs.
- 01
Sends go through a port that refuses
A message leaves only when its approval, its checks and its limits pass. Anything else is refused, and the refusal says why.
- 02
Do-not-contact, checked first
Opt-outs and do-not-contact registers are checked before every send, not once a month.
- 03
Research you can inspect
Every score says why, and every draft shows the research it used.
Measured on the record, not estimated.
- 01
Prospects researched
Per week, with their sources.
- 02
Drafts approved or rejected
And the reasons you gave.
- 03
Replies by kind
Interest, questions, not now, opt-out.
- 04
Time to follow-up
From a reply to the next message.
Every run is recorded with its time, its steps, its decisions and its cost, so these are read from the record, not estimated.
The questions operators ask first.
What exactly do you build?
Five sizes of the same thing. An automation takes one repetitive process off your team. An AI agent handles a defined business function with judgement. An AI system connects several agents and workflows. An AI department runs a whole function end to end, and an AI operating system puts every department under one orchestrator. All of them run on the same platform, with the same approvals and the same record.
Do we have to change our tools?
No. That is the point. We build against the CRM, accounting system, inboxes and spreadsheets you already run, through their own APIs. If something genuinely cannot be automated where it stands, we tell you before you pay for it.
What happens when an agent gets it wrong?
Anything that would reach a customer or leave your business starts behind a person’s approval, so a wrong draft stops there, not in someone’s inbox, unless you have chosen to let that kind of work run on its own. Every run is recorded step by step, so a wrong call is traceable the same day. Where a fact is missing, the work stops and names it instead of guessing.
Will the AI act on its own?
Only where you have allowed it, and only once its record shows it can. Every agent starts supervised; anything that leaves your business starts as a draft or a proposal a person approves. Running unattended is earned task by task, on your own records.
How much does it cost?
Builds start from €750 for a focused automation, €2,500 for an AI agent, €5,000 for an AI system and €10,000 for an AI department; enterprise programmes are priced per scope. Keeping a system monitored and improving starts from €250 a month. The real figure depends on scope, integrations, data, rules and support, so after a free assessment call you get a written scope and a fixed price before anything starts.
Other departments
Find the first thing worth automating.
Bring us one process your team loses time on. We'll map it, show you what can be automated and what a Dephrast system would look like, whether or not you build it with us.
Free, 30 minutes, and a reply from a person within one working day.