Sales agent
Prepares customer meetings, finds matching references and products, summarises conversations, drafts follow-ups. Reads your CRM, proposal history and product material — writes nothing without your approval.
4–6 weeks
Pillar 01
AI Agents
An agent is not a chat window. It knows your data, follows your rules, works inside your systems — and someone on your side owns what it is allowed to do.
Three levels
From assistant to agent that takes work off your hands
Not every company has to start at level 3. Most begin at level 1 or 2 — and that is exactly right.
Level 1
Personal support
Your team leads, the AI assists
- Preparing and summarising meetings
- Researching across approved documents
- Drafting proposals, emails and reports
- Supporting engineering and documentation
Level 2
Domain agents
Knows one area, works with your data
- Sales agent: CRM, references, proposal history
- Service agent: documentation, tickets, fault analysis
- Back-office agent: policies and forms
- Engineering agent: repositories and architecture
Level 3
Process agents
Takes over steps — with approvals
- Checking and routing incoming documents
- Pre-qualifying enquiries
- Sorting tickets and proposing solutions
- Checking data and flagging what needs attention
At every level the same rule applies: people decide. What an agent may do on its own is your call — not ours, and not the model’s.
Agent packages
Agents we have already built
These agents came out of real projects. The building blocks exist and we know where the traps are. What differs in your company are the data sources, the vocabulary and the approval rules — and that is what we work on with you.
Service agent
Answers questions about technical documentation, helps with fault analysis, pre-sorts tickets and suggests solutions. Particularly valuable where service knowledge sits with a few experienced people.
4–6 weeks
Knowledge agent
Makes company knowledge from SharePoint, file shares, email and your DMS findable — with a source for every answer and a permissions model that respects what you already have.
3–5 weeks
Proposal agent
Drafts proposals from templates, previous proposals and price lists. Sales reviews and approves. The time from conversation to a proposal ready to send drops from days to hours.
3–5 weeks
Management assistant
A daily briefing on numbers, appointments and open decisions. Pulls together from ERP, calendar and mailbox what belongs on the desk in the morning.
3–4 weeks
Custom agents
Engineering, procurement or process agents for workflows that exist only in your company. Not a package, but built on the same foundations — and therefore faster than starting from zero.
scope dependent
Approach
How an agent comes about
- 01
Sharpen the use case
What should the agent deliver, for whom, in which situation? And just as important: what must it never do?
- 02
Connect the data
We establish which sources are authoritative, how they can be reached and which permissions apply. Two or three good sources usually beat ten mediocre ones.
- 03
Prototype
A working agent on real data, anonymised where necessary. Your team tests it against actual cases, not invented ones.
- 04
Put it into production
Roles, approvals, logging, operations. From here it is no longer an experiment but a tool in daily use.
- 05
Hand it over
Your AI people learn to maintain the agent, take in feedback and make small adjustments themselves.
Which agent fits your company?
That is best settled against a concrete example from your business — in the workshop.