Find an internal answer
Help a colleague find the relevant policy, procedure or project detail, with a link to the source.
If the information is missing or disagrees, the question goes to its owner.
Custom AI agents
for your business.
A colleague asks a question.
The answer is spread
across five places.
An AI agent can look up information and use tools to help carry out a task. We build it around your team’s work. You choose what it can read, what it can do and when it needs to ask a person.
Getting ready for a meeting or answering a customer often starts with a search: the CRM, an old email, a shared folder, someone else’s notes.
01 / Where it helpsWhere could an AI agent
Where could an AI agent
help your team?
Start with one recurring task. We test it with the documents, questions and languages your team actually uses.
Get ready to help a customer
Bring together earlier conversations, product details and account history, then prepare a suggested reply.
Your team reviews sensitive replies and any promises to the customer.
Prepare research
Gather the agreed sources, organise the findings and help update a working memo.
Your team’s conclusions stay separate from the AI’s research.
These are examples of possible projects. We agree the tools, access and checks with you before building.
02 / How it could work“Can you help me
“Can you help me
get ready for this meeting?”
Here is how an internal assistant could prepare a meeting brief. It uses the information and tools you have chosen for that job.
- 01
Ask
A colleague requests a brief for a meeting.
- 02
Check
Check which records that colleague can access.
- 03
Find
Gather relevant account details and notes.
- 04
Prepare
Show the brief with sources and open questions.
- 05
Review
Ask for any required approval and save the agreed result.
When it cannot find the answer, it should tell you.
Missing documents, conflicting information and broken connections need a clear explanation. The agent stops or asks the responsible person. It cannot give itself more access to finish the job.
Reading an email, drafting a reply and sending it are separate permissions. We agree them before connecting live tools.
03 / Planning the first versionHow much should
How much should
the agent do for you?
An agent can choose different steps depending on the request. If the task always follows the same sequence, a simpler automation may be a better fit.
| Task | Who stays in control |
|---|---|
| Read information | Use the records available to that person and show the sources. |
| Prepare a draft | Label it as a draft, with the facts behind it. |
| Send a message or change a record | Show what will happen and ask for approval where needed. |
| Move money or grant access | Keep outside the agent’s default job, with separate authorization and checks. |
04 / Projects and readingSee the thinking
See the thinking
in practice.
Our investment-memo project shows AI helping with research. The support project shows the account information a useful assistant needs.
AI / Investment research
Research that keeps pace with the deal.
New information updates the memo’s research sections while the analysts’ own conclusions stay intact.
See the investment-memo project Related work / Customer supportThe customer story reaches the right person.
A rule-based workflow brings account details and ownership into a support alert. It shows the kind of context an assistant can build on.
See the support project05 / How we work togetherStart with one task
Start with one task
and see how it helps.
We agree what the first version should do, how to check it and who will look after it. Then we work through it with your team.
- 01
Understand the job.
We choose who the agent helps, what information it needs and which actions it must ask about.
- 02
Try the questions your team asks.
We choose everyday and difficult examples, including missing information and the languages your team uses.
- 03
Check answers and actions.
We test whether the result is useful, whether sources support it and how the agent handles failed tools or misleading instructions.
- 04
Put your team in charge.
We document access, approval rules and support, and show how to correct, change or pause the agent.
06 / Access and upkeepUseful help,
Useful help,
with someone in charge.
Keep access tied to the person.
We agree which records each role can use and what happens when a document is removed or someone’s access changes.
Know where information goes.
We identify the AI providers, connected tools and storage used for documents, conversation history and activity records.
See what happened.
Keep a record of proposed actions, approvals and results, with a way to pause the agent or deal with a failed step.
Keep improving the useful parts.
We agree who reviews answers, corrections and costs. Changes to the AI, its instructions or sources are tested before use.
07 / Questions before you start
Questions about AI agents.
Do we need an agent or an automation?
If the steps are always the same, an automation may be enough. An agent can help when the next step depends on the question or the information it finds. We compare options around the job.
Can everyone see all our connected documents?
They should only see what their role allows. We agree and test access for each group, including what happens when permissions change.
Can it show where an answer came from?
We can build answers with source links and test whether those sources support the answer. We also check how it handles missing, conflicting or old information.
What will it ask us to approve?
We agree that with you. Reading, drafting, sending and changing records can each have different rules. A reviewer needs to see the proposed action before approving it.
How do you check that it stays within its job?
We try normal tasks, misleading documents, requests it should refuse and failed connections. Then we check what it actually did, including whether it respected access and approval rules.
Can it work in our languages?
We test German, French, Italian or English against the work you need it to do. The examples should reflect your team’s terminology and documents.
Where are our documents and conversations kept?
We explain which providers process them, where they are stored, who can access them and how long they are kept. We check the connected services as part of the same setup.
What does a first project cost?
First projects start from CHF 4,800 for one agreed task. We test the agent with examples from your team and confirm the scope, timing and review needed before building. The proposal sets out AI usage and any other running costs.
08 / Explore the serviceWhere could an agent
Where could an agent
help your team?
You might start with phone calls, investment research or sales preparation. These roles can overlap. A sales team may also need help handling calls.
Phone conversations
AI voice agents
Help callers with routine questions, arrange a callback or follow up on an agreed customer task. We test the languages and handover to your team.
The outcome: The caller knows what happens next, and your team has the details.
Explore voice agents Investment teamsAI agents for VC funds & family offices
Bring company research together, prepare memo updates and help get ready for portfolio reviews. Sources, dates and CHF/EUR figures stay easy to check.
The outcome: Analysts can begin with the findings and open questions in one place.
Explore investment agents Sales teamsAI agents for sales teams
Prepare account briefs, turn meeting notes into next steps and draft follow-ups in the customer’s language. Your salesperson checks the work before it goes out.
The outcome: More context for the conversation and less admin around it.
Explore sales agentsWe agree the tools, languages and actions for each project, including when a person takes over.
What would you like
your team to have help with?
Tell us about a task that keeps taking people away from their main work. We’ll explore what an agent could help with and what should stay with your team.
Book a first call