Software where people
and AI agents work together
From web and mobile to AI agents. We design, build, and run the software people need.
Live on day 12
What we build
From prototypes that test an idea to systems your team uses every day, built precisely and only as much as needed.
AI agents
Agents that read documents, query systems, draft work, and ask a person to confirm, placed inside your real workflows.
Software development
Web services, mobile apps, and internal systems, from design through operations.
AX/DX transformation
A roadmap that moves your organization's work and data toward AI and digital, and the execution to make it real.
Consulting
Advice on technology choices, architecture, and team structure from people who have actually built it.
Recent projects
Services we build and run ourselves.
In-house service
BITBOX CLOUD, file cloud storage
A file cloud where tens of gigabytes upload straight from the browser, files go only to named recipients, and you can see who downloaded what and when. From individuals to teams and businesses, on a flat monthly price regardless of member count.
In-house serviceFile cloudLarge file deliveryTeam collaboration
In-house service
FileRisk, file malware scanning API
A scanning service that takes any file over an API, returns a verdict with its reasons, and deletes the file as soon as the scan is done. Web uploads, file storage, email attachments, and business systems all connect with a single API call.
In-house serviceSecurity APIMalware scanningFile security
AI agents that work like employees
We build agents that take on a whole role in your organization. They receive work, move across your systems to handle it, and report back. People review and decide.
Onboarded like a hire
It starts with a job description. Define what the role does, which systems it touches, and who it reports to, and we build and onboard an agent for that seat.
People make the calls
Agents draft and process, but anything that spends money or leaves the company is approved by a person. The seat of responsibility never sits empty.
One person leads many agents
The organization we picture is not one with fewer people. It is one where a single person leads a team of agents. Repetition goes to agents, judgment stays with people.
Roles we start with
Quotes and proposals
Drafts from order history and price lists, sent after the owner approves.
Support triage
Sorts tickets by channel, escalates delays, and writes the weekly report.
Expense processing
Reads receipts, fills the ledger, and flags only what breaks policy.
First-pass hiring review
Screens applications against the job requirements and schedules interviews.
Contract and document review
Points out deviations from standard clauses and drafts review notes.
Inventory and purchasing
Watches stock thresholds, drafts purchase orders, and waits for approval.
AI Assistant · Coming soon
An assistant is not just for executives
We are preparing an AI assistant that knows your calendar, email, notes, and the tools you use every day. It works the way you work, and your data stays in your own accounts.
Ask about the AI AssistantCalendar and email
Sorts your inbox, drafts replies, and schedules requests against your calendar.
Memory and recall
Keeps meeting notes, documents, and conversations, and brings them back when you need them.
Recurring work
Runs the weekly report, the expense sheet, and the research you used to do by hand, and shows you only the result.
Your way
Learns your tone, priorities, and judgment, and acts the way you would. When unsure, it asks.
About AIGENT
We started by building software and grew into AI agents. To web, mobile, and business systems we have added AX/DX and technology consulting. We work with you from deciding what to build. The building is done by AI and by us.
We build only what gets used
If even one person needs it, we build it. If no one uses it, we remove it. What actually gets used comes before what looks good.
When a better wheel appears, we rebuild
If the right tool does not exist, we start with the wheel. We choose what measures better, not what feels familiar.
We do not take on risks we cannot control
We keep dependencies few and weigh risks in advance. We build so that licenses and vendors do not lock us in.
Notices
All noticesFrequently asked questions
See all questionsWhat first-time inquirers ask most often.
What does AIGENT do?
We build software. Web services, mobile apps, and business systems, from design through operation, and on top of them, AI agents. By AI agent we do not mean a chatbot; we mean software that takes on a role in your organization, such as writing quotes, triaging support tickets, or processing expenses.
We also help set direction without building. AX/DX transformation assesses which processes to automate first and produces a roadmap, and technology consulting advises on technology choices and team structure.
The four services and their deliverables are in the Services section, and the things we have built are in our Work.
How does a project run?
Usually in four stages.
- Listening (1–2 weeks): we see how you work today and where time leaks, on site. We look at your existing data and systems too. This stage ends with a proposal stating what we will build, how long it will take, and what it will cost.
- Building small: we get one core flow working first and run it on real data. For an agent, that means running it first on real cases in an environment kept separate from operations.
- Widening: the proven flow is extended to the remaining processes and teams, with approval screens, dashboards, and integrations.
- Handing over: operations handover, staff training, and a guide for adjusting rules. We can keep running it for you if you prefer.
We share progress, cost, and risk openly, and raise the hard conversations first.
How are cost and timeline decided?
When the first stage, listening, is done, you get a proposal stating what we will build, how long it will take, and what it will cost. We do not give numbers before that, because an estimate made without seeing how you work is hard to keep.
As a rough sense: an agent for a single task or a prototype takes a few weeks to two or three months; a system or app used by several teams takes three to six months. Cost is based on duration and team size and is billed by stage. You can stop after the first stage.
Budget range and preferred timeline on the contact form are optional. You do not need to have decided them in advance. Start a project
Where is our data stored, and who can see it?
The principle is that data stays in your accounts and systems. Agents work with access permissions to your existing systems, such as the ERP, email, or help desk, and copy no data to our side. Any servers or accounts needed are created in your name, and our access is withdrawn when the project ends.
Where AI models are used, we document at the design stage which data goes to which model, and choose between commercial models under terms that exclude training on your data and models running inside your own infrastructure. For data containing personal information, masking and minimization rules are agreed first.
What an agent reads and produces is logged, and your staff can review it at any time. If you have security policies or audit requirements, we review them together in the first stage.
Let us talk about what to build
An unpolished idea is fine. Tell us about it and we will help shape the direction together.