AI Assistant
One assistant for the whole company. Under your control.
The Plainsight AI Assistant is a secure, governed AI assistant for companies: one chat platform for your whole team, in an environment that is yours alone, grounded in your own documents through the knowledge engine we built ourselves.
Right now your people are already using AI, just scattered across personal accounts your IT team never sees. This replaces that with one platform you govern, priced per platform instead of per seat.
In plain terms: the AI chat your people already want, but it knows your company, and your IT team decides where it runs and what it may see. Your own cloud, your own servers, or our EU infrastructure if you would rather not run it.
What your team does with it
Not a demo reel. The four things people reach for every day, in the tools and language they already work in.
Company answers, with sources
Ask about the price list, the safety procedure, the contract clause. Answers come from your own documents through the knowledge engine underneath, cited, and only from documents that person may open.
Mail, calendar and documents
Connected to the Microsoft 365 your team already lives in: drafting and triaging mail, finding the meeting slot, working with the files where they are.
Data analysis and charts
Drop in a spreadsheet or a report and ask. Summaries, comparisons and charts without leaving the conversation.
Presentations and drafts
From a rough brief to a presentable deck or document. The routine writing stops eating the day, and people review instead of type.
One question, two sources
The difference between a chatbot and an assistant that earns its place shows up in one ordinary question. This one gets answered from a document and from a system at the same time, and the answer says which is which.
Nobody had to know which system holds what. That is the part people feel on day one.
“A customer says the amount on their invoice is wrong. What do I do?”
The steps your own policy prescribes, in order, with the paragraph they come from. Not a guess at what usually happens, and not a colleague interrupted for the ninth time this month.
“Summarise the obligations in this NDA and flag anything unusual.”
Read against the template your company actually uses, so unusual means unusual for you. The clauses that differ come back named, with the wording quoted.
“Does this booking match the document behind it?”
A specialised agent checks the entry against the invoice or contract it came from, names what does not line up, and points at where it lands on the balance sheet. It works inside the rules you gave it, not whatever it decides is reasonable.
One assistant, or as many specialists as you need
The accounting example above is not a different product. It is the same assistant with an agent configured for one job: its own instructions, its own sources, its own limits. Everyone still gets the general assistant, and the specialists sit behind it for the work that has rules.
The general one, for everyone
A chat window, the model that fits that department, your own documents behind it. This is what most people use most of the time, and it needs no setup per person.
Specialists, where a job has rules
Marketing wants a campaign checked the way campaigns get approved here. Accounting wants bookings checked against the documents behind them. Each gets its own agent, with its own instructions, its own sources and its own limits.
Reached by asking, not by choosing
Nobody has to know which agents exist or which one to open. People ask the way they would ask a colleague, and the assistant hands it to the one built for that job.
It knows your company
A generic chatbot knows the internet. This assistant knows your price lists, your procedures, your project history, because the knowledge engine we built ourselves sits underneath every answer: cited, permission-aware retrieval on your own documents. It is part of the package, not a separately priced add-on. Each department gets its own knowledge base with its own rules, so sales cannot wander through HR's files.
Separately from all of that, you can connect the Plainsight Brain to it: the wider company memory holding your documents, your lessons, your guardrails and your brand. The Brain is its own thing, not something bundled into this assistant, and it connects to any tool that speaks MCP, so Claude, ChatGPT and the coding assistants read the same memory as ours.
THE ENGINE UNDERNEATH
For the person who has to sign it off
Most people never think about the engine. They ask a question and get an answer with a source. If your job is to check how that works, Nexora has its own page: how documents get read before they get indexed, how a citation is chosen, and why the engine returns nothing rather than leaking when two systems disagree about access.
See how the engine worksOne assistant, connected to every source
Most assistants see the mailbox and stop there. The useful answers live one system further: in the ERP, the CRM, the HR tool, and in the documents nobody can find. Your people ask in one place and never have to know which system holds what.
Runs where you decide
Sovereignty is a decision, not a feature toggle. Infrastructure, models and rules stay yours, whichever cloud you run, without one, or on our EU infrastructure if running it yourself is not the point.
Your infrastructure, or ours
Azure, Google Cloud, AWS, your own servers, or our own EU infrastructure if you would rather not run it yourself. Either way the environment is dedicated to you, never shared with another company.
Your models
Pick the model that fits each department and switch any time: Claude, OpenAI, or open-source models through one gateway. We are tied to none of them.
Your rules
Single sign-on through your own identity provider, isolation per department, audit on everything. GDPR compliant and EU AI Act ready.
Governed by design
The point of one platform is that someone is actually in charge of it. IT gets the controls and the audit trail; your people just get an assistant that works.
How a rollout goes
Measured in weeks, not quarters. The proven route starts small on real work and grows department by department.
Decide where it runs
Your own cloud, your own datacentre, or our EU infrastructure if you would rather not run it yourself. It connects to your identity provider either way. Days, not months.
Connect the first knowledge base
Nexora indexes the documents one department actually uses. Selective on purpose: index what people use, not everything you store.
Pilot on real work
A test group uses it on their actual tasks. Their questions and complaints tune the setup better than any workshop.
Scale team by team
Each new department gets its own space, knowledge and rules. Use cases surface as you go, and the platform grows around them.
See it, don't take our word for it
Screenshots, the full feature list, security detail and current pricing live on the product site. This page is the short version.
Visit aiassistant.plainsight.proFrequently asked questions
What can people actually do with it?
The everyday work: ask questions that get cited answers from company documents, draft and triage mail in Microsoft 365, analyse data and build charts, and turn briefs into presentations. One governed place to ask, instead of a different subscription per team.
Where does our data go?
Into an environment that is yours alone, and nowhere else. Usually that is your own tenant: Azure, Google Cloud, AWS, or your own servers. If you would rather not run it yourself, it can sit on our own EU infrastructure, still isolated to you and never shared with another company. Either way your data stays in your region, is never used to train models, and people sign in with your existing identity provider.
How does it know our documents?
Through the knowledge engine we built ourselves, which is part of the assistant and included in the platform price rather than billed as an add-on. Each department gets its own knowledge base, answers cite their source, and nobody sees a document their permissions would not already open.
Can we control who sees what?
Yes, and it is the default rather than a setting. Departments are isolated from each other with their own knowledge bases and rules, permissions are enforced per document, and an admin dashboard shows usage, costs, models and users.
Why not just use what is in our Microsoft licence?
We work with Microsoft rather than against it: the assistant plugs into the Microsoft 365 your team lives in and deploys to the environment you already govern. What we add is model-vendor neutrality (pick the model that fits each department, switch any time), knowledge bases with per-document permissions, and platform pricing instead of per-seat licences. We pick what fits, we are not tied to any vendor.
What does it cost?
A setup fee plus a flat monthly platform fee, with infrastructure billed at cost. No per-seat licences, so the maths does not punish you for rolling it out to everyone. The knowledge engine underneath is included in that platform fee, not billed separately. Current numbers live on the product site's pricing page.
How fast can a team start?
Deployment into your environment plus connecting the first knowledge base is measured in weeks, not quarters. The proven route: start with one or two departments on real work, then scale team by team as use cases surface.
Ready to replace scattered AI with one you govern?
Tell us how your teams use AI today, official or otherwise. We'll show you the assistant on real work, in an environment that is yours.
Ask for a demo