A different model for every department.

Put Finance on deep reasoning, Comms on something fast and cheap, and Support on a model running inside your own building. Eight providers, twenty-six models, eleven departments, changed from one screen and live on the next prompt.

AI assistantHarbour PointStagnant 24dDraft the follow-up
Reads183 dealsno upload
FlagsThree stagnantno asking
DraftsThe follow-upno blank page
OrdersYour dayno triage
It opens with what is wrong, not with a cursor.
It reads firstThree deals have not moved in twenty-four days, and it says so before you ask

The assistant opens with your pipeline beside it: active deals, and the ones going quiet, named, with how long. A blank box waiting for a prompt would know none of that.

Routing

Every department, its own model.

Most AI in business software gives every team the same fixed model from one vendor. Here each department gets the model that suits its work, and you can change it whenever you like.

NearSyncNearSync AIModel SettingsSearch, plan and askKAll hubs
Providers8Models26Departments routed10 of 11Runs on your own machinesOptional
  • SalesGPT-5.4Fast, and it talks to people all day
  • FinanceClaude Opus 4.8Reasoning, where being wrong costs
  • MarketingClaude Sonnet 4.6Writing
  • OperationsGPT-5.4Builds your workflows
  • EngineeringClaude Opus 4.8Long context
  • CommsGemini 3.5 FlashHigh volume, every message
  • SupportLlama, on your own machinesNothing leaves the building
  • PeopleGemini 3.5 FlashEveryday questions
  • WebGemini 3.5 FlashContent and tidy-ups
  • AnalyticsGPT-5.4Turns a sentence into a chart
  • NearSync AIMasterInherited by every HQ on Master

Change one and it applies to every session on the next prompt. A department left on Master follows whatever the base model is.

Change it once, and it applies on the next prompt.

Your models

Eight providers, or your own hardware.

OpenAI, Anthropic, Google, xAI, Mistral, Groq and DeepSeek, twenty-six models between them. Or run Llama on machines you own, so nothing leaves your building at all. Set one as the base model and every department uses it until you say otherwise.

The base model

What every department uses until you give it one of its own. Change it once and they all update together.

Voice has its own

Spoken conversations run on a realtime model chosen separately, so talking is fast without making everything else expensive.

Fully local, if you want

Point a department at Llama on your own hardware. Nothing about that department's work leaves your network.

Compare before you commit

Ask two models the same thing, side by side.

Watch them answer in parallel, see how long each took and what each cost in credits, and keep the one you preferred.

  • Two or three at once. Pick the models you are weighing up and send one prompt to all of them.
  • They answer side by side. Each answer appears in its own column as it is written, so you can compare as you go.
  • The same question, exactly. Every model gets an identical prompt, including the department context, so the comparison is fair.
  • How long each took. Real elapsed time per model, measured, not estimated.
  • What each one costs you. Shown in credits, so you can see whether the better answer is worth the difference.
  • Pick the winner. Choose the answer you preferred. The comparison is saved, so you can look back at it later.
Side by sideAnswering
GPT-5.41.2s
Claude Opus 4.82.6s
Gemini 3.5 Flash0.7s
The same question
PromptWord for word
Department contextIncluded
DifferenceOnly the model
Pick the winnerthe run is kept, so you can look back at why you chose it
Make it yours

Name your assistant and shape how it speaks.

Set it up once and it looks and sounds the same everywhere it appears: in chat, the inbox, agents and voice.

  • Give it a name and pick from fourteen icons
  • Write its role and the greeting it opens with
  • Set its tone, how long it answers for, and its language
  • Add your own rules in your own words
  • Name topics it should stay off, and ask it to cite its sources
Set onceTen fields
Its nameYours to choose
Its iconFourteen marks
Its languageTen of them
Where it shows up
ChatThe same name
Inbox draftsThe same tone
VoiceThe same greeting
Topics to stay offwritten once, read before every reply
It knows the product

It already knows what every part of NearSync does.

Every question is handed a written description of the whole platform first: deals and pipelines in Sales, invoices and approvals in Finance, sprints in Projects. So when somebody asks how to do a thing, they get the screen to go to rather than general advice. There is nothing to upload for that.

On every question
Every hubDescribed for it
How do I do thisAnswered with the screen
Setting it upNothing to do
It knows how the parts join up, like an invoice following a deal
Choosing one

Every model tells you how fast and how thorough it is.

Nobody expects you to test twenty-six models. Each is marked ultra fast, fast, balanced or deep, with what it is good at, how much it costs in credits, and how much it can read at once. One in each provider is marked as the sensible starting choice.

One model in the list
SpeedBalanced
Good atReasoning and code
CostShown in credits
One recommended pick in every provider
Before you route

Check a provider is answering before you move a department onto it.

Every provider has a test on the model settings screen. Run it and you get a tick or a cross straight away, so nobody is moved onto something that turns out to be set up wrongly. Providers a browser cannot reach directly are routed through NearSync, and the screen marks which those are.

Provider check
ResultA tick or a cross
Run itWhenever you like
Your own hardwareMarked as local
Nobody finds out at the next prompt

Identity

Preview it as you build it.

Fill in the name, the icon, the role and the greeting on the left, and a live preview on the right shows exactly what your team will see, updating as you type. There is nothing to publish before you can check it.

NearSyncNearSync AIPersona and SafetySearch, plan and askKAll hubs

Persona and safety

Ten things you set once.

These shape every answer the AI gives anyone in your company, on every screen it appears on.

Its name

Call it whatever suits you. The name follows it everywhere, in chat, in the inbox, on agents and in voice.

Its icon

Fourteen marks to pick from, so it looks like part of your product rather than a bolted-on robot.

Its role

One line describing what it is there for. It appears under the name on every screen.

Its greeting

The first thing it says when somebody opens a new conversation.

Its tone

Professional, warm, direct, or whatever you write. It follows this in every reply.

How long it answers for

Short and to the point, balanced, or thorough.

Its language

Ten to choose from: English, Arabic, French, Spanish, German, Portuguese, Hindi, Chinese, Japanese and Korean.

Your own rules

Anything else you want it to always do, in your words.

Topics to stay off

List the subjects it should not discuss with your people.

Show its sources

Ask it to cite the knowledge base article behind an answer, every time.

Knowledge

Teach it what your company knows.

The AI answers from your own knowledge base articles, finding the right one by meaning rather than by exact keyword. An article only reaches customers after somebody publishes it and marks it customer facing, and both of those are off until a person turns them on. You can refresh the whole library whenever you like.

It cites what it used

An answer names the article it came from, so anyone can check it.

It says when it does not know

When it is not confident in an answer, it says so and offers a person instead of guessing.

You decide what is public

Two separate switches, both off by default, before an article can reach a customer.

Prompt library

Keep the prompts that work.

A shared library your whole organisation can see, organised by department, with ten ready to use the day you start.

  • Deal risk, follow-up emails, expense categories, collection letters and job descriptions, ready on day one
  • Plus performance reviews, content calendars, site audits, written procedures and meeting summaries
  • Write your own, with placeholders you fill in each time
  • Your prompts work exactly like the built-in ones, in the same list
  • Filter by department so everyone only sees the prompts they need
Two kindsOne list
Ready to useTen from NearSync
YoursAs many as you like
They behaveIdentically
Fill in the blanks
Which dealYou pick
Which quarterYou pick
The wordingStays the same
Filed by departmentso a person sees the ones their team actually uses

Access

Who can do what.

Everybody uses the AI. Choosing which model a department runs on, and how the assistant speaks to the whole company, belongs to Admin.

See

See which model your department runs on.

Do

Use the assistant, and the prompts in the library.

Manage

Add prompts to the library for your team.

Admin

Choose providers, route departments, and set the persona.

Admin is the highest role and is not constrained by the permission grid, so it is worth keeping to the smallest group that genuinely needs it.

NearSync AI guides

See NearSync AI on your own data.

Half an hour on your own material, routed to whichever model you want answering.