One credit, one question.

Every question costs one credit, so there are no tokens to work out and no surprise bill. See what the company asked, on which models, and by whom. Set a daily allowance per person and a monthly one for the company. Meetings have their own separate allowance, with fifty hours included.

MeasuresWon revenue99 definedUsed by 14 boards
Sales boardSame numberno argument
Finance boardSame numberno argument
Exec boardSame numberno argument
InBase currencyno conversion
Ninety-nine measures, one language.
One definitionRevenue means the same thing on every board in the company

A measure is defined once - the entity, the aggregation, the field and the currency-safe field - and every widget, report and board reads that definition rather than a column somebody picked.

What it costs you

Costs anyone can understand.

Everything is counted in questions, so anyone in the company can look at the number and know what it means.

A credit is a question

Ask the assistant something and that is one credit. No tokens or word counts to work out.

Meetings are separate

Transcription, the write-up and the coaching all run on real AI and none of it touches your credits. Fifty hours come with the plan.

Credits are per seat

Each person has their own allowance, so one heavy week from one person does not eat the whole team's month.

Your own hardware costs nothing

Point a department at a model running on your own machines and its questions are free.

Watching it

What the company asked, and on what.

Six numbers across the top, three charts under them, and every model, person and question underneath. Choose today, the last seven days, the last thirty, or everything since you started, and the whole screen updates to match.

NearSyncNearSync AIUsageSearch, plan and askKAll hubs
Credits used4,180-8% on the period beforeAverage latency1.4s-26% on the period beforeQuestions asked4,180+14% on the period beforeTokens9.2m+11% on the period beforeModels in use6+1 on the period beforeErrors0.2%-0.3pt on the period before
How long answers tookThe middle answer, the slow one in twenty, and the slowest in a hundred
Half of all answersNineteen in twentyNinety-nine in a hundred
Credits by departmentStacked, day by day
SalesFinanceCommsSupport
Credits by modelShare of the month
  • GPT-5.448%
  • Claude Opus 4.832%
  • Gemini 3.5 Flash13%
  • Claude Sonnet 4.67%

The six numbers

Every number shows which way it is moving.

Each figure is shown with its change against the previous period, so you can see at a glance whether it is rising or falling.

Credits used

How many questions the company asked, in the unit you are billed in. Nothing to convert.

Average latency

How long an answer took, on average. Moving a department to a faster model shows up here within a day.

Questions asked

The total count across everyone, shown next to credits so you can spot when one climbs faster than the other.

Tokens

The raw usage underneath, for anyone who wants the detail. You are never billed on this number.

Models in use

How many different models the company actually used. Useful the week after you change which models answer.

Errors

The share of requests that failed. A provider having a bad afternoon is visible before anyone reports it.

The charts

Three charts answer the big questions.

Is it fast, where is it being used, and what is the expensive part. One chart each, drawn from the same period you picked at the top.

Is it fast enoughAnswer times, three ways at once

Not just the average. The typical answer, the slow one in twenty and the slowest in a hundred, plotted together, so a few slow answers cannot hide behind a good average.

Where is it being usedCredits by department, day by day

One bar per day, split by department. You can see a team start using the assistant, and you can see one stop.

What is the expensive partCredits by model

The share of credits each model used over the month, so you can see whether the expensive model is earning its place.

Fifty hours of meetings, outside your credits.

Meetings

Meeting AI has its own allowance.

Transcription, the write-up and the coaching afterwards all run on real AI, and none of it touches the credits your people ask questions with. Fifty hours come with the plan, so a heavy month of meetings never cuts into the assistant allowance.

Fifty hours, included

Recorded and transcribed meetings, bundled with the plan rather than drawn from anybody's allowance.

The write-up is AI

A summary, the decisions and the follow-ups, produced by a real model reading the transcript.

So is the coaching

Talk ratio, questions asked and the habits worth changing, scored after the call.

None of it costs a credit

A heavy month of meetings leaves the assistant allowance exactly where it was.

You set the ceiling

Three limits, and you choose all of them.

A daily allowance per person, a monthly one for the company, and a rate per minute.

  • Cap what any one person can use in a day
  • Cap what the whole company can use in a month
  • Cap how many questions can be asked per minute, so a runaway automation cannot drain credits
  • Set any of them to unlimited
  • See the same meter your people see, so nobody is surprised
Three limitsAll yours
A person, a day200 credits
The company, a month12,000 credits
Anyone, a minute20 questions
Or none of them
Set it to zeroUnlimited
Takes effectNext prompt
Applies toEveryone
One numberthe meter a person watches is the cap that gates them
Per seat

Everyone has their own allowance.

Your meter and the limit that applies to you are the same number, so you always know where you stand.

  • See your own use as you go, in credits
  • Keep an allowance that is yours alone, not shared from a pool
  • Let a manager see what their department is using
  • Compare what each model actually cost you across a month
  • Watch a department move to your own hardware and its cost drop to zero
Your monthPer seat
Today41 credits
This month612 credits
Shared out of a poolNo
What a manager reads
Their departmentBy person
Each modelWhat it accounted for
Your own hardwareNothing
Counted in questionsa credit means the same thing on every screen
Before the answer

Your allowance is checked before the question is answered.

NearSync asks whether you are inside your allowance first, then answers. There is nothing to settle at the end of the month and no bill that turns up bigger than the plan, because a question beyond the allowance was never answered in the first place.

Each question
CheckedBefore it runs
Settled at month endNever
Charged for going overNever
The check reads the same figure your meter shows
At the ceiling

When the month's allowance runs out, AI pauses and says so.

Nobody gets a vague error. The message names how many credits your workspace has used out of its allowance and what to do about it. Everything else in NearSync carries on exactly as normal, and the allowance comes back at the start of the next month.

The message
NamesCredits used and allowed
Rest of NearSyncUnaffected
Allowance returnsNext month
Paused, not quietly billed on
On our side

A problem on our side never stops your team asking.

If the allowance check itself cannot be reached, NearSync lets the question through instead of blocking it. We would rather serve a handful of questions we did not count than lock a paying team out over a fault that was ours.

If the check is down
Your questionStill answered
Locked outNo
Checked againWithin the minute
We would rather over-serve than block you

Spending less

It shows you where the credits go.

NearSync looks at your own usage and points out the obvious savings: a department using a heavy model for simple questions, a model that costs several times more than an alternative for the same work, or a team that could run on your own hardware for free. Make the change on the Setup screen, and the next chart shows whether it worked.

Which department

Named, with the model it uses now and the kind of questions it asks.

Which model

The cost per question, shown next to the model you would switch to.

What it would save

The saving in credits, over the period you are looking at.

Access

Who can do what.

Everyone can see their own meter, and managers can see their department. What the whole company uses, and the limits themselves, belong to Admin.

See

Watch your own credit meter as you use it.

Do

Ask questions, knowing exactly how much of your allowance is left.

Manage

See what your department is using, and on which models.

Admin

Set the daily, monthly and per-minute limits.

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.