Separ8™by AETHER

Separ8: sort a whole inbox in seconds, then see which answers to trust

Today AETHER is opening early access to Separ8, a tool that answers plain-English questions about every row of an inbox, lead list or spreadsheet at once, then measures how far those answers can be trusted before anyone relies on them.

Separ8 sorting support emails, marking which can be handled automatically and which need a person

Why we built it

Most teams have a pile someone reads by hand just to decide what happens next: support tickets, inbound leads, product reviews, applications. The reading isn't the work. The decision is: which team, how urgent, does this need a person.

In September, TypeSafe released Jev, a model built for exactly that kind of decision. It doesn't write. It answers questions you define, with a probability for each answer, in a fraction of a second, for about four cents per million tokens of input. Developers took to it fast, and the demos were everywhere.

But two things stood out to us. Nearly every tool built on Jev so far is for engineers: command-line scripts, SDKs, SQL functions. And the independent research kept saying the same thing: Jev's confidence numbers aren't reliable out of the box. One audit found its calibration shifts with the task and even with the wording of the same question. So the number that's supposed to tell software when to act on its own can't be taken on faith.

Separ8 is our answer to both. It gives non-engineers a way to use a decision model on their own data, and it makes them check the model before they trust it.

How it works

  1. Describe the decision. Upload a CSV, or start from a sample, and say in a sentence what you need to know. "Route each email to the right team, flag anyone asking for money back." Separ8 drafts precise questions, defines every answer, and adds a way out for rows that fit nothing. You can edit all of it.
  2. Sort everything at once. Every question runs on every row in parallel. You get a summary of every answer and a table showing each row's answers and how sure the model was.
  3. Check, then trust. You mark the right answer for 20 to 50 rows. Separ8 measures how often the model agreed with you at each confidence level, then finds the line that meets the accuracy you choose. Rows above it can be handled automatically. Rows below it go to a person, highlighted.

The third step is the point. A model that's 90% sure isn't right 90% of the time just because it says so. Your own answers are what turn its numbers into a line you can stand behind.

What we saw in testing

We built three fictional datasets and ran each through Separ8 with four questions per row. Every sort finished in under two seconds and cost less than half a cent.

DatasetRowsQuestions per rowTimeModel cost
Support inbox11641.2 s$0.0041
Sales leads6040.5 s$0.0020
Product reviews6040.5 s$0.0017

It caught every safety problem we planted. We wrote six of the 60 reviews to describe a hazard: a carafe that cracked and splashed hot coffee, a kettle that sparked, a mixer that smoked. Separ8 flagged exactly those six. A review about a lingering chemical smell came in just under the line at 31%, the kind of gray-area case a person should see anyway.

The trust check told the real story. On the support inbox we checked 20 emails by hand, giving our honest answer even on the gray-area ones. The model agreed with us 75% of the time overall. That's not good enough to automate everything, and Separ8 doesn't pretend it is. The pattern underneath is what matters: of the 10 answers Jev was at least 95% sure of, all 10 matched ours; of the 10 it was under 60% sure of, only half did. With a 90% accuracy target, Separ8 recommended handling 93% of emails automatically and sending the other 7% to a person.

The trust check after 20 emails: 75% agreement overall, 93% of emails handled automatically at a 90% accuracy target
The trust check after 20 emails. Confident answers matched every time; unsure ones were a coin flip.

Twenty checks is an early read, and the app says so. These datasets are also ones we wrote ourselves. Real inboxes are messier, which is exactly why the check is built in rather than left to faith.

Results table with one email highlighted as needing a person
Rows below the line are highlighted for a person. The rest can be handled automatically.

Where it fits

Separ8 helps anywhere people read a pile one item at a time just to decide what happens next.

TeamWhat Separ8 decidesWhat changes
SupportWhich team, refund or chargeback risk, how blocked and how angryThe angriest, most-blocked customers are at the top of the morning queue
SalesFit, timeline, budget, real intentRecruiters, vendors and students drop out; buyers who need it this month rise
Ecommerce and brandsSafety risk, topic, needs a reply, sentimentReviews mentioning burns or sparks are caught the day they land
Operations and financeCategory, needs approval, unusual or routineOnly the unclear transactions reach a person
Legal and complianceRequest type, clause type, risk levelLawyers start with the items that actually need them
ProductFeature area, urgency, bug or requestRoadmap calls start from counts, not anecdotes

One caution: for hiring, Separ8 should flag and people should decide. Researchers at Bocconi University found Jev can be swayed by irrelevant numbers and by the order answers are listed in. We also recommend removing names and other personal details first.

Self-serve or done for you

You can use Separ8 yourself today, or have AETHER set it up and run it for you.

Self-serveDone for you by AETHER
Best forA pile you want sorted todayDecisions that happen every day
SetupAbout ten minutes: upload a CSV, describe the decision, edit the drafted questionsWe connect Separ8 to where items arrive (inbox, helpdesk, CRM, forms), write and test the questions with your team, and run the trust check on your real history
ReportsA summary of every answer, every row with its confidence, and a CSV exportResults land where you already work, plus a monthly report: volume, share handled automatically, accuracy against fresh spot checks
OngoingRe-check 20 rows whenever your data changesWe watch for drift, re-measure when the model updates, and adjust the questions as your business changes

Today the app works with CSV files. Connections to live systems are part of the done-for-you setup, built for each client.

The live demo runs on real models with three sample datasets, and you can upload your own CSV of up to 500 rows. The two-minute walkthrough shows a full run, from a raw inbox to the trust check. We're opening Separ8 to a small group first.

Sources