Something new at Superhuman

Catch conflicts in drafts without interrupting every edit

Published Nov 6, 2026

You’re the ai / ml engineer. Your team is in the room.

The setting

makes , an email app that works with Gmail and Outlook. It uses AI to draft replies in the user's voice and to sort incoming messages, for individual professionals and sales teams.

Checking a draft against its thread offers factual help at the cost of another interruption before sending.

Dates and prices deserve scrutiny, but ambiguous agreements make confident warnings difficult to justify.

Who you’d be doing this for

“I nearly sent the old fee again. I had to scroll through six replies to find the number we'd actually agreed.”

Carla Vargas · Consulting engagement manager · a character in this brief

Negotiates delivery dates and fees across long client threads.

What is at stake

Reviewers found factual conflicts in 19 of 120 client email threads. You choose what a new check should judge and how to prove it helps.

Why it isn’t already fixed

Every obvious fix costs something else. That’s the part you’d have to decide.

  • conflict recall vs interruption burden
  • explicit agreements vs ambiguous negotiations
  • offline precision vs fewer sent mistakes
  • automatic detection vs deliberate invocation

Why Superhuman

AI drafts replies in a user's voice, while the proposed capability judges whether those fluent replies still match the conversation.

Written with these in mind

Product-minded ML engineersLLM evaluation buildersExperiment-driven AI engineers

Not your kind of problem? 49 more at Superhuman, or browse every organization.

Where the organization context comes fromThe postings this brief was written from, and the reporting read before it.

The organization context comes from public information. The situation and characters are written for the brief.

Job postings it was written from

Public descriptions of the work at Superhuman. They are listed as sources, not as openings. The lines under a posting are its own words, where it meets this brief.

This is the setup. The work is inside.

Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.

Other live briefs connected to this one, and what connects them.

Similar problems at other organizations

Like this one, each of these is about people starting something and never quite finishing it.

The same setting, from another role

Each is set around Superhuman’s Superhuman Mail, written for a different role. They’re separate briefs, not the same scenario.