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.
A format correction preserves routing costs while a route switch preserves the existing prompt.
Calendar lookups need valid arguments, but today's release slot accommodates only one intervention.
Who you’d be doing this for
“I asked for Thursday's openings twice, then opened my calendar while the client waited.”
Nazanin Moradi · Agency account manager · a character in this brief
Checks availability while answering client requests for meetings.
What is at stake
Calendar lookups fail for 7% of requests after a prompt update. You weigh a precise correction against a proven route that costs more.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- narrow correction vs proven route
- shared prompt risk vs recurring cost
- valid arguments vs usable answers
Why Superhuman
Ask AI routes across models, so a model-specific formatting change interrupts an otherwise working MCP tool.
Written with these in mind
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.
- AI Engineer (Superhuman Mail) - US (opens in a new tab)
- AI Engineer (Superhuman Mail) - Latin America (opens in a new tab)
- AI Engineer (Superhuman Mail) - Canada (opens in a new tab)
- Senior Design Technologist, AI Tooling (opens in a new tab)
- Understand AI API integration: streaming, prompt engineering, structured outputs, tool use.
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.
Where similar work appears
Other live briefs connected to this one, and what connects them.
Similar problems at other organizations
Like this one, each of these turns on fixing one thing without breaking another.
Successful connected asset generations fell to 82% after the prompt-template update.
You must weigh a fast context cap against preserving enough file detail for useful output.
P95 first response has risen from 1.1 to 2.4 seconds after redundant retrieval calls appeared.
You must weigh a faster cache path against session-safe context and answer quality.
Agents received outdated preferences first in 36 of 200 requests, despite correctly stored updates.
You weigh a targeted ranking correction against a filter that excludes superseded preferences from retrieval.
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.
New Mail users skip AI actions when urgent client email arrives.
You must decide whether the first AI moment begins in a live thread or a guided setup moment.
New subscribers are buying an upgrade with conflicting expectations about access.
You must decide how much purchase momentum can move before customer understanding is proven.
New desktop users are skipping iOS setup and staying in a single-device inbox habit.
You need to decide how prominently mobile setup belongs before users reach their first inbox.