The setting
makes productivity software for email-heavy workers and teams. is an AI assistant that takes on tasks across the browser, desktop and Superhuman apps, working from goals written in plain language.
A missed client promise is costly, but a premature reminder is easy to distrust.
The suggestion must catch commitments hidden across work context while preserving the user's confidence that Go knows what matters.
Who you’d be doing this for
“My client asked where the update was, and I had to search three threads to see we’d promised it Friday.”
Bakari Eshetu · Agency Account Director · a character in this brief
Manages client deliverables and follow-ups spread across external email threads and shared working documents.
What is at stake
Agency account directors are missing client promises buried across email and documents. You must decide what evidence earns a proactive suggestion without turning Go into background noise.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- commitment recall vs. interruption trust
- cross-application context vs. explainable evidence
- accepted suggestions vs. model cost
- pilot speed vs. durable evaluation
Why Superhuman
Go's cross-application context is only valuable when it turns scattered client commitments into timely, reviewable work.
Written with these in mind
Not your kind of problem? 36 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.
- Machine Learning Engineer (opens in a new tab)
- You'll also build the suggestions that point out what matters before the user asks.
- Users connect many apps and agents, and their requests can take many steps.
- Senior Design Technologist, AI Tooling (opens in a new tab)
- You will help ensure our AI-native platform (spanning email, calendars, docs, and agents) is supported by scalable systems that maintain our high-quality standards.
- Build high-fidelity, interactive prototypes that bring speculative and near-term product ideas to life with enough realism to be used in research, stakeholder alignment, and product decision-making.
- AI Engineer (opens in a new tab)
- Build high-quality evaluation datasets: Design, source, and curate golden sets, labeled data, and synthetic data for agent behaviors, search ranking, and proactive suggestions.
- As Superhuman Docs’ collaborative workspaces evolve so users can solve arbitrarily complex tasks with agents, rigorous measurement will be what lets us ship with confidence.
- Software Engineer, Full-Stack (opens in a new tab)
- Genuinely excited about what is possible with LLMs today, using them not just as APIs, but as building blocks for intelligent tools and products.
- Build a Groundbreaking AI Agent Platform: Spearhead the development of a new AI platform inside the Superhuman Docs product of the Superhuman suite where multiple AI agents collaborate to solve complex user problems.
Reporting read before this brief was written
The pieces closest to the situation in this brief.
In its August 12, 2026 Go 1.0 launch, Superhuman put connecting work apps and creating custom agents behind paid plans, started with soft usage limits, and said it expects to roll out usage-based pricing over time.
Go 1.0: Custom, Proactive Agents Everywhere You Write (opens in a new tab) · blog.superhuman.com · Aug 12, 2026
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 deciding on evidence that's still thin.
In a sample of 2,000 service conversations, 18% of customers returned within 48 hours, but only some still needed help.
You must weigh a useful signal of unfinished service against unnecessary follow-ups and labels that confuse a new question with an old problem.
The same setting, from another role
Each is set around Superhuman’s Superhuman Go, written for a different role. They’re separate briefs, not the same scenario.
Go workflows complete in the Chrome extension and then stop after a user continues in the desktop app.
You must decide whether the system or the engineers decide which of streaming state, context gathering or the surface handoff gets treated as the cause when they disagree.
Enterprise users can approve prepared work without one complete view of its connected reads and writes.
You have to weigh a fast approval flow against the detail administrators and client-facing users need to trust it.
A replay showed Go preparing an update from context after an administrator removed access.
You have to weigh a fail-closed control against valid workflows that may be blocked during an enterprise rollout.
Other problems with a similar purpose
In each of these, as in this one, the aim is to turn observed user friction into a fast, confident decision that visibly restores a better experience.
Managers export disconnected monitoring and publishing data 2.4 times more often when using both surfaces.
You have to weigh a focused first view against broader reporting expectations.
Marketing specialists are rebuilding near-identical campaigns location by location for multi-unit groups.
You must weigh brand consistency against the local flexibility restaurant managers need.
Search-led product-detail views are stuck at 18% despite rising search volume.
You have to weigh a sharper discovery configuration against the customer engineers’ need to validate it safely.
