Superhuman brings its Go AI assistant to Mail, Docs and the rest of its suite

Nov 19, 2026
The company formerly known as Grammarly adds proactive drafting, background agents and 20 connected agents including DeepL and Databricks.

Superhuman, the company formerly known as Grammarly, is rolling out a more personalised version of its Go assistant and making AI agents available across its products, including Docs and Superhuman Mail.

Go now learns context across different apps, learns users' writing styles for email and Docs, and works proactively, keeping an eye on schedules and email and drafting responses. A revamped onboarding lets users connect their tools and load context about their work upfront. The company is adding 20 connected agents through its Go SDK, including DeepL, Legora, Amplitude, Databricks and Blackboard.

In Docs, all Go agents work natively and can run tasks in the background, and users can set routines that trigger workflows based on events. In Mail, Go replaces the earlier AI tools, offers enterprise search across company knowledge and connected tools, and drafts and organises inboxes across Google and Outlook accounts. Superhuman, which acquired notetaker Fathom in September, is also rolling out live collaborative notetaking, according to TechCrunch.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Enterprise AI Brief or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Enterprise AI Brief

Weekly report on AI business applications, enterprise software releases, automation tools, and industry implementations.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.