21 C
New York
Wednesday, July 23, 2025

Buy now

This startup thinks email could be the key to usable AI agents

AI firms are pushing brokers as the subsequent Nice Office Disruptor, however specialists say they’re nonetheless not prepared for prime time. AI brokers usually battle to make choices by themselves, hallucinate incessantly, can’t cooperate with different brokers, fail at confidentiality consciousness, and combine poorly with current methods.

Trade pioneers like Andrej Karpathy and Ali Ghodsi have stated that, just like the deployment of autonomous automobiles, people must be within the loop to ensure that brokers to succeed. 

A startup known as Mixus desires to handle that with its AI agent platform that not solely retains people within the workflow, it additionally lets customers work together with brokers instantly from their e-mail or Slack. 

“We’re assembly prospects the place they’re at this time,” Elliot Katz, Mixus’ co-founder, informed iinfoai. “The place is each individual within the workforce at this time? For essentially the most half, they’re on e-mail. And so as a result of we are able to do that by means of e-mail, we consider that’s a approach we are able to democratize entry [to agents].”

If Mixus works reliably, it could resolve an enormous downside within the AI agent house. Most AI firms at this time both provide you with a pre-built assistant, à la ChatGPT or Gemini, or builders should construct customized brokers utilizing frameworks like LangChain, AutoGen, or crewAI. 

Mixus launched in beta out of Stanford solely in late 2024, nevertheless it has already raised $2.6 million in pre-seed funding and introduced on some prospects, together with clothes retailer chain Rainbow Outlets, in addition to others throughout finance and tech. 

See also  Meta’s next big bet may be humanoid robotics

The startup says its largest promoting level is ease of use, from the way it helps you create brokers to how one can work together with them. Customers can use textual content prompts to arrange their brokers inside Mixus’s platform through a chat operate, or by merely emailing directions to agent@mixus.com. Then Mixus will construct, run, and handle single- or multi-step brokers instantly from the inbox. 

Techcrunch occasion

San Francisco
|
October 27-29, 2025

For instance, a buyer assist supervisor might use a immediate that reads so: 

Create an agent that finds all open duties in Jira in undertaking mixus-dummy, and ship me a report with data on all duties which can be overdue. Draft emails to all of the assignees who’ve overdue duties, and have me overview them within the chat and with easy clear formatting for e-mail (no attachments/docs). As soon as I confirm, ship the emails. Run it now. And transferring ahead, run it each Monday at 7am PST.

Katz and his co-founder Shai Magzimof demoed the brokers for iinfoai, exhibiting tips on how to add human verifiers in your brokers by merely instructing at which step the agent ought to ask you for oversight.

For instance, they ran an agent to do analysis on iinfoai reporters earlier than pitching them. The agent recognized and gathered know-how information and traits, analyzed the data to determine potential story angles, and compiled a analysis report summarizing the findings. On the final stage, the agent was directed to ship the data to Katz for verification. As soon as authorised, the agent would ship the finished analysis report back to Magzimof. 

See also  Why most enterprise AI agents never reach production and how Databricks plans to fix it

The founders famous that people may be within the loop as a lot or as little as required — Magzimof stated organizations can arrange company-wide guidelines, like making certain an e-mail will get checked by a human if it’s being despatched outdoors the corporate.

Bringing different colleagues into the workflow is as simple as tagging them within the chat with an AI agent, or copying them on the e-mail to the agent. That’s one other standout in comparison with brokers on the markets at this time: Most fashions are single-user, and whereas Notion AI and Slack enable customers to collaborate in shared areas, they don’t let the AI handle conversations and duties between teammates in actual time. 

One other core function of Mixus is its means to recollect information, chats, prompts and brokers. 

“We created Areas so that each crew, each individual, each group of individuals can have a shared reminiscence,” Magzimof stated. “Then all my brokers, all my information, all of the folks may be in that very particular House’s reminiscence.”

Whereas ChatGPT and Claude each assist reminiscence, their enterprise plans don’t but assist shared agent reminiscence throughout customers.  

What else can Mixus do?

In our interview, the founders ran by means of an hour-long demo exhibiting a variety of use instances and talents. Mixus’ brokers do appear succesful, reflecting a excessive diploma of autonomy and reminiscence that locations the corporate in direction of the upper finish of the AI agent spectrum. That’s, if the product works as reliably because it did within the demo.

See also  AllTrails debuts $80/year membership that includes AI-powered smart routes

Like different brokers, Mixus can combine with different instruments, from Gmail to Jira, and customers can set off brokers to run instantly or on a schedule. Brokers can run and edit paperwork or spreadsheets inline — much like ChatGPT, Microsoft Copilot, and Google Gemini, however these are sometimes restricted to sandboxed environments.

Mixus additionally lets brokers autonomously navigate organizational context — like determining who in a corporation owns a job by trying by means of Jira tickets.

Constructed on a mix of Anthropic’s Claude 4 and OpenAI’s o3, Mixus brokers even have entry to the net, which Magzimof says may be tapped for duties like dwell analysis or monitoring. He described it as “Google Alerts on steroids.” 

Taken collectively, Mixus seems to be much less of a productiveness instrument and extra like a tireless digital colleague – one more formidable try to reimagine AI as a collaborator. If it really works as marketed, your subsequent “coworker” may not be human, nevertheless it may get by means of your inbox quicker than you do.

Correction: This text was up to date to replicate how a lot Mixus has raised so far.

Bought a delicate tip or confidential paperwork? We’re reporting on the inside workings of the AI trade — from the businesses shaping its future to the folks impacted by their choices. Attain out to Rebecca Bellan at rebecca.bellan@techcrunch.com and Maxwell Zeff at maxwell.zeff@techcrunch.com. For safe communication, you’ll be able to contact us through Sign at @rebeccabellan.491 and @mzeff.88.

Supply hyperlink

Related Articles

Leave a Reply

Please enter your comment!
Please enter your name here

Latest Articles