AI companies are pushing agents as the next Great Workplace Disruptor, but experts say they’re still not ready for prime time. AI agents often struggle to make decisions by themselves, hallucinate frequently, can’t cooperate with other agents, fail at confidentiality awareness, and integrate poorly with existing systems.
Industry pioneers like Andrej Karpathy and Ali Ghodsi have said that, like the deployment of autonomous vehicles, humans need to be in the loop in order for agents to succeed.
A startup called Mixus wants to address that with its AI agent platform that not only keeps humans in the workflow, it also lets users interact with agents directly from their email or Slack.
“We’re meeting customers where they are today,” Elliot Katz, Mixus’ co-founder, told TechCrunch. “Where is every person in the workforce today? For the most part, they’re on email. And so because we can do this through email, we believe that’s a way we can democratize access [to agents].”
If Mixus works reliably, it may solve a big problem in the AI agent space. Most AI companies today either give you a pre-built assistant, à la ChatGPT or Gemini, or developers have to build custom agents using frameworks like LangChain, AutoGen, or crewAI.
Mixus launched in beta out of Stanford only in late 2024, but it has already raised $2.6 million in pre-seed funding and brought on some customers, including clothing store chain Rainbow Shops, as well as others across finance and tech.
The startup says its biggest selling point is ease of use, from how it helps you create agents to how you can interact with them. Users can use text prompts to set up their agents within Mixus’s platform via a chat function, or by simply emailing instructions to agent@mixus.com. Then Mixus will build, run, and manage single- or multi-step agents directly from the inbox.
For example, a customer support manager may use a prompt that reads so:
Create an agent that finds all open tasks in Jira in project mixus-dummy, and send me a report with information on all tasks that are overdue. Draft emails to all the assignees who have overdue tasks, and have me review them in the chat and with simple clear formatting for email (no attachments/docs). Once I verify, send the emails. Run it now. And moving forward, run it every Monday at 7am PST.
Katz and his co-founder Shai Magzimof demoed the agents for TechCrunch, showing how to add human verifiers for your agents by simply instructing at which step the agent should ask you for oversight.
For example, they ran an agent to do research on TechCrunch reporters before pitching them. The agent identified and gathered technology news and trends, analyzed the information to identify potential story angles, and compiled a research report summarizing the findings. At the last stage, the agent was directed to send the information to Katz for verification. Once approved, the agent would send the completed research report to Magzimof.
Story Continues