adisingh13

i love what workos is doing and i also spoke at their event already. we think this is complementary - we're not setting out to create a new standard, we're giving better access to what already exists.

we extensively rate limit and prevent outbound sending until an agent has been verified by a human :) more detailed in OG post

i appreciate your feedback and thanks for using agentmail!

thanks for the feedback! it is top of mind for us, and we've done our research to prevent this as much as possible. it is constantly ongoing and we never settle in our measures to protect against this

yep we're going to have a footer linked to our website, which should allow people to see that we are an email service for agents. thanks!

This was likely a free tier user. We do this intentionally and don't allow free users to send from custom domains, so you can have a easier time identifying LLM emails. In this case, it seemed like it worked :)

Appreciate the concern Mike, and I actually read your email complaining, which helped us ship this next feature. We have a "sent via AgentMail" footer being added soon to outbound emails to identify emails coming from LLM's.

We also are working on adding more robust checks and LLM-based filtering to prevent messages which contain spam or outbound-like copy.

Re; AgentMail next to Claude, we're working on stateful inboxes which help agents actually recall and understand what they're sending and to who. The goal is to provide the rails for intelligent actors rather than slop.

agreed from a fundamental level. but i think being an intelligent and aware as an autonomous entity requires capabilities beyond sending. agents will need to have contextual awareness of the messages they send and receive

nice, we're working on agentmail so i think we have similar ideas. its a big problem!

how are you implementing agentmail? would love to know more

thank you, this means a lot!

We know the founder of this pretty well actually. It's not really an alternative. They are an MCP that is building an email-like layer for coding agents to talk to each other. We are an actual email inbox provisioned via API for agents to email agents or humans.

i'd love to know more about these use cases. open to chatting sometime? adi@agentmail.cc is my email

i'd love to know more about how you use gumloop and how agentmail can fit in. mind shooting me an email?

adi@agentmail.cc

thanks for the input, we always appreciate constructive feedback!

we have a few things in place, allowlists and permissions act as a layer. also beginning some work on prompt isolation within api soon. but having an isolated identity + data within a separate agentic inbox also puts less risk of your personal email data being injected - which is most people's main concern

Cloudflare/SES works if you want raw email sending and receiving. If you want threading, parsing, storage, retrieval, logic, filtering, labeling, search -- you'll need to build it out yourself.

We're devs ourselves so ik the first thought is usually "how hard can it be?" in our validation, we thought it was hard enough to build a startup around :) these things are easier said than done, and no one in 2026 should be stitching together email workflows. especially not agents

underrated take :)

what confused you? happy to help - shoot me an email at adi(at)agentmail(dot)cc

Yes exactly, we have some cases where people built a fully autonomous AI SDR

We're also pretty interoperable as we're an API and compatible with any framework today. Plans to double down here however

Thanks a lot! We're working on a lot of checks in place within our API for both the agents and email side, including things like spam filtering, verification, and protection against phishing or prompt injection. It's an interesting task at hand, solving both archaic and cutting-edge problems within the same product lol

thank you!!

thanks!!!

Thanks for the input sauwan - it means a lot. We're early, so this is by design. We have a generous free tier coming soon!

For now you can also use our playground at chat.agentmail.to

Fair concern but that comes with any email product. We're a provider not a mass sending API like Resend, Mailgun, Sendgrid - that means our use cases primarily revolve around personalized, two-way conversations between reasoning agents and humans.

Users bring their own :) maybe this changes in the future though

Great question - we get this input a lot. It really depends, while I'm a big believer of voice and API-driven design in the future, I think email's role remains but looks different. It's a sticky, universal protocol that serves as a great system of audit and record. Also think an agent is only as good as its context - an inbox serves almost as a personal gateway to the internet and early customer's use cases show different applications from agent-human connection to identity verification and authentication.