Launched this week
Chert
Build AI agents that text customers in iMessage
288 followers
Build AI agents that text customers in iMessage
288 followers
Build and deploy conversational iMessage agents for customer service, inbound lead capture, and more. Simply configure the system prompt and tone, and you can create your own conversational iMessage agent for inbound handling, outbound follow-up, or whatever workflow you want to test. You can also integrate with CRMs like HubSpot, Close, or GoHighLevel to write back conversation histories.
Chert
Hi everyone, I'm Gary, co-founder of Chert!
We've spent the last six months building projects on iMessage for leasing companies, DTC startups, and home service agencies. Across these use cases, we kept seeing the same problem. Founders wanted to deploy conversational iMessage agents for customer service, lead capture, and outbound follow-up, but the underlying infrastructure was difficult to set up and hard to scale reliably.
This is what inspired us to build Chert, a platform for teams to create and deploy iMessage agents, powered by infrastructure that can send, receive, and automate conversations over iMessage at scale. There's a few main features that we believe will make Chert stable, reliable, and scalable:
- Chert provides comprehensive line health checks, making it safer and more robust for outbound use cases.
- Additionally, Chert offers a scalable pricing structure that lets teams scale to hundreds of lines and thousands of messages.
- Finally, Chert integrates with CRMs like Salesforce, HubSpot, and Close and tools like Vapi and Slack, so teams can easily add iMessage into their existing stacks at scale.
Feel free to try building and deploying your own iMessage agent through the Agents page in our website. No credit card required.
Would love any feedback or thoughts!
Happycapy
@garygao this is actually a very smart angle.
everyone is building AI agents for email/web/chatbots, but iMessage is still weirdly underexplored despite insanely high engagement rates. feels like there’s a real infra opportunity here.
Chert
@victoria_wu I agree! On top of the high engagement rate, it also feels more conversational and human!
@victoria_wu @garygao Hey Gary, congrats on the launch 👋
The iMessage angle is genuinely underexplored - Victoria's right that engagement rates on iMessage dwarf email and webchat. But the question I keep coming back to with any iMessage-at-scale play: how are you handling the Apple side of deliverability?
Specifically: when you scale to "hundreds of lines and thousands of messages," what's the failure mode when Apple's spam heuristics start flagging numbers? Is "line health checks" essentially monitoring delivery rates and rotating numbers proactively, or is there something deeper happening at the infra level?
Asking because the iMessage moat is real (engagement, native UX, no install), but the platform risk is equally real -Apple owns the rails and historically isn't shy about closing them. Curious how you're thinking about durability of the channel over 12-24 months.
Chert
@garygao @victoria_wu Thanks Victoria, mean a lot for us!
@garygao Hi Gary, congrats on the launch. Any plans to add other messaging platforms (WA) later on?
Chert
@zolani_matebese Yes! We're thinking about adding other channels like WhatsApp in the future!
Getting iMessage delivery working for AI agents is a non-trivial integration challenge since Apple doesn't expose a public API. We've wrestled with customer communication channel tradeoffs at RetainSure, and iMessage reach in B2C contexts is real. How are you handling message delivery guarantees and rate limits at scale when the underlying transport doesn't give you standard webhook callbacks?
Chert
@anand_thakkar1 We have a lot of robust health checks in place that prevents rate limitations at scale. We also have custom systems built out that supports webhooks and exposes APIs!
Chert
@anand_thakkar1 Yeah exactly, that’s the core challenge. Since there’s no clean public iMessage API or standard webhook layer, we treat delivery more like an observed state machine than a simple callback system.
On rate limits, we stay conservative and distribute sending across accounts/devices instead of trying to brute force volume. For delivery guarantees, we track message state from the transport layer, retries, failures, response behavior, and operator-visible logs. It’s definitely less deterministic than email or SMS, but that’s also why the channel works so well when handled carefully.
Do people usually use Chert to replace sms or have you seen circumstances where people use
both sms/rcs and blue-bubble messaging?
Chert
@kumar_ritesh21 I've seen circumstances of people using both. A lot of times, people use sms/rcs for auth and transactional messaging and iMessage for 2-way conversational messaging
Chert
@kumar_ritesh21 We usually see Chert used alongside SMS/RCS, especially when teams already have an existing SMS flow. The main reason people add blue-bubble messaging is that the response rate and perceived trust are meaningfully different, especially in consumer-facing conversations.
PopPop AI Vocal Remover
Congrats! This is cool. Are your customers typically coming from other iMessage tools and switching, or are they mostly introducing iMessage as a brand-new channel?
Chert
@charlenechen_123 Mostly as a brand-new channel! Most of them actually use SMS/RCS before switching to iMessage!
Big congrats on the launch. What does the integration actually look like? Is it mostly configuring the agent prompt and workflow in the dashboard, or do teams usually connect it into their existing stack too?
Chert
@vishalmehta8340 Teams can connect it to their existing stack! We already support integrations in Salesforce, Hubspot, Slack, Attio, Close CRM, and more!
Chert
@vishalmehta8340 Thanks! For most teams, the first version is just configuring the agent, workflow, and guardrails in the dashboard.
As they scale, they usually connect Chert into their existing stack so replies, leads, and status changes sync back cleanly.
@garygao Congrats on the launch! Really interesting product. Is there a way to try building an agent before talking to sales? I’d love to send a few test messages and see the developer flow end to end.
Chert
@suyash_kr Yes, try out our agent builder, it's completely free and very easy to get started!
Could see this being really useful for businesses that get a lot of inbound interest. Are people using Chert to capture new demand right now or to mainly convert old demand they already missed?
Chert
@jocky Both! There are companies using Chert to do lead reactivation and also others using Chert to do warm outbound!
@garygao That's pretty awsome!