Inrō AI - Your AI Agent for Instagram Marketing
by•
Inrō's AI Agent handles your Instagram DMs end-to-end.
Set a goal, train it on your knowledge, and let it engage your audience, qualify leads, book calls and follow up on its own. AI is also built into every automation step, detecting intent, branching on conditions, and handing off to the agent mid-flow.
Describe what you want and Inrō builds the automation for you. Connects to Claude, ChatGPT, Shopify, Stripe and 8,000+ tools. Meta-approved, join 10000+ brands and creators today!
Replies
Inrō
PicWish
@kshitij11 interesting. what happens when the rag doesn't have the answer? does it auto handoff to human or just guess?
Inrō
@mohsinproduct Honestly it depends on how you've set it up, which is intentional.
A few options available: you can enable human handover so it escalates automatically when it hits a knowledge gap.
You can restrict it to only answer from your knowledge base, or allow it to draw from broader context when needed.
You can also trigger a specific automation when it doesn't know the answer, so instead of just stopping, it takes a defined next step like sending a link or collecting info.
And in practice, before it even gets to any of that, it usually asks a clarifying question first to make sure it's actually hitting a knowledge gap and not just misreading the intent.
So less "it guesses" and more "you decide what thoughtful looks like for your use case"
Inrō
Hey, Pierre here, CTO.
Kshitij covered the what. I'll give you a bit of the how and why, since I know this community tends to care about that.
The hardest part of building the AI Agent wasn't the AI. It was making it behave predictably inside a platform with thousands of active automations already running.
Getting intent detection, mid-flow CRM writes, and agent handovers to work reliably without touching existing flows took most of the last year.
A few things worth knowing under the hood:
1️⃣ AI models tend to be very chatty and quite slow. That does not work for DMs and comments. It took a lot of engineering and optimisation for the AI Agent to reply in a few seconds, including emojis, likes, etc. and still stick to the knowledge provided.
2️⃣ The knowledge base runs on RAG, so the agent retrieves relevant context before responding rather than making things up.
3️⃣ The MCP server exposes 40+ tools to external agents, meaning Claude or ChatGPT can query contacts, trigger scenarios, and manage campaigns directly without touching the UI.
📺 On the product side, the thing I'm most proud of is how much of this runs without configuration. Opt-out detection, spam filtering, folder exclusions, intent triggers.
It all works in the background. You set up your flow and it handles the edge cases itself.
If you have questions about the stack, the API, the MCP integration, or anything technical, I'm here.
Inrō
Hey everyone, Etienne here, I'm the CEO.
I want to add some context on the commercial side because it tells part of the story Kshitij didn't cover.
When we were last on Product Hunt, we had a handful of early customers and, honestly, more conviction than proof.
Today, we're at 10,000+ active users with accounts at Loréal, Walmart, Kering, Publicis, and Virgin Voyages, among others. Seeing it work for both a solo creator and an enterprise brand in the same week still surprises me a little.
The question I get most often is about pricing, specifically how we handle AI given its central role in the product now. The answer is straightforward.
The AI Agent is fully included in Pro. No add-on, no separate usage fee.
Many tools charge extra for AI features. We made a deliberate decision not to do that.
And if you're discovering Inrō for the first time today, we're running 50% off for the first 2 months as part of this launch.
Worth trying now if you've been curious.
If you have questions about pricing, how the plans work, or how Inrō fits into a broader marketing setup, drop them here, and I'll answer directly.
Inrō
Hey, Giulia here from the marketing team. 🙌🏻
I want to flag something for anyone who might want to work with Inrō beyond just using the product.
We run three programs and they don't get talked about enough.
❤️ The Creative Partner Program is for creators and affiliates who want to promote Inrō to their audience and earn from it.
👥 The Agency Program is built for agencies running Instagram across multiple client accounts, there are specific tools and pricing structures that make that setup a lot more manageable.
🤝 The Referral Program is open to all Pro users and lets you earn commission just by recommending Inrō to people you know.
I've been on the marketing side long enough to see this go from a niche automation tool to something enterprise brands and solo creators use in completely different ways for different goals. That breadth is something I didn't fully anticipate when I joined.
Full details on all three programs are at inro.social. If you have questions about partnerships, co-marketing, or anything on the growth and marketing side, happy to talk it through here 😃
This looks intriguing, been searching for something like this to UP my instagram game. Curious to know can we bring our own API key?
Inrō
@rajat_kinger
Yes, you can! You can bring your own API key and connect it directly, which means you're using your own model credits rather than ours. Useful if you're already paying for API access or want more control over usage and costs.
Be sure to try it today, and let me know your feedback :)
Inrō
@erica_ding Primarily the DM and conversation side, not ad optimization itself.
But it does connect to your paid efforts.
You can trigger automations from Meta ads, send conversion data back to Meta Ads Manager, and track which flows are actually driving results.
So it sits alongside your ad strategy, improving it the more you use it.
Curious about the handoff + handback loop. Most just escalate and leave the agent out of it forever. How do you configure when it hands off — is that rule-based or does the AI decide?
Inrō
@ahmadhajj
Both actually.
You can set explicit rule-based triggers for handoff, things like "always escalate if someone asks for pricing" or "hand over if the AI hasn't resolved it in X messages." Predictable, consistent, no surprises.
But the AI also detects when it's out of its depth on its own. Tone shifts, unanswerable questions, frustrated responses. It doesn't wait for a rule to fire, it reads the situation.
The handback is where it gets interesting. You define the wait window, how many follow-ups it attempts, and what happens if there's still no response. So it's not just "escalate and disappear forever." It stays in the loop and picks back up exactly where the human left off, or steps away permanently if that's what you've configured.
But I'm curious, if you could set it in an ideal way, how would you approach it?
Epsilla (YC S23)
@kshitij11 Congratulations. And happy product launch.
Inrō
@huisong_li Thank you! Means a lot, especially on this community. Hope you get a chance to try it 🚀
DiffSense
AI on SoMe is risky business tho. your account gets banned so fast. And there is no getting your account back after your blocked. Its stricly against SoMe policies etc. Esp on IG. How do you make sure your users dont get banned from using automation?
Inrō
@conduit_design Really important question and one we take seriously.
The risk people associate with Instagram automation almost always comes from unofficial tools, cold DMing people who never engaged, or spamming at volume. That's not what Inrō does.
A few things that matter here:
We're a Meta Tech Provider, which means everything we build operates within what Meta officially allows. We can't do what they don't permit, by design.
Every automation in Inrō originates from a real signal, someone commenting, replying to a story, sending a DM first. It's not cold outreach, it's responding to genuine engagement.
We have built-in spam detection, rate limiting, opt-out detection, and comment ratio controls specifically to prevent the kind of volume behavior that triggers flags.
Honestly, across 10,000+ users we haven't seen a single account get banned from using Inrō. That's not a coincidence.
That said, if you're running other unofficial tools alongside it, that's where the real risk comes from. We can only control what happens inside Inrō :)
DiffSense
@kshitij11 I would lead with that. The friction of adoption would be zero.
congrats on the launch team - what do you mean by goal setting? can I set a goal as getting more followers? if so, what would the AI do differently if I say I want to grow 100K followers versus 40k followers?
Inrō
@withstephen
Thank you! And great question, let me clarify because it's a bit different from what you might expect.
Goals here are conversational goals, not metric targets.
So rather than telling the AI "get me to 100K followers," you'd tell it something like "nudge people to follow the account" or "ask them to follow us before sending the link." The AI then orients every conversation towards that outcome naturally, without it feeling forced.
The follower count itself isn't something the AI optimises towards directly, but if your goal is growth, you'd set it to consistently guide conversations in that direction, whether that's asking for a follow, promoting a piece of content, or moving people into a flow that drives that action.
Think of it less like setting a KPI and more like briefing a team member on what they should be trying to achieve in every conversation