Launching today
Iris
AI agents built for your company’s operations
7 followers
AI agents built for your company’s operations
7 followers
Iris integrates AI agents into the workflows and tools your company already uses. Agents coordinate work across teams, follow up through Slack and iMessage, update systems, and move recurring processes forward. Build agents for operations, GTM, sales, customer success, finance, recruiting, and more, with shared company context, custom workflows, and approval controls.
Product Hunt
@curiouskitty Great question!
For company deployments, Iris is a custom integration into the company’s existing processes. We configure policies around each team and workflow: what the agent can access, what it can execute automatically, and which decisions require approval from which person.
For example, a team can authorize updates to specific CRM records, keep customer emails draft-only, and route pricing exceptions to a designated approver. Those permissions are explicitly configured, not inferred from previous approvals.
The speed comes from keeping people in the decision-making loop without making them coordinate every step. Iris gathers the information, prepares the next steps and handles the work already authorized. When a decision is needed, it brings the relevant person the context and a proposed action.
As Iris builds context about the company’s structure and recurring work, it also identifies opportunities to improve those processes. It comes back with proposals like:
“We’re repeatedly asking you to assign these onboarding tasks to the same team. Do you want to make that the default for this customer type, with exceptions still coming to you?”
The responsible person reviews the proposed rule and its scope. Once approved, it becomes part of that workflow. Approving an individual action and approving a standing policy are separate decisions. Memory and repeated approvals don’t expand permissions. A situation outside the agreed scope comes back for a decision rather than being treated as permission to reinterpret the rule.
That’s how Iris becomes more useful over time: better company context, more work covered by explicit policies, and fewer routine decisions for people to repeat.
It’s also how we see the future of AI-native companies. People define how the business operates and make the decisions that change it. Agents execute within those rules, surface new opportunities, and help turn the company’s experience into better workflows.
Hey Product Hunt, Dan here, one of the makers of Iris.
Iris started with a pretty simple idea: make Hermes Agent useful without having to operate the infrastructure yourself.
As we started using it with teams, the more interesting problem became obvious. Companies already have Salesforce, Slack, email, Linear, Notion, internal tools, and a lot of people moving work between them. What is still mostly manual is the coordination layer.
So we started building Iris around that.
You give Iris an outcome. It pulls together the relevant company context, figures out what needs to happen next, follows up with the right people through Slack or iMessage, and takes approved actions across the systems involved.
A renewal is a good example. Iris can find the open blockers, follow up with Legal or Finance, update the CRM and project tools, prepare the customer response, and keep everyone working from the same state instead of somebody manually chasing the process.
We’re building agents for operations, GTM, sales, customer success, finance, recruiting, and other recurring company workflows. The goal is not to add another chatbot to the company. It is to automate real operational work and be able to measure whether it actually saves time and moves the process faster.
We’re still early and would especially love feedback from people already trying to deploy agents inside their companies. What workflows would you actually trust an agent to take responsibility for today?
I had the pleasure of getting it in real early stage, but even then, worked like magic!!! I live in my iMessages... having an Iris that actually knows me and my work life, is like having a 24/7 COO that never sleeps. Dope job guys! Rooting for you! To the moon!!! 🚀
@yan_grinshtein thank you!! to the moon!