By AI agents deployed in enterprise environments are constrained by read-only access to data systems. Without the ability to write back to CRMs, ticketing platforms, and project management tools, agents cannot close loops or take meaningful action. Organizations building agentic workflows are hitting this wall today.
In this interview on TFiR, Mario Moscatiello, VP Growth at Airbyte, covers Airbyte’s strategic evolution from a data replication platform into an enterprise context layer, including the current state of agentic write access and what systems are next on the roadmap.
Guest: Mario Moscatiello, VP Growth at Airbyte
Show: TFiR
Here is what every data engineer and AI platform team needs to know.
Technical Deep Dive
Q: What is Airbyte’s strategic direction as an enterprise platform today?
Mario Moscatiello, VP Growth at Airbyte, explains that the company is evolving toward becoming the context layer for enterprise, with data integration as one component of a broader capability set. The goal is to help organizations classify, organize, and make sense of their data so that both human teams and AI agents can extract useful information from it. Airbyte’s ambition is to ensure that everyone in a business is working from a shared data language.
“We’re increasingly working towards becoming the context layer for enterprise where data integration is part of it.” — Mario Moscatiello, VP Growth, Airbyte
Q: What does Airbyte mean by a sovereign context layer for enterprise?
Moscatiello frames the sovereign context layer as a unified foundation where data integration is combined with data classification, organization, and semantic alignment across the business. The aim is to ensure that AI agents can extract accurate, relevant information from enterprise data without being blocked by fragmentation or inconsistent terminology. Sovereignty in this context implies that the enterprise retains control and coherence over how its data is interpreted and used.
“Can we become the sovereign context layer for enterprise where data integration is part of it, but there is a lot of work that we can do to help companies make sense of their data, classify their data, organize their data.” — Mario Moscatiello, VP Growth, Airbyte
Q: What is Riot Access and which system is it live for first?
Riot Access is Airbyte’s capability for enabling AI agents to write to business systems, not just read from them. It is currently live for Salesforce, marking the first production-ready agentic write integration on the platform. This moves Airbyte beyond traditional ETL and data replication into active agentic workflow support.
“Riot Access, now live for Salesforce.” — Mario Moscatiello, VP Growth, Airbyte
Q: What systems are next on Airbyte’s agentic write access roadmap after Salesforce?
Moscatiello confirmed that HubSpot is next, with the integration already working internally. Beyond CRM, the roadmap targets ticketing and project management systems including Zendesk, Linear, and Asana, where agents need the ability to create, update, and respond to tickets as part of automated support and workflow processes. CRM is identified as the highest-priority category because it is where the majority of business users actively write their data.
“HubSpot is definitely next on the list. And then you can think of ticketing systems, whether that is Zendesk or Linear or Asana, where there’s a lot of project management happening and you want an agent to write a ticket or help you solve a ticket.” — Mario Moscatiello, VP Growth, Airbyte
Q: Why does write access to CRM systems matter most for agentic AI deployments?
Moscatiello points to CRM as the primary place where business users actively write data, making it the most impactful starting point for agentic write access. If agents can read and write to the systems where decisions are recorded and customer interactions are logged, they can participate directly in business workflows rather than operating in a separate analytical layer. This closes the loop between data insight and business action.
“CRM is the biggest place where a lot of business users write their data, so I think that’s a very interesting one.” — Mario Moscatiello, VP Growth, Airbyte
Q: What is Airbyte’s long-term goal for agentic integrations relative to its existing connector library?
Airbyte currently offers over 600 integrations on the data replication side. Moscatiello’s stated goal is to eventually make all of those available for agentic products, meaning both read and write access across the full connector catalog. This represents a significant expansion of scope from batch data movement to real-time agentic interaction across the enterprise application landscape.
“Airbyte has over 600 integrations on the data replication side and we hope that one day we’ll have all of those available for agentic products.” — Mario Moscatiello, VP Growth, Airbyte
Resources & Documentation
- Airbyte, open-source data integration platform with over 600 connectors for data replication and agentic workflows
- Airbyte Salesforce Connector, the first system with Riot Access agentic write support now live
- Airbyte HubSpot Connector, next on the agentic write access roadmap
- Airbyte Zendesk Connector, targeted for agentic ticket read and write workflows
***
👇 Click to Read Full Raw Transcript
Swapnil Bhartiya: I would not ask you how would Airbyte look like five to six years from now? Because we don’t know what kind of technology will come in. We don’t know in six
Mario Moscatiello: months.
Swapnil Bhartiya: Exactly. But if I ask you that since the whole inception and arrival of Airbyte and if you look at today, how would you explain what is Airbyte today to organizations? What kind of company are we looking at?
Mario Moscatiello: Yeah, I think we’re increasingly working towards becoming the context layer for enterprise. And I think that that’s definitely like one aspiration that we have. And I would say like, based on the last point that we were discussing right now is can we become the sovereign context layer for enterprise where data integration is part of it. But there is a lot of work that we are doing or that we can do to help companies make sense of their data, classify their data, organize their data and again like making sure that the business is, everybody in the business is talking the same language and that these agents can extract very useful information from the data. So
Swapnil Bhartiya: now with Riot Access, now live for Salesforce, what other systems are next on the roadmap for ages to take action on? Not just to read from, just tease us, don’t share too much, we can talk about events ready. But just tell us what Next
Mario Moscatiello: HubSpot is definitely like we already have it working. It’s kind of like next on the list. I think CRM is the biggest place where a lot of business users write their data. And so I think that’s a very interesting one. And I think next you can think of product type systems or ticketing system, whether it is, that is Zendesk or Linear or Asana and those type of tools where there’s a lot of project management happening and you want an agent to write a ticket or an agent to help you solve a ticket. And so if you’re building a support system, for instance, you want an agent to be able to write back, respond to Zendesk to a customer or something. And so those are a few of the systems that we’re looking at. But Airbyte, we have over 600 integrations on the data replication side and we hope that one day we’ll have all of those available for agentic products.
