Re:Show HN: Airbyte Agents – context for agents across multi...
by jeanlaf on Tuesday May 05, 2026 @08:45PM
(#48030760)
Thanks swyx! We'd love to do that session "data engineering for ai engineers", will make you an intro to the right person in the team.
Re:Show HN: Airbyte Agents – context for agents across multi...
by swyx on Wednesday May 06, 2026 @10:18PM
(#48044642)
saw your email, will get back!
Re:Show HN: Airbyte Agents – context for agents across multi...
by aaronsteers on Tuesday May 05, 2026 @08:46PM
(#48030773)
Hey, swyx! Great seeing you here.
> airbyte agents could serve as a form of MCP gateway
Exactly! And a single set of tools for agents to access both realtime (direct reads/writes) as well as cached (Context Store), bringing hopefully the best access path for each different use case.
> would love a "data engineering for ai engineers" type braindump ... at AIE
Great idea - we have a booth at AIE, and we'll submit there for a talk. Mario will reach out to you about this. :)
Re:Show HN: Airbyte Agents – context for agents across multi...
by sails on Wednesday May 06, 2026 @10:51AM
(#48036958)
I think this is right ( a big gap ) but I don’t think data companies even now what the right shape is for AI.
It’s definitely not old school ETL + dbt + BI tool, it might be something like this, but it’s very early
Re:Show HN: Airbyte Agents – context for agents across multi...
by aaronsteers on Thursday May 07, 2026 @12:29PM
(#48051365)
Agreed 100% - we're still super early in this journey, gathering data from our own usage and from our customers' feedback.
hmm so airbyte agents could serve as a form of MCP gateway, or a key building block of an MCP gateway, which btw is how anthropic uses mcp themselves for all their internal apps https://www.youtube.com/watch?v=CD6R4Wf3jnY&t=1s&pp=0gcJCd4K...
i think my most sad/interesting observation about ai engineers is that many ai apps are super data hungry, but many dont have the necessary data engineering background to even know they need an airbyte or what tradeoffs to make in an etl pipeline. would love a "data engineering for ai engineers" type braindump session from someone from airbyte at AIE (https://ai.engineer/cfp )