Just checking now: recent runs tau3[1] was at 96% and toolathlon[2] was at 90%

[1] https://www.induction.ai/docs/benchmarks/tau3 [2] https://www.induction.ai/docs/benchmarks/toolathlon

Some of the tools we use: https://www.induction.ai/docs/context-management

I recently started at Ario where we are building an app for parents that uses AI to make things easier. We are targeting saving them one hour every day. Previously, I co-founded Taskrabbit. That was somewhat similar but now it's time to get LLMs in on the action! It's in the app store, but still early in the game, so we are looking for engineers to build it out. We are using Python and React Native.

To learn more: brian at heyario.com

We can hardly believe it’s been almost four years since our original HN launch (https://news.ycombinator.com/item?id=25917403). What started as a small project has grown way beyond what we imagined, with over 170,000 deployments and 7,000 companies using Airbyte daily.

When we started Airbyte, our mission was simple (though not easy): to solve data movement once and for all. Today feels like a big step toward that goal with the release of Airbyte 1.0 (https://airbyte.com/v1). Reaching this milestone wasn’t a solo effort. It’s taken an incredible amount of work from the whole community and the feedback we’ve received from many of you along the way. We had three goals to reach 1.0: - Broad deployments to cover all major use cases, supported by over 1,200 community contributions. - Reliability and performance improvements (this has been a huge focus for the past year). - Making sure Airbyte fits with your existing production workflow – from Python scripts to Terraform, API, and UI interfaces.

It’s been quite the journey, and we’re excited to say we’ve hit those marks!

But there’s actually more to Airbyte 1.0! - An AI Assistant to help you build connectors in minutes. Just give it the API docs, and you’re good to go. We’ve also added support for GraphQL APIs to our Connector Builder. - The Connector Marketplace: You can now easily contribute connectors or make changes directly from the no-code/low-code builder. Every connector in the marketplace is editable, and we’ve added usage and confidence scores to help gauge reliability. - Airbyte Self-Managed Enterprise generally available: it comes with everything you get from the open-source version, plus enterprise-level features like premium support with SLA, SSO, RBAC, multiple workspaces, advanced observability, and enterprise connectors for Netsuite, Workday, Oracle, and more. - Airbyte can now power your RAG / GenAI workflows without limitations, through its support of unstructured data sources, vector databases, and new mapping capabilities. It also converts structured and unstructured data into documents for chunking, along with embedding support for Cohere and OpenAI.

There’s a lot more coming, and we’d love to hear your thoughts! If you’re curious, check out our launch keynote (https://airbyte.com/v1) and let us know what you think – are there features we could improve? Areas we should explore next? We’re all ears.

Thanks for being part of this journey!

Comments URL: https://news.ycombinator.com/item?id=41637452

Points: 58

# Comments: 14

I like how the article notes that the stuff we were talking about with Reverse ETL (mostly activating your data in SaaS systems like Salesforce, Zendesk, etc) is one important part of Publishing. But we are also seeing traditional use cases like file uploads and new fancy stuff like vector databases.

I built a system for TaskRabbit that scraped all the IKEA products from a variety of sources and ran algorithms to determine their category and predict how long they would take to be assembled. Then there was a Mechanical Turk sort of system for human input. When combined with real-world feedback from the Taskers, it was pretty good.

For better or worse, I've personally been through the entire catalog multiple times.

At Grouparoo, this is a primary use case. We have a UI that engineers use locally. This helps gets things right. It outputs a JSON configuration that is checked in. When that is deployed, it does all the syncing.

* Combine data from different sources to define a model. We'v seen using Postgres as a source of truth and supplementing with Snowflake data, for example.

* Add tags to contacts in mailchimp, zendesk or make lists of them in customer.io, Pardot, etc based on segmentation. I believe Hightouch Audiences is more like a filter.

* Full workflow with branches, PRs, test suite in a repo. I saw Hightouch added git syncing to a known branch yesterday and it looks cool, but it's not the full workflow yet.

I'm certainly trying to keep it in the friendly-competition area, especially on this thread :-)

A few differences: git developer workflow focused (branches, CI, PRs, etc), ability to self host, segmentation in destinations (tagging people in mailchimp based on rules, for example)

https://www.grouparoo.com

Specifically, open source approaches to the modern data stack where the trend is picking the right tools for the job that revolve around the warehouse central data store.

The pieces discussed were around getting data in (Snowplow events, Meltano ELT), transforming it (dbt), reporting (Superset), getting it back into tools (Grouparoo Reverse ETL), and orchestrating things (Dagster).

https://www.opensourcedatastack.com

Comments URL: https://news.ycombinator.com/item?id=28676427

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=28078135

Points: 2

# Comments: 0