What does it take for health plans to move from AI pilots to enterprise scale? ๐ฅ Join our webinar with @AHIPCoverage on Nov 17 to learn from leaders at @caresource, Cambia Health Solutions, & enGen.
UiPathers around the world recently celebrated Diwali. โจ We caught up with our People team to hear about their favorite traditions, memories, & what makes this time of year so special to them: https://t.co/mHRbXjgwzr
We see complex documents everywhere, as we work closely with customers to automate business processes. Industry benchmarks like ParseBench-2 from @llama_index are critical for innovation in enterprise-grade parsing and extraction. Check it out:
Today weโre introducing ParseBench-2 - our most ambitious document parsing benchmark to date.
It is the only benchmark that provides both extreme granularity into every single type of production parsing error, while also making sure that metric scores are highly aligned with human judgment. We do this by painstakingly assigning severity scores to 330+ error types, and tuning each metric to match the severity scores.
Existing benchmarks either use brittle deterministic metrics (e.g. OmniDocBench) or LLM-as-a-judge (ParseArena), which can help recognize equivalent representations but are coarse/stochastic/subject to bias by the prompt+model.
ParseBench-2 also contains:
โ 4.3k+ document pages (double from ParseBench-1).
โ An extra dimension (forms)
โ Much better ground-truth across all dimensions compared to ParseBench-1.
This is the next evolution of ParseBench, our hugely popular benchmark that has 50k+ monthly downloads, over 150+ OCR solutions benchmarked, and has been adopted by companies like NVIDIA, Cohere, Aleph Alpha, Perplexity, and others.
Alongside ParseBench-2, we are also releasing OCRia-1.5 - a new family of document parsing models that powers all our modes in LlamaParse. They represent a massive step up in capabilities from our latest release, and are state of the art in parsing complex tables, forms, charts, formatting, and assigning bounding boxes to complex layouts.
Come check out our blog post, technical report, and website.
Blog: https://t.co/TKbfCyTjht
Technical Report: https://t.co/eAu0s6ttA1
Website: https://t.co/PWczfhp0OX
If youโre interested in trying out our OCRia-1.5 capabilities, come sign up for LlamaParse: https://t.co/XYZmx5TFz8
How do you scale AI where governance is nonnegotiable? ๐ก๏ธ Pramod Dibble from @USAA & @AdamFamularo discuss putting AI & #automation to work in complex, highly regulated environments.
Watch The Path Forward:
๐ Apple: https://t.co/8mQCoqFmY6
๐ง Spotify: https://t.co/gMNVvknbVp
โถ๏ธ YouTube: https://t.co/viG7GasiBm
Testing, but make it lean. Advanced Composites is using UiPath Test Cloud to cover 400+ original tests with 250 streamlined cases, without adding a testing army: https://t.co/c0VMhTs5fV
.
The dark testing factory clocks in without you. Agents do the boring runs, you decide what ships. Colleen Bensen explains our new operating model in 30 seconds: https://t.co/Q5uNyGK9rx
Scaling AI in regulated industries requires governance, transparency, and accountability. โณ Pramod Dibble from USAA and our Adam Famularo discuss financial crime compliance, human oversight, and preparing people for a workplace shaped by AI agents.
Watch The Path Forward:
๐ Apple: https://t.co/atOy9UFH6O
๐ง Spotify: https://t.co/yIJEeemD6r
โถ๏ธ YouTube: https://t.co/3xOCZVlxhy
Your automation is overthinking it ๐ง Join Chibi Chakaravarthi and Kevin Bernstein at @aiDotEngineer Code Summit to learn when a quick judgment is enough, when a model should dig in, and when a human steps in: https://t.co/8sXmnCSA1B
#aiecodesummit#typesafe
Excited to partner with @Google Cloud on the Gemini for healthcare launch! ๐ Weโre integrating the UiPath MCP Server directly into Googleโs secure AI platform to automate and accelerate critical workflows - without compromising compliance.
Your HELOC process could be moving twice as fast. ๐ก Learn how AI-powered dashboards & agents help reduce cycle times & operating costs: https://t.co/5FHeEeq1zJ
A script that works on your machine isn't always ready for production. โ๏ธ Learn to make your code easier to troubleshoot, maintain, & deploy at #UiPathDevDives: https://t.co/2DpxvVyxzT
Testers, your job is safe. The grind is on notice๐งช This white paper explores the Dark Testing Factory and how testers can spend less time on brittle scripts, flaky reruns, and maintenance - and more time leading quality.
The hardest part of transformation is making it last. โณ We sat down with @Equifax to share how leaders can scale #automation, improve outcomes, & prepare people for whatโs next.
Watch The Path Forward:
๐ Apple: https://t.co/POFZS8N6yp
๐ง Spotify: https://t.co/NWSctUDuRU
โถ๏ธ YouTube: https://t.co/ftYRHTbP3R