🧙🏼 European Parliament x Claude

Howdy, wizards.

Great news – ChatGPT’s Advanced Voice Mode is now available in Europe.

Here’s what’s brewing in AI today.

TOGETHER WITH WRITER

The fastest way to build AI apps

• Writer Framework: build Python apps with drag-and-drop UI

• API and SDKs to integrate into your codebase

• Intuitive no-code tools for business users

Start building with AI Studio

DARIO’S PICKS

1. European Parliament uses Claude to make their archives more accessible

When it comes to AI, the EU has been in the spotlight lately mostly for its restrictions, not innovation. However, Anthropic just surfaced a great case study on how the European Parliament is turning weeks of archival research into seconds; using Claude to make their archives more accessible to researchers, policymakers, educators, and the public.

Here’s the deets:

• European Parliament used Claude in Amazon Bedrock to create Ask the EP Archives (also known as Archibot), an AI assistant that helps unlock decades of democratic history.

• Archibot gives users instant, multilingual access to the 2.1 million official documents that have been produced and received by the Parliament all the way back to 1952.

• It summarises docs like like resolutions, positions, policies, and inter-institutional negotiations to help users understand the information quickly. It uses Retrieval augmented generation (RAG) to make it possible to query specific and accurate information (see my example in the screenshot below)

• Search time for documents has been reduced 80% since the launch, while use of the database is up 10x (!).

You can try Archibot yourself by going to this dashboard, selecting content-analysis in the dropdown on the upper right of the page, the clicking on “Ask the EP Archives” in the tab menu.

‎ Why it matters‎ ‎ It’s refreshing to see legacy and bureaucratic institutions finding ways to dramatically improve their customer experiences with gen AI. Solutions like this could be a great way to combat misinformation – users can easily query a database that only cites trustable sources. How many more archives in the world are there, that could increase their usage by 10x by implementing AI?

DARIO’S PICKS

2. 5 Real-world use cases of AI in HR

The HR industry uses AI to get faster internally, as well as integrates it into its products to reduce time-to-hire for companies.

Here’s 5 recent, real-world use cases of AI applied in recruitment:

• Upwork gives ChatGPT Enterprise access to all employees, with team members using it to build custom GPTs to streamline repetitive work, coding & QA, generating sales scripts, optmizing content for SEO, and more. They’re also integrating OpenAI’s GPT models into their customer-facing apps with UMA – Upwork’s Mindful AI. On one side, UMA helps companies hire more effectively by identifying the best matching talent (with sleek side-by-side comparisons) and a job post generator. On the other, it helps freelancers write more effective proposals directly on Upwork’s platform. SOURCE (AUGUST 2024)

• Indeed uses OpenAI's GPT models for contextual job matching in its 'Invite to Apply' feature, offering personalized job recommendations with detailed explanations as to why a candidate is a good fit. This implementation led to a 20% increase in started job applications and a 13% uplift in downstream hiring success. SOURCE (AUGUST 2024)

• LyRise, a recruitment platform connecting companies with AI experts from the Middle East and North Africa, uses Meta's Llama 2 and 3 to implement AI-driven candidate matching. By utilizing Llama's text summarization and RAG capabilities to condense job descriptions and resumes, LyRise reduces time-to-hire by 50%, while ensuring quality talent acquisition. SOURCE (AUGUST 2024)

• Tabiya, a company that helps young people find employment, has built a chatbot powered by Google’s Gemini that asks candidates questions, draws out skills and experiences and matches those to appropriate roles. SOURCE (SEPTEMBER 2024)

• Randstad, a global recruitment company, uses Gemini for Workspace across its organization for writing job ads in different languages with AI in Google Docs and translating speech when interacting with candidates in Google Meet. SOURCE (SEPTEMBER 2024)

‎ Why it matters‎ ‎ The most universal way in which AI is saving time in the recruitment industry is the initial job-candidate matching. Selecting suitable candidates for a job used to require a human sifting through hundreds of applications, which in many cases has been replaced by AI handling the initial screening process. It’s also being applied to make communication between employers and candidates more effective, by enabling easy translations between languages, and sharpening job posts & proposals for clarity and impact.

FROM OUR PARTNERS

Fall Into a New Language with Babbel

Start speaking a new language this fall with Babbel: the language learning app for real conversation. With award-winning lessons, immersive podcasts, addictive games, and bonus content, you can start speaking a new language in as little as three weeks. What’s brewing in AI readers can use this exclusive link to get up to 55% off today!

Try Babbel

THAT’S ALL FOLKS!

Affiliate disclosure: To cover the cost of my email software and the time I spend writing this newsletter, I sometimes link to products and other newsletters. Please assume these are affiliate links. If you choose to subscribe to a newsletter or buy a product through any of my links then THANK YOU – it will make it possible for me to continue to do this.