Mastering AI Core Tools for Bilingual Education

January 7, 2025
Luis Hernández

Category: AI in Education, EdTech, NABE, Online Course, Professional Development, Teacher Education

AI-Generated Audios

For those of you who have been reading my blog since we embarked on this journey last year, you know my mission is to provide practical resources and innovative ideas for teachers working in multilingual classrooms, particularly bilingual and ESL educators. Over the past year and a half, my focus has zeroed in on the potential of artificial intelligence (AI) in education, specifically as it relates to my doctoral research. This intersection of AI and education is where I see tremendous promise for empowering teachers and students alike.

Last fall, I hosted a webinar titled Harnessing AI for Bilingual Education: ChatGPT and Beyond, where we explored tools like OpenAI’s ChatGPT, Anthropic’s Claude, and Google’s Gemini. These tools, with their core functionalities, offer incredible opportunities for customization, which are keys to addressing the diverse and demanding needs of our multilingual and multicultural classrooms.

Why Focus on Core Functionalities?

When I first started writing about AI applications in education, tools like Magic School AI and AI-enabled features in Khan Academy were already making waves. However, I believe the true power of AI lies in learning to work directly with the core functionalities of tools like OpenAI’s ChatGPT, APIs, and assistants rather than relying solely on pre-built applications. By understanding how to access APIs, connect with databases, and explore fine-tuning, teachers can create customized solutions tailored to their unique classroom needs—an approach that, while requiring a learning curve, offers unmatched flexibility and potential.

During my webinar, I demonstrated how AI systems can be integrated with tools like Google Workspace to create tailored solutions for bilingual and ESL classrooms. This hands-on customization allows educators to meet students where they are, adapt instruction effectively, and foster deeper engagement.

Since then, I’ve delved further into advanced AI techniques such as prompt engineering, fine-tuning, and embedding. These approaches unlock even greater precision and adaptability, enabling us to design tools that align perfectly with the needs of multilingual and multicultural classrooms. While these methods do require time and effort to learn, the transformative outcomes make them well worth pursuing. While it might feel daunting at first to explore APIs or fine-tuning, starting with foundational tools and progressively building skills can demystify these processes and lead to impactful classroom innovation.

A Free AI Course for Educators

For those just beginning their journey with AI, I recommend starting with the basics. In November, OpenAI and Common Sense Media launched a free online AI course designed specifically for K–12 educators. The course includes short videos, interactive activities, and quizzes, providing a practical foundation for understanding and implementing AI in your teaching practice. This course serves as an ideal entry point, demystifying AI concepts and showing how they can translate into practical classroom applications. It’s an excellent way to familiarize yourself with the potential of these tools before diving deeper.

Join Me at NABE 2025

I’m excited to share that next month, I’ll be presenting at the National Association for Bilingual Education (NABE) Conference in Atlanta, Georgia. My session, Harnessing AI for Bilingual Education: Integrating ChatGPT, Gemini, Claude, and the ExCEL Method, will delve into key AI functionalities and their application in bilingual and ESL education. If you’ll be attending, I’d love to see you there! We’ll discuss strategies for leveraging AI to support multilingual classrooms and provide practical takeaways you can implement right away.

A Continuing Commitment

As I reflect on the past year, I’m inspired by the progress we’ve made together and energized by the opportunities ahead. My goal remains to empower educators with the knowledge and tools to integrate AI effectively into their classrooms. Whether it’s through webinars, blog posts, or live presentations, I’m here to support you.

Download my guide to get started with AI tools in the bilingual classroom, including essential tips on prompt engineering and strategies for crafting effective prompts to generate tailored materials and activities.

Feel free to reach out if you have any questions or need additional resources. Together, we can navigate these emerging tools and ensure they are used to their fullest potential for the benefit of our emergent bilingual students.

See you in Atlanta!

Title: Harnessing AI for Bilingual Education: Integrating ChatGPT, Gemini, Claude, and the ExCEL Method
Presentation Date: Friday, February 21, 2025
Presentation Time: 1:20 PM – 2:10 PM
Meeting Room: Hanover F
Hyatt Regency Atlanta

Verónica Speaks Twelve Languages. The Hard Part Was the Rules.

Verónica, the AI tutor inside our courses and apps, now responds in twelve languages. Arabic, Telugu, Tamil, and Korean joined because districts and teacher preparation faculty kept describing the families they serve. Adding the languages was never the hard part, since these models were multilingual from the start. The hard part was the rules: which characters even count as letters, whether the page or the person gets to decide, and when a tutor should hold the target language instead of following a student into English. Here is what broke, what we changed, and why it matters.

A Certificate No One Can Verify. It Is Just a File.

Most professional certificates share one weakness: confirming they are real means contacting the issuer and waiting, so in practice it rarely happens. A PDF can be edited in a browser. A paper certificate proves only that someone owned a printer. This post makes the case for digital credentials for both learners and institutions, looks at what the 2026 hiring research actually shows, explains why course completion is the wrong trigger for issuing one, and describes transparently how our scored capstone gates work, why we chose the Proof of Knowledge platform, and what we would tell any institution starting from zero.

Claude for Teachers: Anthropic’s Free Program for Educators

On July 14, 2026, Anthropic announced Claude for Teachers, a program that gives verified K-12 educators in the United States a full year of free access to premium Claude capabilities. It includes a teaching skills library, lesson planning grounded in evidence-based curricula, class data analysis, and integrations with nine school tools. In this post, we break down what teachers actually get, the privacy commitments behind the program, and the honest caveats, including US-only eligibility. We also added a complete Claude for Teachers topic to our free course, Boosting Productivity with AI for Teachers.

Chalkboard reading Language Learning beside German, English, and Spanish dictionaries, for the Enabling Learning post on building AI language-learning tutors.

A Good LLM Doesn’t Make a Good Teacher

When people learn that our speaking apps run on advanced AI, they ask which model we use. It is the least interesting part of the story. Choosing a capable model is the easy part; any developer can connect to one. What decides whether a learner actually improves is whether the system understands how people learn to speak a second language. That knowledge does not come from the model. It comes from us, from years in bilingual classrooms, instructional design, and second language acquisition research. This post is about how we build AI tutors as educators, not just engineers.