I joined the keynote session at the Google Cloud Summit 2019, where I presented AutoML Tables, for 3000+ in Amsterdam. In this demo, I showcase how developers can create custom machine learning models, based on structured historial data in BigQuery. “Predicting the Waiting Time at the Airport”.
Together with Matt & Christiaan I spoke at GOTO Conference. We presented the Google Tulip, April Fools case. The code that I wrote; is actually available online: https://github.com/GoogleCloudPlatform/tulip - for real!
At the Google Cloud Summit event in Paris, I presented the Video Intelligence API for 3000+ IT professionals:
I recently spoke at the Schiphol Developers Group about Machine Learning and Auto ML.
At the Google Cloud Next event in London, I presented my customer care solution during the demo derby!
I’ve presented in Eindhoven during Digital Wednesday about Dialogflow and Google Assistant:
What I like most about Dialogflow, (the tool to create Chatbots and Smart Assistants / Google Assistant apps), is that you can maintain your conversations within the Dialogflow UI. Many users write their complete FAQ content in intents and responses. You no longer need a developer to tweak your conversations or deploy your agent which makes it very scalable for large organizations. It’s also possible to load data from external systems. In that case, you are hosting parts of the conversation elsewhere. You could store these parts in language files or databases. Some organizations prefer to write the full conversation in the Dialogflow UI. That way your copywriters can maintain the full conversation.
It’s good to know that it is possible to use templates and conditionals within the Dialogflow UI. The trick here, is to make use of the custom payload response setting, which you can find in the Intent > Responses section.
Let’s have a look into how you can create custom dynamic Welcome messages for your Google Assistant with Dialogflow and Actions on Google.
When building Google Assistant apps (actions) with Dialogflow, you likely will have to write some logics. The most common way in developing this logics layer is by using a webhook and a Cloud Function. The webhook requires a URL. So technically you can use any web server and program language you like, Cloud Functions are just easy.