![]() Dialogflow CX can implement virtual agents, like: chatbots, voice bots, phone gateways and can support multiple channels in over 50 different languages. To add your own data sources, click on the Data tab in the right hand panel of your chatbot.In this codelab, you'll learn how to build a retail chatbot with Dialogflow CX, a Conversational AI Platform (CAIP) for building conversational UIs. Or if you're building a bot that can answer employee questions about a company-specific event, like a webinar or a retreat. You can imagine how handy this is if you're building a customer support bot and you need it to respond to customers with approved FAQs, for example. It's a bit like feeding the AI your own knowledge to tailor its responses. That means you can upload any personal or internal company documentation to your chatbot, so that it only generates answers from that specific source. But one of the best things about using Interfaces to do that is that you can add your own data sources to limit your chatbot's answers to pre-approved or specific content. You now know the basics of setting up a general AI chatbot. You can always go back and edit it later, but your bot is now ready to share! Create an AI chatbot with your own data sources Once you're happy with the results, remember to save any changes where necessary. Here you can adjust your page options and personalize the page name, meta title, and URL for your bot. Once you're happy with your bot's performance, go back to your interface page and click on the settings icon in the left-hand panel. Remember, the chatbot isn't all-knowing, so it may need clearer instructions. Just go back to your directive and tweak the instructions. If you've still not gotten the results you're after by adjusting the creativity levels, there may be something missing or too vague in your prompt. It'll depend on what you're after, so play around with it. ![]() In turn, if you dial up the setting, you could get more creative and "human-sounding" results. For example, a lower temperature (below 0.7) will churn out more predictable and "generalistic" results than a higher setting. This can help adjust the output you're getting. Play with the temperature (creativity setting)īefore you start reworking your directive to get better results, you should first try playing around with the creativity temperature. If you're not happy with the results, you can do two things:ġ. Once you're happy with your directive, copy and paste it into the Directive field. I recommend writing out the directive on a separate document first, so you can go back and tweak things as you see fit. Consider each sentence of the content and offer feedback anywhere it’s needed." Be specific, and include examples of what should be revised and some suggestions for how to revise. You strike the perfect balance between persuasion and education."Īnd then finally, you might add what the chatbot's goal is, such as: " Your task: Read the content and respond with honest and direct feedback about what could be improved based on the above list. You can also pepper in examples of the kind of writing you want it to emulate.įor better results, you should specify things like the chatbot's role: "You are a very skilled editor "īut you can also add other directives, like: "You know when to dole out the wit and when to be informative. Because this is like the "prompt" you'd give ChatGPT as a user, it's important to remember that the more detailed and clear your instructions are, the better the chatbot will respond.įor our editor bot, we'll include detailed directions on style, tone, grammar preferences, word count, and Zapier's blog voice.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |