Hello we are a small team looking to implement a Gupshup/Whatsapp bot.
We are wondering how long does it take for this kind of bot to setup and have in working order?
apologies if is not a technichal question, but we are not sure where else to ask.
You can ask Gupshup directly and they will be able to help better. From WhatsApp's perspective, once you create your account on Facebook Business Manager and add your WhatsApp number, it goes through an account review which typically takes around 2-3 days and once that is approved, you can start sending messages right away. However, some of these businesses like Gupshup have sandbox experiences at times that give you this experience within minutes without having to go through the entire flow.
There are two parts to the implementation. One is business registration with Whatsapp linked with vendor like Gupshup and the other is coding implementation.
These both can be achieved anywhere from one to two months depending on the use case.
Related
Prewarning: I am a noob with development, I started doing web design when I retired from the Marines about 3 years ago. I specialized in Intelligence and Tactics, so not a computer user during that career. Fast forward to Today:
I work as an Exchange admin and migration specialist with GoDaddy, I have been through several Webdesign courses and learned a decent foundation of html/css/php however JavaScript, Nodejs, Java, Python, C++, and C# are all still things I am working on.
My issue: My lead wants to have a bot built that essentially posts messages in the #general group (I learned how to do this and actually setup a nodejs server within my test hosting server # GD and have a Joke bot running in my slack WS). The tricky part that I have been scratching my brain on is how to use an web API that GD has to monitor our call que, hold times, and agents online. I need to figure out how to get the bot to post a message regarding certain triggers automatically(exp. Hold time exceeds 10mins). I can not figure out whether to use a webhook, eventListener, or a direct bot auth'd into the GD api like my joke bot that links to chuckNorris jokes.
I appreciate all the comments truly, I have thick skin and know that I am late to the game on development. I want to build this for the experience and to integrate with slack, my end goal would be more projects to eventually become a Dev within GD.
I have a few thoughts that might help you.
Regarding these holdtimes, agents online, and call queues, think of these as events. Whenever these events occur, they should fire a payload (HTTP request) to your service that then posts messages to slack. I think you might need a slack bot token for this.
Many APIs have this functionality under webhooks. You provide them the URL to the endpoint your developing and theres usually a toggle to tell them that you want to start accepting events.
To get going on your service/bot, I'd recommend starting with learning about what these webhook event payloads will look like in terms of structure so that you can parse it.
If you have more detailed questions feel free to comment or message. Happy to help. I've written a slack bot or two.
First my apologies if this is a dumb question, or has been asked before. I've been searching for a couple of days and can't find an answer. This usually means I'm asking a dumb question. ;-)
I have a rPi and touchscreen in my kitchen; it displays helpful things like appointments for next 7 days, weather next 7 days, news headlines, etc. It's a web app I wrote in Angular 7, and it queries a NodeJS v8 backend which I also wrote. This was a hobby project to learn Angular and Node.
The Node app performs all interactions with the outside world, using Google's Calendar API to get appointments, Yahoo Weather API, newsapi.org. All of these integrations followed the same pattern -- obtain some apikey token, and use that when invoking some API method to get the requested data in a JSON wad.
Now, I would like to also get the grocery list from my Echo. After reviewing Amazon's Alexa API documentation, it doesn't appear that I can do this the same way as the previous three integrations I did. Must I really write a "skill" for this, though I never intend to invoke it on the Echo?
And if so, could you point to a decent sample? None of the samples provided by Amazon utilize the Lists API.
Yes, you must create a skill in order to receive access_token. And then - Out of Session Interaction feature might be useful.
Can wit.ai, api.ai etc. generate its own conversations by training or are every conversation static structured by stories the "bot" owner created ?
Im in the search for a botting tool that can generate conversations based on what it has learned, and the more conversations it has the better it gets to replying to users, where human-like hour long conversations could be a possibility.
I've looked at wit.ai, api.ai and others like it, but they seem to be based upon stories which typically ends up into some command-like stuff, like ordering a pizza. Though they can be made to remember who they speak to and other entity information.
Do i have to structure a hundred of stories or is it possible to just make a base and make it learn from there, and perhaps add more stories in the future based upon old conversations to make it smarter. ?
There are many parts to the answer.
On the one hand, there is Mitsuku, which probably comes closest to what you are aspiring to. From what I understand, Mitsuku has been built over a long time using plenty of hand coded rules - a bit like the hundreds of stories you are talking about. There isn't a Mitsuku-as-a-service that I know of, at least not yet.
On the other hand, there are bot building frameworks like api.ai, wit.ai and others which are using machine learning to effectively do two main things - intent mapping (what is the subject the user is talking about) and entity extraction (mentions of proper nouns). In combination, it can be quite helpful for task oriented chatbots but not sufficient for the kind of truly conversational chatbots you are trying to build.
I would also encourage you to check out the following YouTube video, specifically the segment where the presenter talks about generative vs retrieval based chatbots.
https://youtu.be/SvV57fuL_M0?t=202
Also, api.ai also has something called "prebuilt domains", which have knowledge about a few domains. There is a "small talk" domain included, but if you look under the hood, it basically expects the bot programmer to fill out a questionnaire which goes from 0% to 100% complete based on usual expected questions.
You also ask about using history to make your bot smarter. If you are prepared to go through the chat logs, bot building frameworks such as API.AI allow you to start with something narrow and go on to make a pretty interesting bot by doing training (hard to explain, take a look at their interface). But this also means a) you are willing to spend a good amount of time improving the bot and b) you can actually drive enough traffic to your bot to field a wide range of questions.
Its my view that there is quite a lot of hype as to what chatbots can do. I think they are quite useful, but they are hardly conversational in the way humans think of conversations.
I am in the middle of the review process for Instagrams new API permissions. We have followed all of their guidelines and fall into one of their valid use cases. Unfortunately we have been denied now 3 times with the only explanation that we don't fall under a valid use case. I would be ok with this response if our software wasn't exactly what they say is a valid use case. So far I am unable to find anyway to contact them or talk about this issue. It would be a lot more helpful if we didn't get a blanket response when getting denied. Anyone else having these issues or have been able to contact their review team?
Perhaps this helps. I have tried two times but our app was declined. I will write the submission text one more time. I also want to go more into detail as the new FAQ says that Instagram expects a very detailed submision.
Cheers,
Christian
FAQ
My submission was rejected but it was a valid use case. What should I do?
A common reason for rejecting a submission is that we do not have enough information to make an assessment of your app. This can happen if your submission was too short, if it missed important information, if you did not provide a good screencast, your website is not working, etc. Before you submit for review again, make sure to provide a long and clear explanation of what your app does and how you use every permission. Make sure also to provide a video screencast and to follow all our Platform Policies.
What should I write in the submission?
The submission should be long enough for us to understand exactly what your app does and why you need the permissions you are asking for. If your submission is too short or does not explain all parts of your integration, then we may not be able to understand and approve your app. For example, your submission should explain what does your app or company do, which of the approved use cases your integration falls into, who will be using your app, how do your user authenticate with your app, how you use the API to power your integration, how does your product use the data acquired from Instagram, etc.
What should I show in the video screencast?
The video screencast is a very important part of a submission and cannot be omitted. Please make sure that the video clearly shows how your application works, including any Instagram login experience and the usage of every permission you are requesting. Since your app may still be in sandbox mode, you can use data from sandbox users to showcase the integration.
My company is working with multiple clients, should I submit one app per project?
No, we do not approve apps that are created for one-off projects (e.g. a hashtag campaign, an event, a website). You should use a single client_id across all your integrations.
Can I revoke a submission if I made a mistake?
You can't cancel a submission that is in progress. You will need to wait until the submission has been reviewed before you can start a new one.
I also have just been denied in the same way. I gave them 20minutes of video and demonstrated everything my app does. I wrote about each action possible in the context of use case 2 and I clearly stated which calls I was making. Short of supplying the source I am not sure what else to tell them.
Like a lot of businesses my employer is dealing with the new world of PCI compliance by avoiding the hard stuff and redirecting our customers to a third-party payment service. The process will entail the customer entering order details into our system but then being redirected to the merchant bank's payment service for the entry of those all important card details.
We wish to retain the services of some business that periodically fills in stages 1 and 2 of our order form with some dummy data, presses place order and sees that the URL it ends up at is in fact the one we're expecting, a bit like a bot or a web spider.
If it finds we've been clickjacked it would alert us by text message or twitter feed or whatever the cool kids are using these days.
Does anyone know of a service that performs this function?
No, I don't believe that there is a service like this. Usually companies with specific testing needs like this will use QuickTest Pro.
I'm still in the process of going through some suggestions and hammering out what exactly we're going to do but almost all the info I've gained has come from:
http://www.softwareqatest.com/index.html
A devastatingly useful site which provides more than answers to this functional testing scenario. There are a couple of Web-Based services which execute QA Functional Testing scripts against your site and send alerts and reports if the tests fail.
The two I had a quick look at were http://www.dotcom-monitor.com/ and http://www.watchmouse.com/en/
The latter service uses Badboy scripts in its tests so you can home brew them and then upload to their server for regular execution.