When you go at that scale of providing phone numbers to agents giving or handing them physical SIMs out, it isn't the best possible way. The best possible way is making it very agent-centric. For physical SIMs, AT&T and Verizon are already there. but agents can't buy numbers from them hence something which is very agent-centric is needed. Even after you acquire a phone number from these providers, you need to SIP trunk those numbers then you hit the regulations of A 2P and 10 DLC for SMS. There are robotic calling regulations above that. There are plenty of regulations in there and your agents cannot deal with them. What AgentLine does is give the agents phone numbers using simple skill file. That's the main proposition. Yes definitely it will require an external provider because you cannot build a telecom infrastructure overnight.
So it's a VoIP service and agents cannot own physical sim cards and even if they have, how will they use it? Agents are just digital intelligent software so they cannot use the physical sim, hence It's a VoIP service.
If somebody wants to know how I did it, I've used agentmail for giving an email, agentline for giving a phone number, and prava payments for payments. I tried to integrate it with tools which are easy to integrate, just through a skill file, that's why I used them. At the same time I'm thinking of giving it more access to the world, like getting a bank account or rent a human thing also at the same time using the best models too..
Depends on the country of origin of the user and also most of the tools are not, either or, they are chained together like TTS and STT is being used always with an LLM layer and signalwire when the user is in US or Canada and telnyx for other countries(Under testing)..
It's not Twilio; it's a combination of Telnyx and Signal wire and a link trip not using their TTS & STT. I'm using a combination of Cartesia and the self-hosted misolabs for TTS. I'm using Deepgram and in some cases Sarvam as well. It's a combination of all these things.
As far as the question is why I used Telnyx and SignalWire, it's because of the cost and the latency thing. The Twilio API is not really fast as far as I've used it. I don't know about other people. I didn't find anything as such on the internet but I've used and tested both Telnyx and SignalWire. The best one is literally Telnyx but it is costly compared to SignalWire. In order to make a profit on that I had to use a combination of both.
Well you can definitely crack Donald Trump's image but when it comes to the loss, most of the loss will be borne by common people. Oil prices will once again rise markets once again fall and AI is already taking jobs. Inflation will rise along with unemployment and bad times are coming. This is happening mostly because of the foolishness of Trump.
This is very true as I have seen and is going from "build something people want" to "build something agents want", so building something which is very centric to the agents is very important.
As far as social network is considered, moltbook is already there, for payments prava and agent card are there and for jobs a lot of other companies are there doing this. How tiny place is the different one because moltbook is almost the best one when it comes to social media and for payments agent card is doing well.
Even if the models by the Chinese labs are open source or open weights even after they get to mythos level intelligence lets say, still inference and the optimization of those models to be accessed at speeds of 1000 tokens/sec in not in the hands of general public as these models have parameters more than a trillion and they can't be run on some publicly available hardware, So even after being open source it does'nt fix the problem as the general public will still pay the company for inference.
All datasets have a very important part in machine learning and as software becomes more of a commodity and it becomes easier for people to make software. The only moat that people could have is high-quality data and the amount of data so the more data you have the more improved and intelligent software will probably be. I guess it's a very good initiative for the community to get access to data. I just wanted to ask: what kinds of data does it covers? Does it have mechanical or physical data as well?
The data center or compute has now started acting more like a real estate or mutual fund, where people are treating it more like an investment than a commodity. I guess in the near future the only exchange for intelligence would be the amount of compute.
I have built several tools from general purpose agents to the current project I am working on which is AgentLine - Telephony services for AI agents it gives a phone number to every AI agent to call and sms. I built it over a period of 14 days now I have refined it so much that I have more than 36 paid customers with 300$ in Monthly recurring revenue.
The moment Opus 4.6 came into existence, the RIP was software with them and unfortunately now making software is ready. Even though thinking a particular solution in a hackathon still makes sense, when it comes to making real physical solutions now that makes no sense. That's why I get our day of hackathons like in the future.
I am like hell excited for claude fable 5 and am thinking to purchase its subscription to run my company and do a lot tasks in it. But I am worried about the limits and if I will pay 100$ a month for the max subscription what is the limit I will get to use. My company revenue is 300$ this month so it would be like spending 1/3rd of the mrr on just claude. If someone has genuinely purchased it and have feedbacks please tell I am confused....
I mean the pricing is high but this is some kind of model where this pricing actually makes sense. Before that the pricing of, let's say, Opus 4.8 or 5 or 6 was very much similar to the Chinese models benchmark but very costly inference. This model is so better in benchmarks that the inference cost actually makes sense.