A telecom chatbot that cannot see the customer's bill or the outage on their street will walk them through a router reset. We build care that answers from the account, the network and the contract, and knows which requests are too risky to automate.
All Telecoms →
Telecom contact clusters around a few themes: a bill higher than expected, roaming or usage charges, slow or no service, a device or contract question, moving home, and leaving. Each needs live data. Bill questions need the itemised bill from the BSS. Service questions need network status for the customer’s location. Contract questions need the plan and the contract summary the customer was given.
Two parts of care need special treatment. SIM swaps and number port-outs are the main route for account takeover fraud, so they always require strong authentication and a person. And leaving has to be easy: European rules under the Electronic Communications Code, and Ofcom rules in the UK, govern switching and contract terms. A care system that hides the exit to protect churn numbers is a regulatory problem, not a retention strategy.
app, web chat, messaging or call
SIM, porting, vulnerability, complaint
account, plan and location in the BSS
bill, usage, outage, plan question
interaction and any credit logged in CRM
high-risk and sensitive requests
When it is integrated with billing, CRM and network status, it can explain bills, trace roaming and usage charges, confirm outages for a customer's location, answer plan and contract questions and apply small credits within rules. Without those integrations, it can only repeat help articles, which is why many telecom chatbots frustrate customers.
Predictive models can identify customers likely to leave so that service problems are fixed and relevant offers are made earlier. What it should not do is make leaving harder; switching and contract rules in the EU and UK protect the customer's right to go. Our systems use churn signals to inform agents and offers, never to obstruct.
The bot does not perform SIM swaps, eSIM transfers or number port-outs. Those requests are detected early in the conversation and passed to a human agent after strong authentication. Account takeover through social engineering is a known attack on telecom care, and the safest automation for it is none.
Yes. The same grounding powers an agent assistant that summarises the account, the bill and recent contacts and suggests a reply, which the agent edits. Many operators start there, because it improves handling quality without changing what the customer sees.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Start with a sample of real contacts and your BSS. We will map which ones can be resolved safely.
30-minute technical call · no deck