How One Consumer Electronics Brand Runs 10 AI Agents Across a Phone and a Pair of Earbuds
By Khoushik Reddy Ananth
- Industry: consumer electronics
- Business area: product experience
- Use case: one team of AI agents helps users with finance, health, career and lifestyle. Users speak to the agents through AI earbuds and tap through a smartphone.
People talk to their earbuds and tap on their phones. For an Indian consumer electronics brand that sells both smartphones and AI earbuds, that difference was the hard part of building AI into its products.
The brand wanted AI in both devices, so they could help people every day with their finances, health, career and lifestyle. The same help had to work through two very different inputs.
Today both devices run on one team of 10 agents. The brand sets the AI governance itself and knows the cost of every request before it runs, and a conversation that starts on the earbuds carries on in the phone app.
Why two devices made this a hard problem
Done the usual way, each device would have needed its own AI stack. A request started by voice on the earbuds would lose its context the moment the user picked up the phone. Voice commands could trigger actions with no check at all, which is an uncomfortable thought when the action changes someone's device or shares their data. And the brand's customers speak many Indian languages as well as English, so the help had to work in all of them.
The brand needed enterprise intelligence that sat above both devices: one set of agents, one set of rules and one memory, whichever device the user reached for.
What LeafCraft did: one AI agent management platform for both devices
LeafCraft gave the brand one platform for both devices, and each of its five pillars solved part of the problem.
Human-AI collaboration, with AI and people as one team
LeafCraft's team built 10 agents for the brand, covering finance, health, career and lifestyle, and gave each one a clear role. When a user asks for something, by voice on the earbuds or in the app, LeafCraft sends the request to the agent whose job it is.
Where an action needs a check, the agent waits for confirmation before it acts. This is how human-AI collaboration works across the two devices: the agent does the work, and the user stays in charge of anything that changes their device.
AI governance that gives every agent a job description
Every agent has a job description and its own level of autonomy, and the brand sets both. Safe actions that are easy to undo can run on their own. Anything that changes the device or the user's data must pass a check first.
That AI governance closed the risk of a voice command acting with no check at all.
AI cost control before a request runs
AI cost control runs on both devices, so the cost of every request is known and capped before it runs. The brand can grow usage without its AI bill growing out of sight.
One view, and AI agent management in one place
All 10 agents sit on one roster that serves both the earbuds and the phone. AI agent management happens in one place, with one set of agents and one set of rules, instead of a separate AI stack to build and maintain for each device.
Enterprise memory and shared institutional knowledge
Both devices share one memory. A conversation started on the earbuds carries on in the app, so the user never has to repeat themselves, in English or in any of the Indian languages the agents support.
The same memory keeps a record of each request. Over time that record becomes the brand's institutional knowledge of how its agents are used.
How a typical request moves through the team
Take one request, made on a morning walk.
- What the agent did: A user asks the earbuds, in Hindi, how much they spent on food delivery last month. The finance agent answers. The user then asks it to send that summary to a family member.
- Why it went to a person: Sharing personal data is an action that must pass a check, so the agent does not send it on its own. It asks the user to confirm.
- What the person did: When the user picks up the phone, the app shows the summary and the contact. The user removes one line they would rather keep private and confirms.
- How it was resolved: The agent sends the edited summary and confirms on the earbuds that it has gone.
- What LeafCraft recorded: The request, the agent that handled it, why the check was needed, what the user changed and the final action are all recorded on LeafCraft.
From knowledge retention to decision intelligence
Step five is the one the brand benefits from later. Because every request is recorded, knowledge retention happens as part of normal use.
Over time, this enterprise memory shows the brand which actions users change most before they confirm. That gives the brand decision intelligence it can act on, because it can tune each agent's role and limits from evidence.
The result: one governed team across both devices
The brand now has 10 governed agents on one roster. They help users with finance, health, career and lifestyle, and they work in English and most Indian languages, by voice or app, with one memory across both devices.
The brand did not have to build and maintain two separate AI systems.
About LeafCraft
LeafCraft is the platform for the Hybrid Intelligent Enterprise, where AI agents and people work as one team, each with a job description, under one set of rules. Enterprises run the agents they've built or bought (from SaaS or AI agent vendors), or build new ones on LeafCraft. It works with the workflow and automation tools they already use, whether built in house, bought as software or custom developed.
Human-AI collaboration on LeafCraft rests on four pillars:
- Governance: under LeafCraft's AI governance, every agent and person has a job description, a named owner, clear rules and approvals, and no one checks their own work.
- Cost control: with AI cost control, the cost of every task is known and capped before it runs.
- One view: enterprises see every agent, built or bought, alongside their people on one roster, which keeps AI agent management in one place.
- Enterprise memory: every decision and its reason is recorded and stays with the enterprise. Knowledge retention is built in, and the record becomes institutional knowledge that supports decision intelligence.
People and AI as one team. You own the rules, memory and budget.
If you are planning the move from AI tools to AI teammates, we would be glad to show you how it works. Book a conversation.
Frequently asked questions
What does Human-AI collaboration mean on a consumer device?
In this case study, the agents and the user share the work. The agents answer questions and prepare actions. The user confirms anything that changes their device or shares their data, as with the food delivery summary that was edited before it was sent.
How does AI governance work when the input is voice?
Every agent has a job description and a level of autonomy set by the brand. Safe actions that are easy to undo run on their own. Anything that changes the device or the user's data waits for a check, so a voice command cannot act unchecked.
What does an AI agent management platform do for a brand with two devices?
It puts every agent on one roster. The brand's 10 agents serve both the earbuds and the phone, so AI agent management happens in one place with one set of rules, and there is no second AI stack to build and maintain.
How does AI cost control work across the earbuds and the phone?
The cost of every request is known and capped before it runs, on both devices. The brand can grow usage without its AI bill growing out of sight.
How do the agents support institutional knowledge and knowledge retention?
Both devices share one memory, and LeafCraft records each request: the agent that handled it, why a check was needed, what the user changed and the final action. That record is the brand's institutional knowledge of how its agents are used.
Where does decision intelligence come in?
Over time, the record shows which actions users change most before they confirm. The brand uses that evidence to tune each agent's role and limits.
Which languages do the agents work in?
English and most Indian languages, by voice on the earbuds or by touch in the app. A conversation started on the earbuds carries on in the app.
Is this kind of enterprise intelligence only for consumer electronics?
No. LeafCraft is a horizontal platform, so the same five pillars apply in any industry and any process.
What is LeafCraft?
LeafCraft is an AI agent management platform for the Hybrid Intelligent Enterprise. AI agents and people work as one team, each with a job description, under one set of rules, and the enterprise owns the rules, memory and budget.
Does LeafCraft work with the agents and tools an enterprise already has?
Yes. Enterprises run the agents they've built or bought, from SaaS or AI agent vendors, or build new ones on LeafCraft. It works with the workflow and automation tools they already use, whether built in house, bought as software or custom developed.
What happens to the decisions agents and people make on LeafCraft?
Every decision and its reason is recorded and stays with the enterprise. That record is the enterprise's institutional knowledge, and it is what makes knowledge retention and decision intelligence possible.