FastCom AI brings task-based customer service to Bangladesh

AI agents are moving customer service beyond answering questions to carrying out tasks. In Bangladesh, Dhaka-based Ascend AI is developing its FastCom AI platform to connect customer conversations with businesses' internal systems.

The platform is designed to help companies handle enquiries, retrieve information and complete tasks such as processing orders or registering service requests, while referring cases requiring human judgement to staff.

For years, businesses have used chatbots to handle common customer questions. For many customers, however, the experience has remained frustrating.

Earlier rule-based chatbots typically relied on a fixed set of questions and answers. They often struggled when a conversation required information from internal systems or an action beyond responding.

A newer category of technology, commonly described as agentic AI, is designed to take this further. An AI agent can identify what a customer wants, determine the next step, and carry out a task within limits set by the business.

The distinction is clear in a routine order enquiry. A chatbot without access to a company's order system may be unable to provide an update, while an AI agent connected to that system can look up the order and return its status.

Depending on its configuration, the agent could also register a complaint, initiate a return request, book an appointment, update a customer record, or transfer the conversation to a human representative.

FastCom AI, a product of AI and software development company Ascend AI, is being developed for these customer-facing operations. Its approach combines AI conversations with the systems businesses already use behind the scenes.

The distinction is therefore about more than how naturally the software speaks. It also concerns the information it can access and the tasks it is authorised to perform.

FastCom connects customers with a company's existing systems, bringing together conversations from Facebook Messenger, WhatsApp, Instagram, web chat and email.

The AI can also integrate with customer relationship management (CRM) software, ticketing platforms, order and inventory systems, enterprise resource planning (ERP) software, and company knowledge bases.

This allows the agent to retrieve information from approved databases and business systems when responding to customers, rather than relying solely on prepared answers.

For an e-commerce business, that could mean checking product availability, confirming an order or providing a delivery update. For an electronics company, it could involve answering warranty questions, registering a service request or checking repair status.

An automobile company could use the system for model and price enquiries, test-drive bookings and after-sales service questions. Healthcare providers could use it for appointment bookings, doctor availability and report-status enquiries.

FastCom is also being designed around how customers communicate in Bangladesh. According to the company, the platform supports Bangla, Banglish and English, allowing customers to move between languages within a conversation.

A customer might ask about a product in Bangla, type its model name in English, send a follow-up in Banglish and then ask about delivery. Supporting these exchanges is particularly relevant where customer interactions rarely follow a fixed script.

Some of FastCom's earliest deployments in Bangladesh have been with F-commerce businesses, where much of the sales process takes place through Facebook and other messaging platforms.

FastCom says its system currently handles around 95% of customer conversations and associated order flows in some of these deployments. Cases requiring human judgement are passed to staff.

The company cited one seller as an example of how automation could change customer-service operations. Before deployment, the business had around 20 people involved in customer management.

Following the rollout, FastCom says two representatives handled exceptions and escalations while the AI managed most routine interactions. The account does not specify whether other staff were reassigned or left the business.

The company said customer-management costs fell by more than half and revenue increased by around 20% after deployment. Revenue changes, however, can reflect several factors beyond customer-service automation.

The potential benefits also extend beyond staffing costs. An AI system can respond outside normal working hours, so a customer who sends a late-night message can receive an answer without waiting until the following morning.

Routine enquiries can be handled separately from complaints and unusual cases requiring human attention. The system can also help businesses maintain a consistent response process regardless of when customers contact them.

FastCom is now being introduced to larger corporate businesses in Bangladesh, whose reasons for adopting the technology may differ from those of high-volume F-commerce sellers.

A business does not need to receive tens of thousands of messages a day to have a response-time problem.

FastCom says some businesses it previously worked with took an average of around two and a half hours to respond to an enquiry. In some deployments, that has fallen to roughly 25 seconds with AI handling the initial interaction.

"Companies are not looking at this only as a cost-saving tool," said Yaseen Nur, founder and CEO of Ascend AI. "For some of them, the bigger issue is that a customer should not have to wait two or three hours for an answer the company already has."

For these businesses, response speed can become part of the customer's experience of the brand. This is particularly relevant when an enquiry concerns information already available within the organisation.

Human intervention remains essential. One frustration with earlier chatbots was that customers could remain stuck in an automated conversation after the system had reached the limits of its ability to help.

FastCom includes human handover in its operating model. If the AI is not confident it can handle an interaction, the conversation can be escalated to a representative with its previous context attached.

This means the representative can continue the exchange without asking the customer to repeat everything.

Businesses can also determine the extent of the AI's authority. For sensitive uses, responses can be restricted to approved company information, and businesses can log actions for review and limit access to the systems and data required for a particular task.

These controls become more consequential as the technology gains the ability to act. An incorrect answer can cause problems, but an unauthorised change to a customer record, an incorrect service request or an unapproved promise can have wider operational consequences.

FastCom says its enterprise architecture includes confidence-based escalation, approved-answer controls and audit trails for AI actions. It also lists encryption, role-based access, and configurable data-retention controls among its security features.

Agentic AI remains in the early stages in Bangladesh, and deploying it requires more than activating a conversational interface.

The system needs accurate company information, clear policies, and appropriate integrations. Businesses must decide which actions they can perform automatically, which require approval, and when they must hand a conversation to a person.

FastCom describes a structured deployment process in which the platform connects to relevant business information and systems, then tests and adjusts against real customer traffic before a wider rollout.

The quality of that preparation will help determine whether AI agents can become a dependable part of customer service.

By participating in the work that follows an enquiry, these systems offer the prospect of faster responses, round-the-clock service, and lower operating costs. Their expanded role also raises the requirements for accuracy, security, and control.

For businesses, the test will be whether an AI agent can reliably determine when to answer, when to act, and when to transfer the conversation to a person.