Use cases › IT / internal ops

UNACEM: how the agent works and how to build one like it

Summary: UNACEM, a cement company, uses a WhatsApp logistics agent that cut driver wait times by up to 40%; a safety (EHS) agent is next, per the source.

Source: https://www.ibm.com/new/product-blog/how-an-industrial-powerhouse-unacem-modernized-operations-with-agentic-ai source read via search extract

Why this use case works

Drivers and field workers live on their phones, not in enterprise software. Putting the agent on WhatsApp brings scheduling and status updates to them, and the same channel can then carry other workflows such as safety reporting. (Our analysis.)

Agent pattern: Internal ops agent

An internal-ops agent living in a chat tool employees already use (Slack, Teams, WhatsApp), with read access to documentation and write access limited to creating tickets or records. Start read-only and widen permissions as accuracy is proven.

How a smaller team could replicate it

Distributors, construction suppliers and fleets can use the WhatsApp Business API with an agent that answers loading slots, queue position and documents needed, connected to their dispatch or yard system. (Our analysis, not a claim made by the source.)

Want a rough business case first? Try the AI agent ROI calculator, or ask us to scope it.

Risks and guardrails

Risks: drivers with poor connectivity, messages in mixed languages, and stale yard data. Guardrails: short message formats, a fallback phone number, and status data refreshed from the dispatch system in near real time. (Our analysis.)

What to measure

Driver wait time, gate turnaround, messages handled without dispatcher involvement, and adoption among drivers.

Related IT / internal ops deployments

Part of the AgentStack Atlas catalog of 52 sourced agentic AI deployments. Spotted an error? Email agentstackatlas@mail.grokbot.com.