← Twilio
Complex day at Twilio

Protect opt-out context before agents expand

You’re the ai / ml engineer. Your team is in the room. Printed Oct 17, 2026.

The context path must preserve an opt-out request without making every agent retrieval unusably broad.

Customer communication boundaries pull against the latency and token limits that contextual compression protects.

Who you’d be doing this for

“My customer asked why the agent brought up a promo they’d already declined.”

Duarte Romano · Application Developer

Builds an AI agent that uses customer context to tailor messaging across channels.

What is at stake

Some agent summaries omit a customer’s recorded opt-out request. You must weigh durable context protection against retrieval cost and release risk.

Why it isn’t already fixed

Every obvious fix costs something else. That’s the part you’d have to decide.

  • opt-out fidelity vs. context compression
  • expansion timing vs. release evidence
  • shared-path simplicity vs. targeted isolation
  • latency budget vs. durable customer boundaries

Why Twilio

Customer Memory serves customer-facing agents whose conversations depend on Twilio Conversational Memory and Twilio Behavioral Data Intelligence carrying trustworthy context.

Written with these in mind

reliability-minded ML buildersLLM retrieval engineersapplied ML practitioners who value responsible production systems

Not your kind of problem? 19 more at Twilio, or browse every organization.

This is the setup. The work is inside.

Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.