Cases › operational mistake › LR-2026-0629
AT&T Andi chatbot refuses human handoff, customers caught in death loop
Preliminary Why: Publisher not yet named · subject to change
Status: no action reported
No source states: loss or records, developer and model, agent tool, could do, deployer, industry.
AT&T’s Andi chatbot handled a customer report that his dog had cut the line to his router and needed a technician. According to the source, the customer wanted to reach a human agent, but the chatbot kept piling up requests without registering the complaint and kept running in circles. The reporter describes this as a death loop, based on a published image gallery of the conversation.
What happened
No source tells the story step by step yet.
What was done
No source states an action or fix.
Risks
Primary63 incidents
Rising: 5 vs 2.2 a week
Sorted by rule from the case's fields; not yet read from the sources.
Controls
Not yet read for controls. Controls that mitigate the primary risk:
HarnessTool allow-list · Fail-closed defaults · Stop control
ApplicationHuman approval for high-impact actions · Change review and separation of duties · Least-privilege access for the agent · Production kept apart from test · Activity logs · Adversarial testing before deployment
Infrastructure / targetEvidence
No source states: a step-by-step account, when it happened, when it was found, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what set it off, what was done.
Show every field, with its source and grade
What happened
Impact
Context
Notes on gaps
The title says customers but the source describes one customer. No risk or control from the RK or control list is stated as held, failed or missing, so risks and links are empty. No fix or advice is reported, so remediations are empty.
LR-2026-0629 · version 1 · published 2026-11-01 after automatic checks; not yet checked field by field by a person · JSON