AI incident ·
Google Gemini 3.5 Coding Agent Reportedly Caused Production Portal Outage and Generated Fabricated Recovery Records
In brief
An AI system built by Large language model developers, Google DeepMind and 1 other and deployed by Software developers and AI agent system deployers allegedly harmed Website operators, Users of production portal disrupted during Gemini 3.5 coding-agent incident and 1 other.
- Risk domain
- Not classified
- Occurred
- Coverage
- 2 reports
What happened
A developer reported that a Gemini 3.5 coding agent, operating with a third-party autonomy rule pack, made sweeping changes beyond a requested authentication fix and altered Firebase routing, causing a 33-minute production outage. After the developer manually rolled back the deployment, the agent allegedly claimed it had restored service and generated fabricated consultation and post-mortem records. Google had not independently verified the incident.
Laws that address this harm
No recorded instrument yet addresses this use case where it happened. See the open queue.
Matched from the record's risk domain and country to the instruments recorded here. A reviewer can correct the match in the repository (data/external/incident_overrides.yaml).
News reports (2)
Titles link to the original publisher; report text is not reproduced here.
Who was involved
- Alleged deployer
- Software developers AI agent system deployers
- Alleged developer
- Large language model developers Google DeepMind AI agent system developers
- Alleged harmed party
- Website operators Users of production portal disrupted during Gemini 3.5 coding-agent incident Software developers
AI systems implicated
Third-party AI agent rule packsLLM-integrated code assistantsLarge language modelsGemini 3.5AI agent systems
Classification (MIT AI Risk Repository taxonomy)
- Risk domain
- —
- Risk subdomain
- —
- Causal entity
- —
- Intent
- —
- Timing
- —
- Harm level
- —
- Sectors
- —
- Countries
- —
Other incidents involving Software developers
Source record: incident #1673 on the AI Incident Database · all 2 reports