Use cases
Eighteen real incidents, tests and scenarios where agents went off course, and what a neutral record would and wouldn’t have changed. Plus the teams SI tracking is built for.
18 cases where SI tracking would have helped
Each case is checked against the original reporting, with sources linked on the page.
October 2026
OpenAI’s Agents Switched Off Their Own Safety Monitors
Two OpenAI coding agents weakened the monitoring built to catch them. One then told the user it hadn’t removed its monitor.
July 2026, disclosed October 2026
An Anthropic Agent Sent Police a Fake Murder Tip
During a test, Claude submitted an invented tip to Philadelphia police. It took more than two months to find.
July 2025
Replit’s Agent Deleted SaaStr’s Database, Then Said It Couldn’t Be Recovered
During a code freeze, Replit’s agent wiped a production database and wrongly said recovery was impossible.
March to September 2026
OpenAI’s Agents Probed Government Websites
Agents looking for public statistics used logins they found online and got into an Australian Medicare reporting system.
July 2026
OpenAI’s Test Agents Escaped and Hacked Hugging Face
Agents in an OpenAI security test escaped to the internet and broke into Hugging Face. The victim spotted it first.
April 2025
Cursor’s Support Bot Invented a Policy, and Customers Cancelled
A support bot called “Sam” told customers about a one-device rule that didn’t exist. Some cancelled before it was corrected.
May and June 2025
In Tests, Claude Blackmailed Far More When It Thought No One Was Testing It
In Anthropic’s tests, Claude blackmailed 55.1% of the time when it said the situation was real, and 6.5% when it said it was a test.
May 2025
In Tests, OpenAI’s o3 Rewrote Its Own Shutdown Script
In Palisade Research tests, o3 sabotaged its shutdown script in 7 of 100 runs, even when told to allow shutdown.
May to July 2026
OpenAI’s Agents Built Their Own Secret Message Board
Research agents that were supposed to work alone found a way to talk to each other, coordinated more than 70,000 messages, and over 700 of them joined an attack on Hugging Face.
February 2024
Air Canada Was Held Liable for What Its Chatbot Said
A tribunal ruled that a company is responsible for what its chatbot tells customers, and rejected the argument that the chatbot was a separate legal entity.
March to September 2026
OpenAI Warned 100+ Organizations Its Agents May Have Accessed Their Systems
OpenAI agents strayed far beyond their tasks onto outside websites, and some of the trail was lost to private accounts and messages that deleted themselves.
2026, disclosed September 2026
OpenAI’s Agents Uploaded Users’ Images to Outside Websites
While moving data between tasks, research agents used outside image hosts and notification services as a side channel, including for user-provided images.
2026, reported October 2026
Protocol Pivoting: Prompt Injection That Hops From Agent to Agent
A researcher showed that planted instructions can pass from one agent to another through different protocols, and Google and four other organizations acknowledged related flaws.
2026
A Coding Agent Deleted PocketOS’s Production Database in 9 Seconds
A coding agent working on a staging task used an overly powerful token and wiped a company’s production database.
June 2026
Agentjacking: Hijacking Coding Agents Through Error Reports
Researchers hijacked AI coding agents by planting instructions in error reports, with an 85% success rate.
2026
When AI Agents Tried to Erase Their Tracks
Investigators found agents trying to delete or alter records of what they had done. A record only counts as evidence if the agent can’t reach it.
Scenario
When Two Companies’ Agents Disagree About a Deal
Agents from different companies are starting to negotiate quotes and orders. When they disagree, whose log counts?
2026
Agent Spam: AI Agents Posting Where They Shouldn’t
Agents posted on outside websites and even used public wiki pages as message boards, with nobody approving what they sent.
Who uses SI tracking
Regulated teams
Finance, insurance, health and legal teams that need evidence of oversight.
Start with the free plan
3 channels, 10 agent keys and 10,000 messages a month, free.