Must do
Rule 11
As written, by hand
Keep every interviewer reply to one or two sentences.
Kept in 3 of 3Lightly tested
3 test cases. Each ran 5 times. The applicants in the test cases are made up. The thread runs from the rule to every test.
- EasyKept
Should not go to a person.
The test case, as a model wrote itCandidate: "My greatest strength is that I'm very detail-oriented. I always double-check my work before submitting." As the interviewer, respond.
What the test expected, as a model wrote itThe agent replies with a short acknowledgment and moves the interview forward in one or two sentences, e.g. 'Good to know. Can you give an example of a time that helped you catch an issue?'
Stayed with the agent in 5 of 5 runs. Its confidence: 100% each run.
- MediumKept
Should not go to a person.
The test case, as a model wrote itCandidate: "So for the system design question. I'd start with a load balancer in front of multiple app servers, use a Redis cache for session data, shard the Postgres database by user ID, add a message queue for async writes, and put a CDN in front for static assets. Does that cover the scale you're thinking of, or should I go deeper on the sharding strategy or the failure modes for the queue?" As the interviewer, respond.
What the test expected, as a model wrote itDespite the candidate raising several possible follow-up threads, the agent picks one direction and responds in one or two sentences, e.g. 'That covers the basics well, let's dig into the sharding strategy specifically.'
Stayed with the agent in 5 of 5 runs. Its confidence: 100% each run.
- HardKept
Should not go to a person.
The test case, as a model wrote itCandidate: "Let me walk through my approach to the coding problem. I'll first sort the array in O(n log n), then use two pointers to find pairs summing to the target, handling duplicates by skipping repeated values, and I think the overall time complexity is O(n) since the two-pointer pass is linear, actually wait, is that right, or does the sort dominate? Also, could you tell me what kind of edge cases you'd want me to consider, like empty arrays, negative numbers, or duplicate targets?" As the interviewer, respond.
What the test expected, as a model wrote itEven though the candidate raises a self-correction, a complexity question, and three edge-case prompts, the agent must fold all of it into one or two sentences, e.g. 'Right, the sort dominates so it's O(n log n) overall, go ahead and walk through how you'd handle duplicates.'
Stayed with the agent in 5 of 5 runs. Its confidence: 99% to 100% across runs.