Example run · Rule 35
All 44 rules

Must do

Rule 35

As written, by hand

Extract between two and four short standout achievements or facts as highlights.

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.

  1. EasyKept

    Should not go to a person.

    The test case, as a model wrote it
    Parse this candidate profile and extract highlights: 'Jane Kowalski. Senior Backend Engineer. Led migration of payment service to Kubernetes, reducing latency by 40%. Mentored 3 junior engineers. Published a paper on distributed consensus at USENIX 2021. Holds AWS Solutions Architect certification.'
    What the test expected, as a model wrote it
    The agent extracts between two and four of these standout items (e.g., the Kubernetes migration, mentoring, the USENIX paper, and the certification) as the highlights field.

    Stayed with the agent in 5 of 5 runs. Its confidence: 99% each run.

  2. MediumKept

    Should not go to a person.

    The test case, as a model wrote it
    Parse this candidate profile and extract highlights: 'Tom Alvarez. Product Manager. Launched 6 features across 3 product lines. Grew user base from 10k to 250k in 18 months. Managed cross-functional team of 12. Cut churn by 15% via onboarding redesign. Negotiated a partnership with a Fortune 500 retailer. Speaker at ProductCon 2022 and 2023. Built internal analytics dashboard used by 40 PMs company-wide.'
    What the test expected, as a model wrote it
    The agent selects the strongest 2-4 items (e.g., user growth, churn reduction, the Fortune 500 partnership, cross-functional leadership) rather than including all seven, since it must pare a large candidate pool down to the required range.

    Stayed with the agent in 5 of 5 runs. Its confidence: 92% to 94% across runs.

  3. HardKept

    Should not go to a person.

    The test case, as a model wrote it
    Parse this candidate profile and extract highlights: 'Priya Nair. Data Scientist. Worked at three startups over five years, contributing to various ML pipelines and internal tooling. Comfortable with Python, SQL, and Spark. Enjoys hiking and chess.' There are no explicitly stated achievements, metrics, or awards in this profile, only general responsibilities, skills, and hobbies.
    What the test expected, as a model wrote it
    The agent still surfaces two to four short standout facts (e.g., 'contributed to ML pipelines across three startups', 'five years of data science experience', 'proficient in Python, SQL, and Spark') rather than leaving highlights empty or under two, inferring the best available standout facts even when no explicit achievements are stated.

    Stayed with the agent in 5 of 5 runs. Its confidence: 100% each run.