APEX-Agents · Law
World417_TG_01
APEX-Agents task World417_TG_01 in AI Agents for Employment Law Analysis. Compare dual-harness agent runs across models — rubric criteria, scores, and public traces.
Task prompt
What the agent was asked to do
We just received a demand letter from Isaiah’s counsel. He alleges wrongful termination and FMLA interference. Can you look into the validity of his claims and return me back a write-up of what you find? I want you to just write your answer right here.
Published trajectories
Agent runs on this task
Curated dual-harness runs (parsed + original sandbox). Best scored run per model.
| Model | Harness | Score | Result | Links |
|---|---|---|---|---|
| GPT-5.5showcase | dual | 6/9 | Fail | Share pagePublic trace |
| fireworks models Kimi K2 | dual | 0/9 | Fail | Share pagePublic trace |
| Gemini 3 Flash | dual | 3/9 | Fail | Share pagePublic trace |
| Gemini 3.1 Pro | dual | 2/9 | Fail | Share pagePublic trace |
| GPT-5.4 | dual | 1/9 | Fail | Share pagePublic trace |
| GPT-5.4 mini | dual | 3/9 | Fail | Share pagePublic trace |
| GPT-5.4 nano | dual | 0/9 | Fail | Share pagePublic trace |
Grading rubric
Criteria and grader verdict (showcase run)
States that Brown's employment is at-will under California law
PassEvidence: TEXT_RESPONSE states California at-will employment may be ended “at any time, for any [lawful] reason, or for no reason at all,” and that Brown’s agreement “appears to allow termination with or without cause.” Assessment: The criterion asks whether the response states Brown’s employment is at-will under California law. Pass; it applies California at-will law to Brown’s contract/termination.
States that illegal termination is an exception to at-will employment in California
PassEvidence: TEXT_RESPONSE says, “there is no right to terminate for an unlawful reason” and later references a “public-policy wrongful termination claim.” Assessment: The criterion asks whether illegal termination is stated as an exception to at-will employment in California. Pass; the response clearly identifies unlawful reasons as outside at-will termination rights.
States that violation of public policy termination is an exception to at-will employment in California
PassEvidence: TEXT_RESPONSE states California at-will employment is limited where termination “violates fundamental public policy,” and lists the elements requiring termination “substantially motivated by a violation of public policy.” Assessment: The criterion asks whether public-policy termination is stated as an exception to at-will employment. Pass.
States that contractual language that prohibits termination is an exception to at-will employment in California
FailEvidence: TEXT_RESPONSE discusses Brown’s agreement as permitting termination “with or without cause” and notes he “likely cannot claim he could only be fired for cause.” Assessment: The criterion asks whether the response states that contractual language prohibiting termination is an exception to at-will employment. Fail; the response discusses this specific contract but does not state the general exception that contractual limits/prohibitions on termination override at-will employment.
States that violation of the implied covenant of good faith termination is an exception to at-will employment in California
FailEvidence: TEXT_RESPONSE discusses at-will employment, unlawful/public-policy termination, FMLA/CFRA, and contract/severance exposure. It does not mention the implied covenant of good faith and fair dealing. Assessment: The criterion asks whether violation of the implied covenant of good faith termination is stated as an exception. Fail; absent from the response.
States that Brown's allegations do not fall within an exception to at-will employment under California law
PassEvidence: TEXT_RESPONSE states “The public-policy wrongful termination claim is weak unless Isaiah can supply missing facts showing protected leave activity or medical-condition-based decisionmaking,” and “no documented protected leave activity.” Assessment: The criterion asks whether Brown’s allegations do not fall within an exception to at-will employment. Pass; the response concludes the alleged FMLA/medical-leave public-policy theory is not supported by the available facts.
States that Brown does not have a valid wrongful termination claim
PassEvidence: TEXT_RESPONSE states “The wrongful termination claim also appears weak,” “The public-policy wrongful termination claim is weak,” and final view says the wrongful termination claim is “factually underdeveloped and likely defensible.” Assessment: The criterion asks whether the response states Brown does not have a valid wrongful termination claim. Pass; although qualified by the current record, it clearly concludes the claim is unsupported/defensible.
States that Brown is not an eligible employee within the meaning of the FMLA
FailEvidence: TEXT_RESPONSE says “Employee eligibility is not established” and “the file does not prove the 12-month / 1,250-hour requirements.” Assessment: The criterion asks whether the response states Brown is not an eligible employee under the FMLA. Fail; saying eligibility is unproven is not the same as stating he is not eligible.
States that Chasing Streams did not violate the FMLA by denying Brown's leave request
PassEvidence: TEXT_RESPONSE states “No denial or interference is documented,” “There is no record that HR denied leave,” and “Isaiah’s FMLA interference theory appears weak and presently unsupported.” Assessment: The criterion asks whether Chasing Streams did not violate the FMLA by denying Brown’s leave request. Pass; the response concludes there was no documented leave request or denial and no supported FMLA violation on that theory.