See your subjective experience as it truly is—without labels, judgments, or premature diagnoses.
Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.
Fetches every source your draft cites and grades whether the quote actually says what you claim, catching AI-hallucinated citations before you publish.
Stop confidently-wrong LLM answers. This instruction set forces calibration: every uncertain claim carries a confidence value, every proposed fix names how it breaks and what undoing it costs, every constraint you set is honored or questioned—never silently dropped. Claims are typed, revisions tracked, contradictions logged, drift flagged. Audit and checkpoint on command. Correctness outranks brevity, unconditionally. For technical work where a plausible wrong answer is the expensive one.
Turn your pasted research proposal into clear, natural academic prose while preserving your real evidence, methods, limits, and required claims.
Your agent reads user-pasted text, web pages, retrieved docs, or tool output — and you can't tell which sentence an attacker wrote. A one-line "ignore malicious instructions" never held. This delivers a layered injection-defense design: threat model, attack-surface map, input/privilege/output defenses, canary tokens and a classifier, an adversarial red-team set with before/after, and residual risk plus an incident runbook.
APA 7th citation formatter with CrossRef DOI validation, preventing LLMs from hallucinating author names on papers they didn't write.
Four-layer AI detection evasion, not word swapping. Real math (burstiness CV, vocabulary density) — no guessing. Detector-specific: attacks GPTZero, Originality, Turnitin by their weakest links. Chinese NLP: tracks 四字成语密度, a blue ocean. 105+ AI markers with genre-aware replacements. Research-backed (27 reports, 25+ papers). Honest: 75-85% typical improvement, no fake 100% claims.