Review a bounded paper corpus for papers relevant to a topic. Use when Codex needs to scan all or most papers from one or more named conferences, journals, proceedings sites, or other bounded sources, prove corpus coverage, rank papers by semantic relevance, inspect the source structure before choosing tooling, and shard large reviews across sub-agents without losing auditability.
Monitor selected research sources over time and triage newly relevant papers. Use when Codex needs to repeatedly check one or more feeds, venues, journals, archives, or alerts for new papers on a topic, detect what is newly worth attention since the last pass, de-duplicate against previously seen items, rank what deserves immediate reading, and report the watch outcome with an explicit watch boundary and time window.
Map the interaction structure of an application, website, or product flow. Use when Codex needs to inspect a product surface, enumerate screens or states, build a route or page manifest, map the main user flows for important tasks, identify decision points, loops, dead ends, and hidden branches, and report how the interaction model actually works before deeper usability evaluation or redesign work.
Design semi-structured research interview guides for product, UX, and usability work. Use when Codex needs to turn research goals into a practical interview plan, define who should be interviewed and why, structure a session into warm-up, core questions, and probes, reduce bias in wording and moderation, and produce a guide that a researcher can actually use in the room.
Audit the usability of an existing product experience and produce evidence-backed findings. Use when Codex needs to evaluate a website, app, flow, or prototype for usability issues, inspect important tasks through a user-centered lens, apply explicit heuristics or evaluation criteria, capture concrete evidence, assign severity and task impact, and report prioritized findings that can guide design or product decisions.
Deeply analyze one or a few papers and turn them into reusable research notes. Use when Codex needs to read a paper beyond surface summary, extract the problem, claims, method, evidence, limitations, and relevance to a research goal, compare a small set of papers directly, or produce an auditable critique grounded in what the paper actually says.
Expand from one or more seed papers to find relevant prior work, follow-up work, and adjacent papers around a topic. Use when Codex needs to start from known papers instead of a fully bounded corpus, trace citations or other relation signals outward, maintain explicit provenance from each discovered paper back to the seeds, rank the resulting reading map, and stop based on a documented saturation argument rather than pretending to cover the whole literature.