Paste code along with its concurrency model and the shared state involved for a review that skips general code-review concerns entirely and focuses only on concurrency.
- Race conditions from unsynchronized read-modify-write or check-then-act patterns
- Deadlock or livelock risk from lock ordering across threads or async tasks
- Cleanup gaps under concurrent cancellation or failure
- Each issue ships with the exact interleaving that triggers it, not a generic warning
Reviews a chart — its type, intended message, underlying data, and any suspected issues — before it goes into a deck or report.
- Checks: whether the chart type fits the data relationship, honest visual encoding, data-to-ink ratio
- Tests: whether the key insight lands within 5 seconds and holds up in black and white or for colorblind readers
- Output: concrete before/after fixes, not just a list of complaints
Paste the slow query along with the database engine, approximate table
sizes, current execution time, and any existing indexes, and this prompt
diagnoses the real bottleneck — a full table scan, a missing index, an
unnecessary join — before rewriting the query for performance. It
proposes concrete CREATE INDEX statements, estimates the expected
speedup, and suggests an alternative like a materialized view or
pre-aggregation when a rewrite alone won't be enough, showing
before-and-after versions with an explanation for each change.
Describe the recurring problem, its business impact, when it started, and
what data you have available, and this prompt runs a structured 5 Whys
investigation instead of a quick patch.
- Asks why five times to pinpoint the actual root cause
- Identifies contributing and systemic factors behind it
- Produces corrective actions and preventive measures
- Ends with a concrete implementation plan
Paste a draft set of interview questions to sanity-check before running
them with real participants.
- Flags leading language in each question
- Flags ambiguity and structural problems
- Offers a revised version alongside every critique
- Pairs well as a review pass after drafting an interview guide
Submits your own finished essay for a critical review against your course or qualification level, asking the AI to evaluate content accuracy and how well it addresses the central themes, assign a predicted grade, and list simple bullet-pointed suggestions for raising that grade. Designed for revising your own draft before submission, not for generating essay content from scratch.
Has an AI acting as your course professor grade your own uploaded essay against the rubric you provide, evaluating it against the specific essay prompt and course level, identifying real strengths, and giving specific, actionable suggestions for improvement without ever rewriting the essay for you. Built for getting honest, rubric-anchored feedback on a draft before submission, not a substitute for revising it yourself.
Paste any AI-generated code snippet you're about to merge and get a plain-language walkthrough of what it does, how it works step by step, and where its assumptions or edge cases might fail. Built for the moment right after a code-generation tool hands you something you don't fully trust yet, so you catch problems before they reach review instead of during an incident.
Reviews a pasted diff through the lens of a senior engineer who has owned this codebase for two years and has strong opinions about pragmatic architecture.
Instead of hedged, generic notes, it calls out whether abstractions sit at the right level, flags trade-offs that will bite in six months, and says so directly rather than diplomatically. Swap in your real stack and values for a sharper persona.