Verified against Cursor · 2026-07-18
Point Cursor BugBot at real risk instead of letting it restate the diff
A PR description written for BugBot, Cursor's automated PR-review agent, that states risk areas and known trade-offs up front so its comments concentrate on logic and security instead of narrating what the diff already shows.
The prompt
Ready to copy — highlighted parts are example details you can swap.
PR SUMMARY Switches the checkout discount calculation from a flat percentage to a tiered table looked up by cart total. RISK AREAS TO FOCUS REVIEW ON The boundary values between tiers (is $100.00 exactly tier 2 or tier 3?), and whether the old flat-percentage code path is fully removed or still reachable from the cart API. KNOWN TRADE-OFFS — do not flag these as bugs, they were a deliberate choice Tier boundaries are hardcoded, not config-driven — intentional for this release, a follow-up ticket will move them to settings. @BugBot review this PR against the risk areas above specifically. For each finding: cite the file and line, classify it as Bug, Security, or Style, and rate it Blocking or Minor. Skip anything already listed under known trade-offs — if you disagree with a trade-off, say so as a Minor note, not a Blocking finding.
Customize the highlighted detailsoptional — the prompt above already works
Why this works
BugBot runs automatically against a PR's diff once enabled on a repo and posts inline comments without a human writing a review prompt at all, which is exactly the problem: with no steer, it reviews the whole diff at a uniform level of attention and its comment thread mixes real logic risk with restated-diff narration and style nits in no particular order. Naming RISK AREAS concentrates its attention the same way a scoped rubric concentrates any LLM reviewer — it's told where the actual uncertainty in this change lives (tier boundaries, a possibly-still-reachable old code path) instead of treating every line as equally suspicious. KNOWN TRADE-OFFS does the opposite job: it suppresses the single most common false-positive pattern in automated PR review, where a deliberate simplification gets flagged as a defect because the reviewer has no way to know it was a choice rather than an oversight, and it explicitly downgrades a disagreement to a Minor note instead of a Blocking finding so a legitimate design debate doesn't stall the merge.
What you get back
BugBot findings: 1. checkout/pricing/tiers.ts:34 — Bug, Blocking. Tier lookup uses cartTotal > threshold, so a cart total of exactly $100.00 falls into tier 1, not tier 2 as the PR summary implies. Off-by-boundary on the exact value you flagged. 2. checkout/pricing/legacy.ts:12 — Bug, Blocking. calculateFlatDiscount is still exported and still called from api/cart/quote.ts, so the old code path you asked me to check is in fact still reachable. 3. checkout/pricing/tiers.ts:8 — Style, Minor. Hardcoded tier boundaries — noted as a known trade-off, not blocking, but flagging the follow-up ticket isn't linked anywhere in this PR.
Verified against
Cursor 2.1 · 2026-07-18
Changelog
- 2026-07-18 — Initial publish, verified against Cursor BugBot's GitHub PR integration on Cursor 2.1.
Need this built into your business?
If a prompt isn't enough — custom software, built and maintained for you — that's Scult's day job.
EXPLORE CUSTOM SOFTWARE
