O Triador de Testes Instáveis: Transforme Testes de CI com Falhas Intermitentes em um Plano de Quarentena Ordenado por Causa Raiz
Porque é que este prompt importa
Flaky tests that go untriaged do not stay flat — they compound, because "just re-run it" becomes the team's default response to any red build. A widely cited Google engineering study found flaky tests account for roughly 1 in every 300 test runs in large CI suites, and engineering teams that track the human cost put it far higher: SREs commonly estimate several lost engineer-hours per week spent manually re-running or waiting out intermittent failures across a mid-sized team. Left untriaged, flaky tests are also one of the most common reasons teams eventually weaken or disable CI gating altogether — trading the short-term convenience of a green build for the exact safety net CI exists to provide, right up until a real regression slips through disguised as "probably just flaky."
Para que o usamos
Your team's CI dashboard has quietly accumulated 18 tests tagged "flaky" over the past two months. Nobody owns the list, and new hires are simply told to click re-run when one of them turns red. On Thursday afternoon, ahead of Friday's release freeze, the QA lead exports the flaky-test tracker — test names, failure rates, and the last few stack traces for each — and runs it through this prompt to get a sprint-ready triage: which tests to quarantine today, which ones trace back to one shared root cause, and which genuinely need another engineer's eyes before anyone touches them.
Prompt
Role: Act as a senior test infrastructure engineer / staff SDET with 10+ years of experience stabilizing CI pipelines at scale. You have seen every category of flaky test and know the difference between a real intermittent bug and a badly-written test. Context: My team's CI system is [CI SYSTEM NAME, e.g. GitHub Actions / CircleCI / Jenkins]. Over the past [TIME WINDOW, e.g. "6 weeks"], the following tests have been flagged as flaky (intermittently failing with no corresponding code change in the failing area): [PASTE FLAKY TEST LIST — for each test include: test name, approximate failure rate (e.g. "fails 1 in 8 runs"), the error message or stack trace snippet from the last 2-3 failures, and how long it has been flaky] Relevant recent changes to the codebase or infrastructure: [RECENT CODE/INFRA CHANGES, e.g. "migrated CI runners to new containers 3 weeks ago", "added a Redis caching layer", "none known"] Engineering capacity available to fix tests this sprint: [TEAM SIZE / CAPACITY, e.g. "2 engineers, 1 day each"] Task: For each test in the list, triage it into a root-cause category, assign a confidence level, and recommend a specific next action. Then identify any systemic patterns across multiple tests (e.g. several tests failing because of one shared fixture or one piece of shared infrastructure) and surface those separately, since fixing one shared root cause may resolve several "individual" flaky tests at once. Constraints: - Do not guess a root cause without citing specific evidence from the error message or stack trace provided. If the evidence given is insufficient to form a confident hypothesis, say so explicitly and mark the test as "Needs More Data" rather than inventing a plausible-sounding cause. - Do not recommend "just add a retry" or "increase the timeout" as a fix unless the evidence specifically points to a timing/race condition where that is a legitimate mitigation — and if you do recommend it, label it clearly as a MITIGATION, not a FIX, and note that the underlying bug is still open. - Keep every recommended action realistic for the stated engineering capacity — do not recommend 5 fixes if the team only has 1 day available; rank by impact instead. - If a test appears to be testing something that no longer matters (e.g. a deprecated feature), flag it as a candidate for deletion rather than a fix. - Be direct about tests that are poorly designed (e.g. depend on wall-clock time, test execution order, or shared mutable state) versus tests exposing a genuine product bug — these require different fixes. Output Format: 1. A table with these exact columns: Test Name | Suspected Root Cause Category (Shared State / Race Condition / External Dependency / Environment-Infra / Genuine Product Bug / Poorly Designed Test / Needs More Data) | Confidence (High/Medium/Low) | Evidence Cited | Recommended Action | Suggested Owner/Skillset 2. A "Quarantine Now" section: a bare list of test names that should be disabled or skipped immediately, each with a one-line justification, so they stop blocking merges while the real fix is scheduled. 3. A "Systemic Issues" section: any root cause that explains 2+ tests in the list, with the shared fix that would resolve multiple rows at once, ranked by how many tests it would unblock. 4. A "This Sprint" section: given the stated capacity, the single highest-leverage action to take first and why.
Resultado
Here is the triage based on the 6 tests and context provided:
| Test Name | Root Cause Category | Confidence | Evidence Cited | Recommended Action | Owner | |---|---|---|---|---|---| | test_checkout_coupon_apply | Shared State | High | Failure log shows AssertionError: expected balance 42.00, got 38.50 only when run after test_checkout_refund_flow in the same worker — both tests share a module-level TEST_WALLET fixture that is never reset between runs | Fix Now: move TEST_WALLET to a per-test fixture with explicit teardown | Backend/test-infra engineer, ~2 hrs | | test_session_refresh_race | Race Condition | High | Stack trace shows TokenExpiredError thrown 40ms after the refresh call returned 200 — the token refresh writes to cache asynchronously | Mitigation only: await the cache write explicitly in the test. This is NOT a fix — the underlying async write-then-read gap may also affect production under load; file a separate ticket | Platform engineer | | test_search_results_count | External Dependency | Medium | 3 of 4 recent failures logged ConnectionTimeout against the staging Elasticsearch cluster, not the application code | Quarantine Now + file an infra ticket for staging ES cluster capacity | Infra/SRE | | test_legacy_sms_notification | Unknown | Low | Only one failure instance provided and the error message is truncated — not enough evidence to confirm a root cause | Needs More Data: capture the full stack trace on the next 2 failures before assigning an owner | QA | | test_deprecated_loyalty_tier_calc | Poorly Designed Test / Deletion Candidate | High | Test covers the loyalty-tier feature that was flagged for removal in last quarter's roadmap doc | Delete rather than fix | Feature owner | | test_cart_total_rounding | Shared State | Medium | Same TEST_WALLET fixture referenced in the failure context as test_checkout_coupon_apply | Resolved by the same fix as row 1 | — |
Quarantine Now: test_search_results_count — blocked on a staging infrastructure problem, not application code; disabling it stops it from blocking unrelated merges while SRE addresses cluster capacity.
Systemic Issues: The TEST_WALLET shared fixture explains 2 of the 6 failures (test_checkout_coupon_apply and test_cart_total_rounding). Fixing the fixture's teardown logic once resolves both rows and should be prioritized over fixing either individually — this is the highest-leverage single change in the list.
This Sprint: With 1 engineer-day available, fix the TEST_WALLET fixture teardown first. It resolves 2 of 6 flaky tests in roughly 2 hours, leaving the rest of the day to quarantine test_search_results_count and file the Elasticsearch capacity ticket with infra.
Toda equipe de engenharia acumula testes instáveis (flaky) da mesma forma: um falha de forma intermitente, alguém clica em «executar novamente», o teste passa, e nenhum ticket é aberto para investigar a causa real. Seis meses depois, existe uma lista com mais de 20 testes que ninguém possui, e a confiança da equipe nos sinais de verde e vermelho do CI se desgastou silenciosamente.
Este prompt foi projetado como uma estrutura de triagem, não como um simples pedido de «cole o erro, receba a solução», porque diagnosticar um teste instável é, antes de tudo, um problema de classificação, não de correção. A seção de Função (Role) posiciona a IA como engenheira sênior de infraestrutura de testes justamente para que ela reconheça padrões das categorias conhecidas de instabilidade (estado compartilhado, condição de corrida, dependência externa, infraestrutura, bug real do produto, ou teste mal projetado) em vez de tratar cada falha como um mistério único.
A seção de Restrições (Constraints) faz o trabalho mais pesado. Ela proíbe explicitamente dois erros comuns da depuração assistida por IA: inventar uma causa raiz plausível quando as evidências fornecidas não a sustentam, e recomendar por reflexo «adicione um retry» como se isso fosse uma correção, e não apenas um remendo temporário. As duas instruções forçam o modelo a ser honesto sobre a incerteza — o que importa mais aqui do que na maioria dos prompts, porque um palpite errado de causa raiz manda um engenheiro perseguir a correção errada por meio dia.
O Formato de Saída (Output Format) é deliberadamente dividido em quatro seções, em vez de uma única tabela, porque o verdadeiro valor da triagem não está nas linhas individuais, mas em perceber que três testes «sem relação» na verdade dependem de uma mesma fixture compartilhada. A seção dedicada a «Problemas Sistêmicos» força essa síntese explicitamente, em vez de deixá-la escondida em uma tabela que um engenheiro cansado só folheia. A seção «Este Sprint» conecta o resultado à capacidade real da equipe, de modo que o prompt produza um plano executável hoje, e não uma lista aspiracional de 20 correções para as quais ninguém tem tempo.
Execute-o semanalmente ou antes de qualquer congelamento de versão, colando o que o painel do CI marcou desde a última vez — isso transforma a limpeza de testes instáveis de um backlog que ninguém toca em uma triagem recorrente de 15 minutos.