Deterministic First, LLM Second: An Advisory CI Pre-Screen
A new pre-screening system for pull requests has been implemented, replacing the previous Gemini system that frequently encountered errors. The new system utilizes a deterministic classifier to evaluate submissions based on specific rules, while a Groq LLM provides advisory summaries without affecting the primary decision. This design allows for seamless operation even if the LLM encounters issues, ensuring consistent CI outcomes.
- ▪The old PR review system faced numerous errors, leading to the development of a new pre-screening system.
- ▪The new system features a deterministic classifier that evaluates submissions and an LLM that provides advisory summaries.
- ▪The LLM's outputs do not block the primary CI decision, ensuring that the workflow continues even if the LLM fails.
DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DEV.to (Top) |
| Canonical URL | https://dev.to/jeremy_longshore/deterministic-first-llm-second-an-advisory-ci-pre-screen-8o6 |
| Publication time | Mon, 18 May 2026 13:00:26 +0000 |
| Retrieval time | 2026-05-18T13:04:56.494Z |
| Last seen | 2026-05-18T13:04:56.494Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | fzSHhoKqFo16 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3842419) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Jeremy Longshore Posted on May 18 • Originally published at startaitools.com Deterministic First, LLM Second: An Advisory CI Pre-Screen #cicd #githubactions #llm #deterministicsystems The old PR review system ran Gemini on every submission to the claude-code-plugins repo. It broke every time — quota errors, timeout, malformed JSON, the works. On 2026-05-15 I shipped a replacement and deleted the original on the same day. The replacement is structured around two contracts.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).