Catalogue
- Cards
- 165
- Records
- 486
- Workloads
- 19
- Corpus version
- 74847648e25a
53 of 486 records match; the first 20 are shown.
| Kind | Record | Organisation | Year | Setup |
|---|---|---|---|---|
| Decision | Partition catalog clustering to per-shop tasks and filter standalone stores deterministically via Liquid themes before calling LLMs | Shopify | 2026 | |
| Decision | Replace naive linkage-tree clustering with FAISS HNSW plus sparse UPGMA average linkage to form coherent chunks up to 200 products | Shopify | 2026 | |
| Decision | Use a two-stage propose-and-critique LLM flow with dynamic per-chunk Structured Output schemas and normalized product IDs | Shopify | 2026 | |
| Failure | Tarpit rate limiting held sockets open until the load balancers ran out of connection slots and rejected real traffic | Healthchecks.io | 2025 | |
| Decision | Answer rate-limited requests with an immediate HTTP 429 instead of tarpitting them | Healthchecks.io | 2025 | |
| Decision | Pair GPT-4 confirmation and MetaReflection hybrid prompts with expanded offline evaluation to curb LLM false positives | GitHub | 2025 | |
| Decision | Share LLM capacity across push and full-history scans with dynamic rate-limit ranges and filepath exclusions | GitHub | 2025 | |
| Decision | Validate prompt and filter changes via mirror testing on public-preview repositories before GA | GitHub | 2025 | |
| Decision | Move rate-limit state from MariaDB tables to Redis with per-key TTLs | Let's Encrypt | 2025 | |
| Decision | Replace week-long sliding-window counters with GCRA virtual scheduling | Let's Encrypt | 2025 | |
| Decision | Pause failing zombie clients by tracking consecutive ACME challenge failures per account and domain | Let's Encrypt | 2025 | |
| Decision | Store user segment membership for 270M+ users in roaring bitmaps downloaded from S3 at startup instead of Bloom filters | Grab | 2023 | Sharded |
| Decision | Enforce per-user frequency caps with a Redis sorted-set sliding log instead of DynamoDB or a sliding window limiter | Grab | 2023 | Sharded |
| Decision | Preload the Lua script via SCRIPT LOAD and pipeline per-user EVALSHA calls to avoid Redis Cluster CROSSSLOT errors | Grab | 2023 | Sharded |
| Decision | Use few-shot GPT-4-chat (gpt-4-32k) instead of fine-tuning davinci-002 or using the completion API | Canva | 2023 | |
| Decision | Redact internal data pre-LLM, use soft 600-character prompt targets with retries, and track edits via Jira webhooks | Canva | 2023 | |
| Decision | Run nearest-neighbor vector search in memory inside stateless Kubernetes services rather than a stateful database | Spotify | 2023 | |
| Decision | Build Voyager as a new HNSW package to succeed Annoy instead of making breaking changes in hnswlib | Spotify | 2023 | |
| Decision | Replace the Wide & Deep (XGBoost + DNN) fraud ensemble with a ResNeXt-inspired multi-branch pure DNN | Stripe | 2023 | |
| Decision | Pair black-box DNN fraud scoring with merchant Risk Insights (backed by Elasticsearch) and internal feature-contribution tables | Stripe | 2023 |
33 more records. Sign in to see all 53.