Agent-safe pipeline with secret masking
When agents handle user data, mask before any logging or storage - secrets should never reach an LLM or a kv store unredacted. Full guard pipeline - ...
Prompt
Batch LLM with rate limiting
Prevents failure at job 847 of 10,000 - throttle paces the pipeline, tok gates each doc before the API call wastes a request. Process a large ...
Cache LLM response
Avoids duplicate API calls for identical prompts - the hash keys the cache so reruns are free. Send a prompt, get the request hash, and store the ...
Fetch and summarise a page
Catches oversized pages before the API call - no wasted request on a doc that won't fit in context. Grab a URL, check token count, then summarise ...
Retry flaky API call
Transient 500s don't kill the pipeline - coax retries with backoff so one bad request doesn't stop the run. Wrap an LLM prompt in coax for ...
Scrub secrets from LLM output
Catches secrets the model echoes back before they reach storage - one leaked API key in kv is a breach. Mask any accidentally leaked secrets before ...
Token-checked LLM call
Prevents silent truncation - the model never sees a prompt it can only half-fit. Count tokens before sending to an LLM - abort if too large.
Validate LLM output before it propagates
Bad structured output exits 1 before reaching downstream systems - you catch schema drift at the source, not in production. Gate the pipeline on ...