recipe
Validate LLM output before it propagates
· 2 min read
Bad structured output exits 1 before reaching downstream systems - you catch schema drift at the source, not in production. Gate the pipeline on ...
tag
#prompt
8 posts tagged #prompt
recipe
Token-checked LLM call
· 2 min read
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.
recipe
Scrub secrets from LLM output
· 2 min read
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 ...
recipe
Retry flaky API call
· 2 min read
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 ...
recipe
Fetch and summarise a page
· 1 min read
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 ...
recipe
Cache LLM response
· 1 min read
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 ...
recipe
Batch LLM with rate limiting
· 2 min read
Prevents failure at job 847 of 10,000 - throttle paces filenames so each API call respects the rate limit. Process a large document set without ...
recipe
Agent-safe pipeline with secret masking
· 2 min read
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 - ...