back_office_ops · ecommerce · workflow
Instacart's prompt engineering techniques for internal LLM productivity tooling
LLMs used in Instacart's internal productivity tools face challenges including hallucinations, context size limits, difficulty completing tasks, and unreliable output formatting when used programmatically.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Code diff input received
A code diff triggers the PR title and description generation workflow.
Tools used
GPT-4GPT-3.5OpenAI
Outcome
Instacart developed and deployed a suite of prompt engineering techniques for the Ava family of internal productivity products, achieving reliable structured output and improved LLM response quality.
Grounding & classification
Source type: technical build writeup
16 fields verified against source quotes.
agentic workflowcontent generationcode diff prnamed customerproduction runtime claimedtools describedworkflow describedecommerceemployee productivitytechnical build writeupback office opsai draft human approval