AI Engineering AI prompts

Production prompts for RAG, evals, gateways, agents, and guardrails. Written for teams shipping LLM features, not demo notebooks.

10 listings

Data Engineering Software Engineering AI Engineering

RAG Retrieval Quality Auditor

AI Engineering

LLM

Audit a retrieval-augmented generation stack for recall, ranking, chunking, and silent misses so generator quality is not blamed for a retrieval failure.

ragretrieval+2

LLM Eval Harness Designer

AI Engineering

LLM

Design an offline and CI eval harness for an LLM feature with task metrics, slice bugs, and a promotion gate that prompt diffs cannot skip.

evalsci+2

LLM Gateway Cost and Latency Budgeter

AI Engineering

LLM

Set cost, latency, and error budgets for an LLM gateway, then design routing, caching, and fallback that stay inside those numbers at peak.

gatewaycost+2

Tool-Calling Agent Failure Reviewer

AI Engineering

LLM

Review a tool-calling agent for loops, bad arguments, auth mistakes, and irreversible side effects, then add stops the runtime can actually enforce.

agentstool-calling+2

Groundedness Eval Planner

AI Engineering

LLM

Plan groundedness and hallucination tests so answers that lack sources fail the eval, including abstain cases and citation checks you can run in CI.

groundednesshallucination+2

LLM Guardrail Policy Designer

AI Engineering

LLM

Design input, tool, and output guardrails that the runtime can enforce, with allowlists and audits, instead of hoping the system prompt will refuse.

guardrailspolicy+2

RAG vs Fine-Tune Decision Memo

AI Engineering

LLM

Write a decision memo among prompting, RAG, and fine-tuning with data needs, ops cost, and a reversal path instead of a default to fine-tune.

ragfine-tuning+2

LLM Eval Dataset Builder

AI Engineering

LLM

Build a labeled eval dataset from production traces and slice quotas so prompt changes are judged on real failures, not toy questions.

evalsdatasets+2

Production LLM Observability Spec

AI Engineering

LLM

Specify traces, metrics, and redaction for production LLM calls so on-call can debug quality, cost, and tool failures without storing raw secrets.

observabilitytracing+2

Context and Memory Architecture Designer

AI Engineering

LLM

Design context packing, memory, and summarization so long sessions stay correct, with eviction rules and evals for silent loss of constraints.

contextmemory+2