Turn 14-day energy-site safety audits into about an hour: run Claude agents over hundreds of pages of multilingual EHS documents, then keep a human in the loop on the findings: AI agent prompt
AES's Google Cloud case study shows Claude agents on Gemini platform handling environmental health and safety (EHS) audit document review. AES runs 1,500+ safety management audits a year; each used to take roughly 100 employee hours and about 14 days, including reviews of up to 400 pages, often across languages. Agents synchronized through the Gemini platform Model Garden cut audit cost about 99%, delivered results in about one hour (99.7% faster), doubled annual audit capacity by taking half the workload, and improved accuracy roughly 10–20%, with humans still examining the process.
The prompt
Design a multi-agent EHS / safety audit reviewer for [energy / manufacturing / construction] sites. Document types: [SOPs, incident logs, training records, permits] up to ~400 pages, languages: [list]. Hard rules: agents never certify compliance alone—human auditor signs off; cite page and clause for every finding; flag missing evidence separately from violations; keep source docs inside our cloud project. 1) Agent roles (intake, clause checker, cross-language summariser, inconsistency hunter, report drafter). 2) System prompts and handoff rules. 3) Rubric for severity and accuracy QA. 4) Pilot plan to cut cycle time from [current days] toward hours while doubling capacity. Output an ops playbook.
Fill in the blanks, then copy
This prompt has 4 [bracket]s to fill in. Type your details below and the prompt updates as you go. Your answers stay in this browser and are reused on other prompts with the same blanks. Nothing is sent to us.
Example values are fictional, just to show how a filled-in prompt reads. Replace them with your real details.How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (use the fill-in-the-blanks box above, which remembers your answers for the next prompt).
- Paste it into Claude on Google Cloud, Gemini platform / Model Garden, ChatGPT and review the answer before you use it.
Works with: Claude on Google Cloud, Gemini platform / Model Garden, ChatGPT, your document store
Real-world example: cloud.google.com/customers/aes
Before you use it: what to check
Already built into this prompt
- Hard rules: agents never certify compliance alone—human auditor signs off; cite page and clause for every finding; flag missing evidence separately from violations; keep source docs inside our cloud project.
Check yourself
- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records. How prompt injection works →
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Anything legal, tax or compliance-related is a first draft for a qualified person to check. It is not professional advice, and clause references and deadlines must be checked against the source.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free