Stop waiting days for a custom report: give pricing and demand analysts domain AI agents grounded in curated datasets and airline terms so they ask follow-ups in minutes while every model call stays behind one governed gateway: AI agent prompt
A Databricks customer story on PROS (airline offer and pricing software) describes PROS Kairos, launched October 2026 on Databricks. Domain-specific Genie Agents for demand, pricing and flight analysis are grounded in curated datasets and internal documents that explain airline terms. A central orchestrator (a Databricks App) routes each question to the right Genie Agent, MCP server or skill. Analysts who once waited about two days for engineering reports now get answers in minutes with follow-ups in the same flow. Every agent reaches models through Unity Gateway for logging, sensitive-data blocking, usage caps and failover. Lakebase Postgres already stores AI agent session data. Figures and quotes are from PROS; adapt the pattern to your own curated domains rather than raw warehouse dumps.
The prompt
1. Pick three domains your team asks about weekly (for example demand, pricing, inventory) and name the curated tables plus the glossary docs each domain needs. 2. For each domain, write sample questions, standing instructions, and which tables the agent may query—no free roam across the whole warehouse. 3. Put a single front door (chat or app) that routes each question to the matching domain agent; keep model calls behind one gateway with logging, PII blocks and a spend cap. 4. Take five real tickets that used to wait on engineering, ask them through the agents, and compare answers to the old reports. 5. Only after answers stay stable for a week, let more analysts in—and keep a human owner for anything that changes a live offer or price.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (or fill in the blanks on AgentPlaybook Real Estate, which remembers your answers for the next prompt).
- Paste it into Databricks Genie Agents / Unity Gateway (or similar governed analytics agents), curated datasets, internal glossary docs and review the answer before you use it.
Works with: Databricks Genie Agents / Unity Gateway (or similar governed analytics agents), curated datasets, internal glossary docs, orchestrator app
Real-world example: databricks.com/customers/pros/genie
Featured in: ChatGPT prompts for business email, replies and follow-ups · AI prompts for writing SOPs, reports, policies and checklists
Before you use it: what to check
Already built into this prompt
- Only after answers stay stable for a week, let more analysts in—and keep a human owner for anything that changes a live offer or price.
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