Copy-paste prompt
Compare quotes for [spec, quantity] from [vendor URLs / quote emails]. For each vendor, give the unit price, minimum order, lead time, shipping, payment terms and landed cost per unit at our quantity, with a link to each quote. List what's missing and draft the questions to ask. Recommend one and explain the trade-offs. Don't contact anyone.
Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.
What you need
- Vendor URLs or quote emails
- Your spec
How the agent does it
- Gather the price, minimums, lead time, shipping and payment terms for each vendor.
- Normalize to your quantity and the landed cost per unit.
- Note missing information and draft clarification questions.
- Recommend the best fit with the trade-offs.
What you get
A comparison table, a recommendation and draft clarification emails.
| Schedule | On demand. |
|---|---|
| Needs your approval | Contacting vendors and placing orders need approval. |
| How to check it worked | Landed cost math is shown; every figure links to its quote. |
Common mistakes
- Comparing unlike units. Normalize everything to the same spec and quantity.
Setting it up in each agent
In Grok Bot
Ask the Bot to run the prompt once and review the result. Then say "Save the process we just used as a skill called 'Vendor quote comparison'" and "Create a routine that runs the Vendor quote comparison skill on demand". Grok Bot's docs say a Bot can own up to 50 routines, schedules must be at least five minutes apart, and you should use Test run before you enable one.
In Meta Muse
Paste the prompt into Muse and ask it to remember the job and run it on the schedule. Muse asks for approval before outbound actions and purchases, so keep the 'don't send' line in the prompt. Before you rely on it, check that Muse can reach the apps this recipe needs.
In ChatGPT Dots
Give your dot the prompt as an ongoing goal and set the schedule. Dots can work between chats and ask for approval before sensitive actions. OpenAI says background work counts toward your plan's allowance, so match the frequency to what you actually need.
Run it by hand once with harmless inputs before you schedule it. A test run does real work.