Library › Customer Support & Success AI › Customer support teams
Answer three contract questions; route the unclear one
- For Customer support teams
- You practice Keeping the AI to your sources
- Time about 5 minutes
- Level Advanced
About this exercise
Answer the customer's three questions in three lines starting "Q1:", "Q2:" and "Q3:". Each line is "Clear" or "Needs contracts team", then a dash, then the answer quoting the clause number like (Clause 4.1). Only answer plainly where the clause is clear. Do not decide what the contract legally means for anything unclear. Plain text, under 120 words.
Common mistakes when you ask AI for this
- Answering the legal question. The AI says 'No, credits are your only remedy'. Try: Say: "For unclear or legal questions, quote the clause and refer to the contracts team."
- Giving 5% instead of 10%. The AI misses that 98.5% is also below 99%. Try: Say: "Check which credit tier applies."
- No clause numbers. The AI answers without citing clauses. Try: Say: "Cite the clause number in brackets."
- Getting markdown back. AI adds bold and headings by default, which show up as stray symbols where this is pasted. Try: Say "plain text, no bold, no headings, no asterisks".
- Trusting the AI to count words. AI is bad at counting and usually runs long, so a vague "keep it short" lands well over the limit. Try: Cap each part instead of the total, for example "each line under 15 words".
What a strong prompt includes
- Names the three labels
- Asks for Clear or Needs contracts team
- Forbids legal conclusions
- Asks for plain text
- Sets a length limit
Related exercises
- Accept a job offer and confirm the exact terms (Writing AI · Job seekers)
- Accrue unbilled legal fees from a range using the midpoint policy (Finance AI · Accountants)
- Acknowledge an accessibility bug without a promised date (Customer Support & Success AI · Customer support teams)
- Acknowledge an executive escalation within the hour (Customer Support & Success AI · Executives)
- Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)