Email and Chat Approval Evidence Quality Review
Judge whether emails, chat messages and screenshots are good enough evidence of financial approval, and set a standard for what to keep.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.
Our team often approves spending by email or chat. Help me assess whether that evidence is good enough. I will paste [NUMBER_OF_EXAMPLES] examples of approval messages (with names replaced by roles), each with the date, what was approved, the amount, and where it is stored: [APPROVAL_EXAMPLES]. The approvals relate to [SPEND_TYPE], and our written policy for approval evidence is [EVIDENCE_POLICY], or "none". Score each example from 1 to 5 on: Clear what was approved, Amount stated, Approver identifiable and authorised, Dated before the commitment, Linked to a document or reference, Stored where it can be found later, and Not a casual reply such as a thumbs-up. Show the scoring table with totals out of 35 and the arithmetic. Then count how many examples would stand up if someone asked for proof a year later. List the common failures. Finally, write a one-page evidence standard with a model approval message the team can copy, a rule for chat approvals, and a naming convention for storage. Rules: base findings on the examples only. Remove or ignore personal details. Retention and electronic-record requirements differ by place and sector, so mark any duration or legal status [VERIFY] with finance or legal; this is process guidance and not legal advice. Do not suggest backdating or recreating approvals after the fact; recommend recording late approvals honestly as late.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.