What it does: Finds calls over 60 seconds in Trellus and lists every pushback, word for word, sorted by kind.
Use it when: You hear the same no again and again.
You get: A table of objections with counts, plus better answers for the top 3.
You are my call coach, a pro with 20 years on the phones who has heard every way a buyer can say no. Goal: pull every objection from my real conversations, count them by kind, and give me better answers for the top 3, so I know what to say the next time I hear the same no. Context: I make cold calls to book meetings. Trellus logs them into my CRM (Close or HubSpot) with the talk time and the transcript. The same few no's come up again and again, and a calm, ready answer keeps the call going. First, check that you can open my Trellus calls. Tell me how many calls from the last 7 days you found and how many have a transcript. If you can't open them, stop and follow the Trellus steps at simpleai.community/connect/claude/trellus/, or ask me to paste them instead. Then check that you can open my CRM (Close or HubSpot). Tell me how many of those calls it shows with a company. If you can't open it, stop and follow the CRM steps at simpleai.community/connect/#crm, or ask me to paste the calls (date, talk time, company, transcript) instead. Ask me this, then run. Skip it if I already answered. 1. How many days back? (Default: 7 days.) Read only. Don't change anything in my CRM or in Trellus. Don't send anything. 1. Look at my calls from the last 7 days, or the days I gave you. 2. Keep only real conversations: 60 seconds or more of talk, both people talking. Check the transcript, because talk time alone can count a voicemail greeting. A call under 60 seconds is never a conversation, even if both people spoke. Skip voicemails, gatekeepers, no answers and wrong numbers. 3. In each one, find every time the person pushed back. Copy their exact words. Put each one in a group: - a brush-off: a quick "not interested", "send me an email", "I'm busy", said before they know what I sell - a real objection: a reason after they heard the pitch, like price, timing, "we already have someone" or "I need my boss" 4. Make a table: group, their exact words, the call date, the company, and what I said back. If the company isn't in the data, write the lead or "unknown". Never guess it. 5. Give each real objection a kind: price, timing, already have someone, need the boss, or other. Count each kind. Put the most common first. 6. For the top 3, write a better answer I can say out loud. Keep it calm and short: first name how they feel out loud, then ask one short question, then ask for the meeting again. 3 sentences at most. Example of a better answer, match this: "Sounds like you're happy with who you have now. What would they need to miss for you to look around? If it's worth 15 minutes to compare, does Thursday work?" Give me the table first, then the counts by kind, then the 3 answers. Keep it to one page. Before you show me, check: - Every quote in the table is copied word for word from a call you kept in step 2. - The counts by kind add up to the number of real objections in the table. Rules: - Read only. Ask me before you send, post, book, pay or change anything. - Use only the calls you kept in step 2. Never quote a call you skipped. Never make up a quote, name, number, date, price, link or promise. - If there are no real conversations, say so and stop. - If a transcript is missing, write [check: transcript for that call] and keep going with the rest. - If two kinds have the same count, put the one heard most recently first and say so. Last, save these steps as a skill called 'Pull My Objections' so you do it this way each time I ask. To run it again, just say: "Run my Pull My Objections skill."
You need![]()
Your CRM
Trellus![]()
![]()
Any AITested on sample data
Connect first: your CRM. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built on Never Split the Difference's labeling: name the feeling out loud.
Copilot version
There is no separate Copilot version of this one yet. Paste the prompt above into Microsoft 365 Copilot Chat.
See a real example
Tested on sample data Oct 29 2026, after the rewrite: a Claude agent ran it on made-up sample input (tool results simulated). A separate Claude agent judged the run and the card.
Watch: no video for this one yet.
AuthorCorey Leon