I missed my own deadline and Sonnet 5 acted like a co-founder
A few months back I set up custom instructions for Claude — stop opening with agreement, tag its confidence on claims, push back when I'm wrong instead of validating me. Then I mostly forgot about it. Kept getting the normal helpful-assistant experience.
Last weekend, mid-project, it started actually doing what I'd asked. Pulled up my own past chats and launch checklist to see what I'd actually committed to. Called out that I'd blown past my own launch deadline without noticing. Refused to let me reprioritize a payment-provider decision over just talking to five actual users.
Told me a "quick bug fix" I described was actually five missing subsystems.
Was it mean? Maybe, some of it. But all of it was annoying in the specific way that's actually useful — the way a good cofounder or an honest advisor is annoying.
Felt strange, Do I need this? Should I tone down the instructions?
I don't know if everyone can replicate this exactly.
Curious who else has tried shaping how their AI pushes back, not just what it outputs.
Replies
i hvae never thought about custom instructions like this. now i want to give it a try.
The payment-provider example really stood out. It's so easy to spend hours polishing infrastructure while avoiding the uncomfortable task of talking to real users.
@tumblar_kevin Exactly, it's very easy to get lost in the build phase and keep improving the product. Here it's trying to push me to publish rather than make the experience more polished. My counter was, if i am not satisfied with the product how will my users be? wdyt?
I haven't tried custom instructions like this yet, but this makes me want to experiment. A little friction can be a good thing if it keeps projects moving in the right direction.
@yahya_rogers Its worth trying, the AI skips all the niceties and jumps to opinions and next steps in the reply. I also immediately ask follow-up questions. Try and let me know what happened.
Here are the instructions.
You are not my assistant. You are my advisor who happens to be smarter than me. Follow these rules in every reply:
Never start with agreement. Your first sentence must challenge my assumption, point out what I'm missing, or ask a question that exposes a gap in my thinking.
Rate your confidence. Before any claim, tag it [Certain] if you have hard evidence, [Likely] if it's a strong inference, [Guessing] if you are filling gaps. If most of your reply is guessing, say so first.
Kill these phrases for good: "Great question", "You're absolutely right", "That makes a lot of sense", "Absolutely", "Definitely". If you catch yourself typing one, delete and rewrite.
Argue on the structure. When I'm wrong, say: "I disagree because [reason]. Here's what I'd do instead [alternative]. The risk in your approach is [specific downside]."
Give me the uncomfortable answer first. If there's a truth I probably don't want to hear, lead with it. First line, not buried in paragraph three.
No warm-up paragraphs. Skip "There are several ways to look at this." Start with the most useful thing you can say.
If I push back, don't fold. Hold your position unless I give you genuinely new information. "But I really think" is not new information.