SoN 2.43: When your AI buries you in questions


VOL 2, ISSUE 43 · NOVEMBER 2026

One of my favourite ways of working with AI is to set Claude or ChatGPT a task, or a series of them, before I go and do other jobs around the house. But often when I come back to it, it's waiting on me with a list of questions about details I don't remember discussing. I've spent the last hour on something else, and now it wants answers.

I've often typed back something close to this: "These are too many questions. I'm a human. I can't deal with this much throughput. You've got to step me through it, either one question at a time, or you give me more context and detail and help me reason through it, rather than expecting me to just go bap, bap, bap, bap, bap and reply."

The AI doesn't know anything about your day apart from what's in front of it. We don't work at the same speed as the AI does. Telling it how to ask protects your time just as much as it speeds things up. Put these lines in your settings, so they apply to every chat:

When you need answers from me, group your questions by topic. Start each group with a line on what it's about and why you're asking. Give me one group at a time, with no more than three questions in it. If you can find an answer yourself, do that first.

Paste it in once, and it works in every new chat after that.

Learn how to set it up →

Also in this week's issue: how to hand AI work to a new chat or a teammate, how to stop your AI repeating the same mistake, one rulebook for your team's AI, and who fixes the flaws AI finds in local government.

Working with AI

Custom instructions for when your AI asks too many questions Interactive

AnthropicGoogleOpenAI

Paste-in lines for ChatGPT and Claude that make your AI ask in groups of three or fewer, each with a line on what it's about, so you can answer after a break.

Get the paste-in lines →

Hand AI work to a new chat or teammate with a short handover Interactive

AnthropicGoogleOpenAI

Ask your AI for a handover in one format, keep that format in a Claude or ChatGPT project, and share daily logs so a new chat or a teammate's AI can carry on.

Get the handover request →

Five whys: stop your AI repeating the same mistake Interactive

AnthropicGoogleOpenAI

A post-mortem prompt for the end of a bad AI chat: it asks why five times and gives you one rule to check before you paste it into your AI's instructions.

Run the five whys prompt →

Shared project instructions: one rulebook for your team's AI Interactive

AnthropicGoogleOpenAI

Shared project instructions keep your team's ways of working and house rules in one document every AI reads: a shared Claude Project, ChatGPT project or Gem.

Set up a team rulebook →
Jim Christian, drawn in ink

Book a discovery session

Just starting out with AI, or trying to find a way into AI enablement inside your organisation? Book a 60-minute AI discovery session at jimchristian.net/discovery and let's have a chat about what you can make possible.

Learn more and book →

Security and Risk

Local government cybersecurity: who fixes the flaws AI finds?

Anthropic

Part 3 of my series "AI Finds the Flaws. Who Fixes Them?": each council and public body is responsible for its own security, and most help on offer is grant money. Ask who patches your town hall's systems, and how fast.

Read part 3 →

Have you filled in the reader survey?

If you haven't filled in the reader survey yet, it asks how you use AI at work and what you're stuck on.

Take the survey →

Reader challenge: do you know what a system prompt is?

A

A system prompt is a set of instructions an AI keeps for every chat after it's given, covering how it behaves, who it acts as, what it won't do and what it needs to know.

 

B

A system prompt is the first message you type in a new chat, which the AI answers once and then forgets.

See the answer in the glossary →

That's it for this week. If your team is working out what to do with AI, hit reply and tell me where you're stuck.

Jim

Jim Christian - Signal Over Noise

What I care about is helping people bring technology into their lives well — where it's genuinely needed, and where it can do the most good. Not tech for its own sake, not change to look modern. Sometimes that means AI; just as often it means something far simpler.The tech world is accelerating. This is my attempt to slow things down a little: to pick apart the hype and look for the reality and the truth in the messages — primarily around AI, and how it impacts us all.

Read more from Jim Christian - Signal Over Noise
A boxy yellow robot at a wooden workbench assembles a small box labelled SKILL beside a large, worn book labelled SOURCE. Question cards numbered 1 and 2 sit on a spike on the bench, and a scruffy green dog walks up carrying card 3 in its mouth.

VOL 2, ISSUE 42 · NOVEMBER 2026 Frameworks are all around, and they've been in use for ages. Some of my favourites are the five whys, where you ask “why?” until you reach the cause of a problem, and the Eisenhower matrix, which sorts your tasks by how urgent and how important they are. There's no reason why you can't use these in your daily workflows to help you keep organised or to troubleshoot problems. If you don't know one for your job, ask your AI what established methods exist for it,...

A boxy yellow robot at a ticket kiosk labelled DATA HUB holds up a paper ticket marked TOKEN, with a canary in a cage and a scruffy green dog by the gate.

VOL 2, ISSUE 41 · NOVEMBER 2026 Part of my daily routine has changed in the last week, in that I'm talking more with Claude in voice mode on my school runs in the mornings. It beats the repetition of listening to the radio station, and it gives me more space to ramble and go down the odd rabbit hole as I question the morning headlines and look for topics of interest. When I get on to something I like and want to follow up on, I ask Claude to make sure that it's saved as a Google Doc that I...

A boxy yellow robot at a drafting table sketches a plan and points to small helpers at a supermarket checkout.

VOL 2, ISSUE 40 · OCTOBER 2026 In the last week I've been doing more hands-on training with teams of software engineers and marketers alike. No matter what your career or your skill level with AI, a lot of the core principles are the same, and many of them come back to breaking a job down before you hand it to AI. In this week's issue: use the biggest model to plan the job and smaller ones to do the work; a guide to how language models predict the next word, using a birthday song and a...