Multi-turn conversations — letting the chat build a model of the task
At User level, a single prompt is rarely the win. A 5–10 turn conversation that builds a working model of your task is.
::TL;DR · the whole lesson in three lines
- MOVEAt User level, a single prompt is rarely the win. A 5–10 turn conversation that builds a working model of your task is.
- DRILLRun a discovery-first conversation on a real task. Start by asking the AI to interview you. Notice how the eventual draft is calibrated to you, not generic.
- WINYou ran a 7+ turn conversation on one task.
::concept · what's actually happening
A long conversation gives the AI a working model of what you're trying to do, who you are, and what "good" looks like for you. By turn 5 the answers are 2x better than turn 1, because the AI is now drafting against context, not against a cold start.
read full concept · 2 more paragraphs →collapse concept ↑
Three patterns that work: (1) Discovery — start with "ask me 5 questions before you write anything." The AI gathers context first. (2) Iteration — generate, critique, refine, in the same chat. (3) Roleplay — "act as a [role]" carries through the conversation.
When the conversation gets too long (50+ messages), the AI starts losing the earlier context. Time to summarize what's been decided and start fresh with that summary as the new opening prompt.
::drill · do the thing
Run a discovery-first conversation on a real task. Start by asking the AI to interview you. Notice how the eventual draft is calibrated to you, not generic.
::L7 drill · copy-paste into any AI chat
I need to [the task — e.g. "write a year-end performance self-review" / "plan a 3-day weekend in Portland with my partner" / "decide whether to take a job offer at a competitor"]. Before you draft anything, ask me 5 questions you'd need answered to give me a useful first version. Number the questions. Wait for my answers before drafting.
::steps
- 01Pick a real task that has any complexity (not "reply to email").
- 02Run the prompt. The AI asks you 5 questions.
- 03Answer the 5 questions honestly, one message.
- 04Now ask for the draft. Notice how calibrated it is.
- 05Use the iterate pattern (Lesson 4) to refine.
::outcome · what should be true
- You ran a 7+ turn conversation on one task.
- The final output is meaningfully better than what a single one-shot prompt would have produced.
- You start defaulting to discovery on any task with more than one input variable.
::trap · the most common failure
Treating the discovery questions as friction. The 5 questions ARE the value. Most novice/learner answers are bad because the AI didn't get to ask first.
::other lessons at User level
Documents in chat — when paste vs. upload matters
AI is at its best when reading something specific. Knowing how to feed it documents is the next leverage step.
Your first paid tier — which one, when, why
Free tier is enough for most humans for 30+ days. When you outgrow it, you pay for ONE tool. Not four.
Image-in-chat — paste the screenshot
Most people describe what they see when they could just paste the screenshot. The AI reads pixels better than you can describe them. Stop typing the picture.
Voice mode — when speaking beats typing
Real-time conversation with AI is a different shape than chat. Knowing when to switch modes is the actual skill.
Projects and Custom GPTs — stop re-explaining yourself
Every chat starts cold. A Project remembers your background, your style, your files. Create one for the work you actually do every week, and stop pasting the same context twelve times a day.
Artifacts and Canvas — the side panel that runs your work
Claude Artifacts and ChatGPT Canvas turned chat into a workspace. Code runs. Documents render. Edits happen in place. This is where AI stops being chat and starts being a tool.
::part of the AtomEons /learn curriculum · 45 lessons · 5 levels · cc-by 4.0