Bible Network Crypto DeFi Onchain RWA AI Agent Stablecoin Chain SAFU CryptoTax DeFAI AGI Claude Me Claude Skill Claude Design Claude Cowork
Independent Media
Not affiliated with any project
Let Claude Do the Work, Not Just Answer
claudecowork-me.com
LATEST
Recruitment Screening Workflow: Using Claude to Compress Two Days of Resume Screening Into Half a Day  ·  Claude × Google Calendar: Let AI See the Full Picture of Your Schedule — From Being Driven by Your Calendar to Actively Owning Your Time  ·  Claude Workplace Features in 2026: MCP Matures, Memory Deepens — Time to Upgrade How You Work  ·  Performance Self-Review Scene: Why You Never Know How to Write It Each Year — and How Claude Helps You Make Your Results Visible  ·  Difficult Conversation Email Scene: Bad News, Apologies, Refusals — Let Claude Help You Find That Hardest-to-Master Tone  ·  Building a Personal Knowledge Management System with Claude: Stop Letting What You Read Disappear
Glossary · prompt-techniques

Iterative Prompting

prompt-techniques 新手

30-Second Version · For the impatient
Instead of treating Claude as a 'machine that must give perfect answers in one shot,' treating a conversation as a multi-round collaborative process — get an initial output, then use follow-up instructions to refine iteratively until you reach what you actually want. Like having a back-and-forth discussion until satisfied, rather than expecting someone to say exactly what you need in their first sentence.
Full Explanation +
01 · What is this?

What's the fundamental difference between iterative prompting and 'starting over'? Why is iteration more effective?

The fundamental difference: whether you preserve and leverage previous context.

When you start over, Claude has zero memory of your previous output, what you didn't like about it, or the context you already conveyed. You must rebuild all background, and you often aren't sure 'how to phrase this differently to avoid the same problems,' resulting in: some old issues get fixed in the new output, but new ones appear.

The core advantage of iterative prompting is progressive refinement: Claude remembers what you said and what changes have been made, so each follow-up instruction builds on the previous version — fixing one thing won't cause regression somewhere else. Like repeatedly discussing the same draft with someone, rather than asking them to write a completely new one each time.

Another practical advantage: through iteration you develop clearer understanding of what you actually want. The first output may be imperfect, but it lets you say 'not like this — I want it to feel more like this' — that ability to articulate preferences only after seeing something concrete is an important reason iteration is more efficient than one-shot prompting.

02 · Why does it exist?

Is there a formula for good follow-up instructions? How do I phrase them so Claude knows exactly what to change?

Good follow-up instructions have one core principle: clearly state 'what location' has 'what problem,' and what you want it changed to. Not all three elements are required, but more elements = more precise revision.

Most effective follow-up instruction format (from most to least efficient):

'[Specific location] + [problem description] + [desired direction]' Example: 'Third paragraph feels too academic — please rewrite it in more conversational, direct language, like talking to a business partner.' All three elements present; revision direction is very clear.

'[Problem description] + [desired direction]' Example: 'Overall tone too formal — please shift to semi-formal, like a smart friend giving advice.' No location, so Claude adjusts comprehensively — sometimes goes a bit too far.

'[Only desired direction]' Example: 'Please make it more concise.' Claude can guess your direction but may guess wrong about what to cut and by how much.

Common high-efficiency follow-up examples:

  • 'Second paragraph is over 100 words — compress to under 50, keeping the core point'
  • 'Opening feels formulaic — start with a specific question or scenario instead'
  • 'Ending has no action guidance — add one clear next-step recommendation'
  • 'Data section doesn't need explanation — reader has background knowledge, just present the numbers'
  • 'Sounds too AI-written — add one or two concrete examples or analogies to make it feel more human'
03 · How does it affect your decisions?

How many iterations should happen in one conversation? Are there cases where 'too many iterations' actually stops working?

Signs that after 3–4 iterations things still aren't right:

  • Your 'desired outcome' isn't yet clear to yourself — if you aren't sure what you want, each follow-up is exploratory and efficiency is low. Fix: spend 2 minutes clarifying what the final version should look like, then resume iterating.
  • The problem is in the prompt's structure (e.g., your role setting and output format have fundamental contradictions) — not fixable through follow-ups alone. Fix: open a new conversation and redesign the prompt structure from scratch.
  • Your follow-up instructions are correcting different parts each time with no cumulative direction — fixed tone, then structure next time, then tone again. Fix: decide on the single most important issue, resolve it, then continue.

How to know when iteration is 'done enough': When the output you receive needs less than 30 seconds of manual adjustment (add a few words, swap a term) before you can use it — iteration is complete.

When to open a new conversation instead of continuing to iterate: When the conversation is already very long (20+ turns), when you notice output quality starting to decline (Claude may be hitting Context Window limits), or when your task direction has completely changed.

04 · What should you do?

What tasks is iterative prompting best suited for? Which tasks isn't it suited for?

Best suited for iteration: Any task where 'you know good from bad but can't clearly specify requirements' — writing and text refinement (tone, style, voice calibration), proposal and report structure (is the overall structure clear), visual or creative tasks (Claude generates descriptions, then progressively adjust). These tasks' quality standards are usually 'you know it when you see it,' so iteration is the most natural way of working.

Secondarily suited for iteration: Tasks with clearly specified format requirements (e.g., filling in fixed templates) — these are better handled with a good System Prompt or Few-Shot prompt in one pass. But if the first output doesn't fully meet the format, iteration is still more efficient than starting over.

Not suited for iteration: Tasks requiring 'all or nothing' correctness — mathematical calculations, code (logic errors are wrong regardless of tone), queries requiring real-time information (iteration won't give Claude knowledge of post-cutoff events). If the first output has fundamental errors in these tasks, supply correct information and open a new conversation — don't use follow-up instructions to 'cosmetically fix' a fundamentally wrong output.

Real-World Example +

Ms. Sun is a marketing manager at a B2B software company, preparing a client announcement email for an upcoming new feature. She has a feature description, target customer analysis, and some past examples she liked — but isn't sure how to calibrate the email's tone and structure.

First prompt: 'We're launching a new automated reporting feature to help existing enterprise clients reduce time spent manually compiling weekly reports. Please write an announcement email.'

Claude produced a complete email with clear structure, but two problems: ① tone too formal — more like a legal notice than client communication; ② all feature details listed — too long, clients won't finish it.

First follow-up: 'Tone too formal — please make it more relaxed, like sharing good news with a long-time client. Feature details don't need to all be listed — only keep the single most important benefit (the time savings), remove the rest.'

Claude produced v2: tone noticeably more relaxed, much shorter — but Ms. Sun felt the opening hook wasn't compelling enough, and the closing had no clear CTA.

Second follow-up: 'Change the opening — don't start with "we're excited to announce," switch to directly naming the client pain point (how much time they spend on manual reports weekly). Add a specific CTA at the end: invite them to register for next Tuesday's feature walkthrough Webinar, with a link placeholder.'

V3 output arrived. Ms. Sun spent 20 seconds filling in the Webinar link, added the client's name, and sent it. Three iterations total, first prompt to send-ready email in under 10 minutes.

The point: if Ms. Sun had started over after being unsatisfied with v1, she'd have to guess again 'how to phrase it so tone, length, and hook are all right' — and might not guess correctly. Iteration makes each step a clear directional correction, not a new guess.

Diagram
迭代提示 vs 一次提示:工作流比較左邊展示「一次提示法」的問題(期待完美輸出 → 不對就從頭重試),右邊展示「迭代提示法」的正確流程(草稿 → 追加指令修改 → 精化 → 可用輸出)。One-Shot vs Iterative PromptingOne-Shot (common but inefficient)Prompt: "Write a perfect client email"Output: decent but not quite right(tone off, too long, wrong emphasis)❌ "Not right" → start over entirelyNew prompt from scratchAnother output: still not perfectRepeat cycle... wasted timeIterative (effective)Prompt: "Draft a client email about X"Output v1: good structure, tone off→ useful starting pointFollow-up: "More casual, cut paragraph 2"Output v2: tone right, length better→ one more adjustmentFollow-up: "Add a specific next step at end"✓ Output v3: ready to sendClaude Cowork Me · claudecowork-me.com
Feel free to share. Please credit the source.
Common Misconceptions +
✕ Misconception 1
× Misconception 1: Iterative prompting means 'the first prompt doesn't need to be written carefully.' Wrong — first prompt quality still matters because it sets the direction and framework for the entire conversation. If the first prompt gives Claude a wrong task understanding (e.g., completely wrong target audience), subsequent iterations are patching on a wrong foundation — low efficiency. Iteration's value is refinement and elaboration, not recovering from fundamental errors.
✕ Misconception 2
× Misconception 2: More follow-up instructions always mean better final output. This isn't linear. Follow-up instructions typically deliver highest value in the first 3–4 rounds (each change brings obvious improvement), but marginal returns decline after that — especially if you keep revising without a clear 'done condition,' you may enter a cycle of 'keep revising, increasingly unsure of what you want.' Define your done condition before starting to iterate.
The Missing Link +
Direct Impact

The core trade-off: flexibility vs. upfront clarity.

Iterative prompting means you don't need to specify all requirements upfront — you can 'adjust as you go.' This is a significant flexibility advantage, especially for tasks you haven't fully thought through yet, or that are hard to define in advance with words.

The cost: if your initial prompt is poor quality or fundamentally wrong in direction, no amount of iteration will reliably produce good results — because iteration refines within the initial framework, it doesn't rebuild from zero.

Optimal usage strategy: use a good-enough (70/100) initial prompt to quickly get a first draft, then push quality to 90/100 through 2–3 precise iterations. Don't spend effort making the initial prompt perfect (100/100), and don't expect iteration to reach 90/100 from a 30/100 initial prompt.

Ask a Question
Please enter at least 10 characters
More Related Topics