--- title: "Iterating: the art of the follow-up | Optimize All Academy" description: "The first answer is a draft Professionals rarely accept the first result. They treat it as a draft and steer. Iterating well is often faster than trying…" url: https://optimizeall.com/learn/prompt-engineering-foundations/iterating-in-conversation updated: 2026-10-05 --- Prompt Engineering Foundations · Iterating and formatting outputs · lesson 5 of 16 · 10 min # Iterating: the art of the follow-up ## The first answer is a draft Professionals rarely accept the first result. They treat it as a draft and steer. Iterating well is often faster than trying to write a perfect prompt up front. ## Five follow-up moves **1. Adjust.** Change one thing at a time so you can see the effect. ```text Good. Make it 30% shorter and replace the second paragraph with a customer example. ``` **2. Point to specifics.** Quote the part you want changed. ```text The line "we are passionate about quality" feels generic. Replace it with something specific about our hand-stitched seams. ``` **3. Ask for options.** Instead of one version, ask for several and pick. ```text Give me 3 alternative opening lines: one funny, one emotional, one direct. ``` **4. Explain what is wrong and why.** The AI learns your taste within the conversation. ```text This sounds too salesy for our audience of nurses, who are sceptical of marketing. Make it more practical and humble. ``` **5. Combine.** Take the best parts of different versions. ```text Use the opening from version 2 and the ending from version 3. ``` ## When to start fresh Long conversations can drift. The AI may hold on to earlier instructions you have abandoned, or mix details from different drafts. Start a new chat when: - you have changed direction significantly - the answers are getting worse or repetitive - the conversation has become very long When you start fresh, write a new, better prompt that includes everything you learned: "Write X, for Y, in style Z, avoiding A and B." That improved prompt is now reusable. ## Ask the AI to critique itself A simple, effective habit: ```text Before I use this, review your draft against my requirements: under 150 words, mentions the Friday deadline, friendly tone. List anything that doesn't meet them, then fix it. ``` This catches missed requirements. It is not perfect, especially for facts, so you still need to check anything important yourself. ## Ask the AI to improve your prompt You can also ask for help with the prompt itself: ```text Here is a prompt I use to write weekly team updates. Suggest how to make it clearer and more specific, then show me the improved version. ``` This is a great way to learn, because you see what the AI thinks is missing. ## Worked example: iterating an event invitation A community organiser in Karachi drafts a volunteer invitation. Round 1: "Write an invitation for volunteers for a beach clean-up on Saturday." Result: generic and long. Round 2: "Make it under 80 words, suitable for WhatsApp, and add the time (7-10am), meeting point (Sea View, near the camel rides) and what to bring (water, hat, gloves provided)." Result: much better, but a bit formal. Round 3: "Make it more energetic and friendly, with one emoji, and add a line asking people to reply 'IN' to confirm." Result: ready to send. Round 4 (saving for later): "Now write me a reusable prompt I can use for future clean-up invitations, with blanks for date, time and location." In four short messages, the organiser has a finished message *and* a template for next time. ## Save what works Keep a simple document of prompts that worked well, with a note of what they are for. Over time you build a personal library, and your first attempts get better and better. Many AI tools also let you save custom instructions or reusable prompts; check your tool's settings. ## Common iteration mistakes - Changing many things at once, so you cannot tell what helped. - Saying "no, that's wrong" without saying what is wrong. - Continuing a confused conversation instead of starting fresh with a better prompt. - Forgetting to check facts after several rewrites, since errors can creep in. ## Hands-on: the three-message workout Practise iteration deliberately with this routine on any real draft: ```text Message 1 (the brief): Write a 120-word LinkedIn post announcing that I passed my Google Ads certification. Audience: small business owners in the UK who might hire me. Tone: confident, not boastful. Message 2 (point to specifics): The opening "I'm thrilled to announce" is overused. Give me 3 alternative first lines that start with a benefit for the reader. Message 3 (combine and finish): Use option 2 as the opening, keep the rest, and end with a question that invites comments. Then list what you changed. ``` Asking the AI to list its changes makes it easy to review edits instead of re-reading everything. ## Editing in place Many assistants now open longer drafts in a side panel or document view (for example a canvas or artifact-style editor) where you can highlight a sentence and ask for a change to just that part. Use it for long documents: targeted edits keep the parts you already like and avoid the whole text being rewritten each time. ## Branching instead of arguing If an answer goes in the wrong direction, you do not need to argue with it for five messages. Most assistants let you **edit your earlier message** and regenerate, which creates a clean branch of the conversation. Fix the prompt at the point things went wrong rather than piling corrections on top. ## When iteration is not the answer If you have sent four follow-ups and the answer is still not right, stop and diagnose. Usually one of three things is missing: - **Information** the AI does not have (add context or paste material). - **A clear picture of good** (add an example). - **The right tool or mode** (for a hard calculation or multi-step plan, try a thinking mode; for current facts, turn on web search). Then start a fresh chat with an improved prompt. ## How to measure your iteration skill Keep a tally for a week: how many messages did it take to reach a usable result? Also note which follow-up moves worked best for you. Most people find that "point to specifics" and "explain why" do most of the work, and that their first prompts improve as they learn what they usually forget. ## Video lecture: Iterating: the art of the follow-up Video: [Iterating: the art of the follow-up](https://www.youtube-nocookie.com/embed/6Sml7wuPuNM) — The first answer is a draft Professionals rarely accept the first result. They treat it as a draft and steer. Iterating well is often faster than trying… 11 chapters · about 7 minutes · captions and full transcript below. 1. Iterating: the art of the follow-up 2. Moves 1 to 3 3. Moves 4 and 5 4. Worked example: beach clean-up invite 5. Drift, branching and editing 6. Stuck after four messages? 7. Two bonus habits 8. The three-message workout 9. Example 1: a party invitation 10. Example 2: a gym promotion (illustrative) 11. Recap ## Lecture transcript ### Iterating: the art of the follow-up Professionals rarely accept the first answer from an AI, and neither should you. In this lecture you will learn five follow-up moves that turn a mediocre draft into a finished piece, when to stop arguing and start a fresh chat, how to use editing and branching features, and how to turn a successful conversation into a reusable template. By the end, you will get usable results in fewer messages. ### Moves 1 to 3 Move one: adjust. Change one thing at a time, so you can see its effect. Make it thirty percent shorter and replace the second paragraph with a customer example. Move two: point to specifics. Quote the part you want changed. The line we are passionate about quality feels generic, replace it with something about our hand-stitched seams. Move three: ask for options. Give me three alternative opening lines, one funny, one emotional, one direct. Choosing is faster than describing. ### Moves 4 and 5 Move four: explain what is wrong and why. This sounds too salesy for our audience of nurses, who are sceptical of marketing, make it more practical and humble. When you give the reason, the AI can fix the whole draft, not just one line. Move five: combine. Use the opening from version two and the ending from version three. Put these five moves together and you will rarely need more than three messages to get something you are happy with. ### Worked example: beach clean-up invite Watch it in practice. A community organiser in Karachi wants volunteers for a beach clean-up. Round one: write an invitation for volunteers for a beach clean-up on Saturday. The result is generic and long. Round two: make it under eighty words for WhatsApp, add the time, seven to ten in the morning, the meeting point at Sea View, and what to bring, water and a hat, with gloves provided. Better, but a bit formal. Round three: make it more energetic, one emoji, and ask people to reply IN to confirm. Ready to send. And round four: write me a reusable prompt for future clean-ups, with blanks for date, time and location. Now she has a message and a template. ### Drift, branching and editing Long conversations can drift. The AI may hold on to instructions you abandoned, or mix details from different drafts. Start a new chat when you have changed direction, when answers are getting worse or repetitive, or when the conversation has become very long. And there is a neater option in many assistants: instead of piling corrections on top, edit your earlier message and regenerate. That creates a clean branch from the point where things went wrong. For long documents, use side-panel editors, where you can highlight a sentence and change just that part. ### Stuck after four messages? If four follow-ups have not fixed it, stop and diagnose. Usually one of three things is missing. Information the AI does not have, so add context or paste material. A clear picture of good, so add an example. Or the right tool, so for a hard calculation try a thinking mode, and for current facts turn on web search. Then write a fresh, improved prompt that includes everything you learned. That improved prompt is now reusable. ### Two bonus habits Two more habits pay off quickly. First, ask the AI to critique its own draft against your requirements: under one hundred and fifty words, mentions the Friday deadline, friendly tone, list anything that does not meet them, then fix it. It catches missed requirements, though not every factual error, so still check facts. Second, ask it to improve your prompt: here is a prompt I use for weekly team updates, suggest how to make it clearer, then show me the improved version. You learn what you usually forget. ### The three-message workout Try this three-message workout. Message one is the brief: write a one-hundred-and-twenty-word LinkedIn post announcing that I passed my Google Ads certification, for small business owners in the UK who might hire me, confident but not boastful. Message two points to specifics: the opening I'm thrilled to announce is overused, give me three alternative first lines that start with a benefit for the reader. Message three combines and finishes: use option two as the opening, keep the rest, end with a question that invites comments, and list what you changed. Asking for a list of changes makes review fast. ### Example 1: a party invitation A simple example to feel the rhythm. You ask for a birthday party invitation for a seven-year-old. Draft one is fine but long. Follow-up one: make it half the length and more playful. Follow-up two: the theme is dinosaurs, add one dinosaur joke, and put the time and address on separate lines. Follow-up three: give me two versions, one for WhatsApp and one for a printed card. Three short messages, each changing one thing, and you have exactly what you need. Notice that no single message was clever. The skill is in steering, one clear adjustment at a time. ### Example 2: a gym promotion (illustrative) Now a business scenario, with illustrative numbers. Fatima manages social media for a gym in Manchester and wants a January promotion post. Draft one is generic: new year, new you. She points to specifics: the new year new you line is overused, give me three openings based on our actual offer, which is the first month for nineteen pounds instead of forty-five. She picks the second option, then explains the audience: our members are mostly busy parents who train before work, so emphasise the six a m classes and the free creche. Finally she combines: use the opening from version two with the ending from version three, and add a deadline of the thirty-first of January. Four messages. A post that speaks to real members, with a real offer and a real deadline. ### Recap To recap. Treat the first answer as a draft. Use the five moves: adjust, point to specifics, ask for options, explain why, and combine. Start fresh or branch when a conversation drifts, and diagnose missing information, examples or tools when you are stuck. Save what works. Try this now: take one draft and improve it in exactly three follow-up messages, then ask the AI to turn the final version into a reusable template prompt. Next lesson: getting outputs in exactly the shape you need. ## Key takeaways - Treat the first answer as a draft; iterate by adjusting, pointing to specifics, asking for options, explaining why, and combining. - Start a fresh chat with an improved prompt when a conversation drifts or gets long. - Ask the AI to check its draft against your requirements, and still verify facts yourself. - Save prompts that work to build a personal library. ## Try it Take one draft the AI gave you and improve it in exactly three follow-up messages. Then ask the AI to write a reusable template prompt from the final version. - [Previous: Giving context and examples](https://optimizeall.com/learn/prompt-engineering-foundations/context-and-examples) - [Next: Formatting outputs: getting the shape you need](https://optimizeall.com/learn/prompt-engineering-foundations/formatting-outputs) - [All lessons of Prompt Engineering Foundations](https://optimizeall.com/learn/prompt-engineering-foundations)