← All Conversations
July 04, 2026

I was prompting Claude 4.8 completely wrong

Claude 4.8 prompting specificity AI productivity Anthropic

Summary

Claude 4.8 marks a sharp shift from earlier versions: it no longer fills in gaps or infers intent, it executes exactly what the user types. This change renders the old habit of vague, half‑finished prompts ineffective and makes specificity the decisive factor for output quality. The author distilled Anthropic’s 31‑page prompting guide into ten actionable rules that directly address this new behavior. First, name the desired output rather than the task—specify format, length, and detail (e.g., “review this contract, flag risks per clause, rate severity 1‑5, return as a table”). Second, cap the response length yourself; instead of “summarize this,” prescribe “5 bullets, each under 15 words, starting with an action verb.” Third, replace negative constraints with positive directives (“write in plain English a 16‑year‑old could read aloud”) because affirmatives are far more likely to be honored. Fourth, make every verb concrete and actionable (“go to Gmail, find the contact, write a send‑ready reply under 90 words, tone confident, casual”). Fifth, explicitly invoke web search when up‑to‑date information is needed, as Claude 4.8 calls fewer tools by default. Sixth, feed the model samples of your own voice to preserve tone, since the new model is notably direct and low‑on‑emoji. Seventh, urge the model to “go beyond the basics” to elicit richer, more creative outputs. Eighth, activate deeper reasoning by appending “Think before answering (maximum reasoning)” to any complex prompt—a free quality boost many overlook. Ninth, convert frequently used prompts into reusable skills to avoid repetitive rewriting. Tenth, spell out every element—output, order, length, tone, format—because the model will not infer missing details. Applying even a subset of these rules yields immediate gains: adding the reasoning cue, swapping a negative for a positive instruction, and defining output format upfront transform mundane tasks like email cleanup or document summarization into noticeably sharper results. The underlying lesson is that prompt engineering has become the highest‑leverage skill in AI work; mastery lies not in secret models or tools but in crystal‑clear, instruction‑dense prompting. Beyond prompting, the note hints at broader market movements—OpenAI and Anthropic eyeing public listings, and a MarketBeat report highlighting seven AI‑related stocks poised to benefit from the next investment wave. It also flags emerging security concerns: as Claude evolves into an agentic platform with MCP connections and autonomous skills, traditional security teams may lack the visibility and controls needed to govern such workflows, pointing to solutions like Harmonic Security for CISO oversight. The core takeaway remains: with Claude 4.8, the burden of clarity shifts squarely onto the user, and precise prompting is now the key to reliable, high‑quality AI output.

Hey

I typed a lazy prompt into Claude last week, hit enter, and quietly hoped it would read my mind.

It did not.

I have been doing this for two years. Type something half-finished, let the model fill in the blanks, accept whatever comes back. That habit worked fine on the old versions. They guessed what I meant and usually guessed right.

Claude 4.8 does not guess anymore.

It does exactly what you type. Nothing more. Nothing less.

That one change rewrites everything about how you should prompt. And most people have not adjusted yet. They are still writing loose prompts from 2024 and wondering why the output feels flat.

Anthropic put out a 31 page prompting guide. Someone smart squeezed it down to 10 rules you can use today. I read the whole thing so you do not have to. Here is what actually matters.

Rule 1: Name the output, not the task

Do not say "review this contract" and pray. Spell it out. "Review this contract. Flag risks per clause. Rate severity 1 to 5. Return as a table." You get structure because you asked for structure.

Rule 2: Cap the length yourself

Saying "summarize this" on a 40 page report lets the model decide how long the answer should be. Box it in. "5 bullets. Each under 15 words. Start each with an action verb." You set the size, not the input.

Rule 3: Flip every negative into a positive

Telling Claude "do not use jargon, do not be salesy" does not stick. State what you DO want instead. "Write in plain English a 16 year old could read aloud." Positive instructions land. Negative ones slip.

Rule 4: Make every verb ship something

"Can you help me with the email?" is too soft. Turn it into a chain of actions. "Go to Gmail. Find the contact. Write the send ready reply. Under 90 words. Tone: confident, casual." Every verb does work.

Rule 5: Force the web search

Here is a detail I did not know. Claude 4.8 calls fewer tools than 4.6 did. So you have to push it. "Use web search aggressively. Verify every claim with at least 2 sources." If you do not push, it will answer from memory.

Rule 6: Feed it your voice

4.8 is direct, with almost zero emojis. If you miss the warmer old tone, do not complain about it. Paste 2 or 3 sentences written exactly how you sound, then tell Claude to match the rhythm. Save those sentences. Reuse them forever.

Rule 7: Ask it to go further

When you request "a landing page," you get the bare minimum. There is one line pulled straight from Anthropic's own doc that fixes this. "Go beyond the basics." Drop it on every creative task and watch the output change.

Rule 8: Turn on thinking

This one surprised me. Claude 4.8 does not reason by default. Add this to the end of your prompt. "Think before answering (maximum reasoning)." It is a free quality upgrade, every single time, and most people never use it.

Rule 9: Build a skill from repeat prompts

If you are rewriting the same prompt 14 times a week, stop. A skill is a command with the instructions already built in. Write the same prompt twice? Make it a skill. Future you will thank present you.

Rule 10: Spell out everything

This is the rule that ties it all together. Old Claude guessed. New Claude does exactly what you typed. So define your output, your order, your length, your tone, your format. If you do not say it, you do not get it.

### The AI IPO Rush Is Coming

OpenAI and Anthropic could bring a new wave of AI attention to the public markets. But investors don’t have to wait for the IPOs.

MarketBeat’s [7 AI Stocks to Buy Now](http://marketbeat.com/newsletter/pdfoffer.aspx?offer=7aistocks&RegistrationCode=Beehiiv-BUBDNZO6MS-7aistocks&_bhiiv=opp_9d958562-a2cd-4a29-9c84-474d1401fb69_7d4f8797&bhcl_id=5bcdd182-f454-46ab-8ab6-f6e877811820_f672f2b6-1e60-4422-8448-ee13d3aa1099_22c35bc7-5e17-4448-baa5-49c4bf23f93e) report reveals 7 publicly traded companies positioned to benefit from the next phase of AI investment.

[Send My Free Report](http://marketbeat.com/newsletter/pdfoffer.aspx?offer=7aistocks&RegistrationCode=Beehiiv-BUBDNZO6MS-7aistocks&_bhiiv=opp_9d958562-a2cd-4a29-9c84-474d1401fb69_7d4f8797&bhcl_id=5bcdd182-f454-46ab-8ab6-f6e877811820_f672f2b6-1e60-4422-8448-ee13d3aa1099_22c35bc7-5e17-4448-baa5-49c4bf23f93e)

Why this list actually matters

Look at all 10 rules together and one theme shows up.

Every single one traces back to the same behavior change. Claude 4.8 stopped filling in the gaps for you.

That sounds like a downside. It is not.

It means you finally get predictable output. The lazier your prompt, the more you are gambling. The clearer your prompt, the more the model just does what you asked. Specificity is the whole game now.

We spent years training ourselves to write loose prompts and let the AI guess. With 4.8, that habit costs you quality on every single request.

Tightening up how you ask is the highest leverage skill in AI right now. Not a new tool. Not a secret model. Just clearer instructions.

If you steal only three things from this list, make it these. Add "Think before answering (maximum reasoning)" to your next complex prompt. Replace one negative instruction with a positive one today. Define your output format upfront, whether that is a table, five bullets, or a word count.

Try them on something boring. Cleaning up an email. Summarizing a doc. You will feel the difference inside one prompt.

Stay curious, talk to you tomorrow.

### Claude is not just a chatbot anymore. Is your security team ready?

Claude.ai is one thing. Agentic workflows, MCP connections, ungoverned skills taking actions across your data? That's a different conversation — and most security teams aren't equipped for it.

Harmonic Security gives your CISO the visibility and controls to say yes confidently.

[Share this Claude guide with security.](https://www.harmonic.security/securing-claude-demo-lp?utm_term=BUBDNZO6MS&utm_source=beehiiv&utm_medium=newsletter&utm_campaign=claude&_bhiiv=opp_77ea4d7c-ef7a-4397-baf6-cbc46b7f5bd1_85dd9654&bhcl_id=9181e42b-be75-4b55-ad46-c6d026e27052_f672f2b6-1e60-4422-8448-ee13d3aa1099_22c35bc7-5e17-4448-baa5-49c4bf23f93e)

[Help Security Say Yes](https://www.harmonic.security/securing-claude-demo-lp?utm_term=BUBDNZO6MS&utm_source=beehiiv&utm_medium=newsletter&utm_campaign=claude&_bhiiv=opp_77ea4d7c-ef7a-4397-baf6-cbc46b7f5bd1_85dd9654&bhcl_id=9181e42b-be75-4b55-ad46-c6d026e27052_f672f2b6-1e60-4422-8448-ee13d3aa1099_22c35bc7-5e17-4448-baa5-49c4bf23f93e)