Blog
What deliberate AI users are reading
Model techniques and practical guides, distilled drop by drop.
Do failed AI requests cost credits? What to check before you subscribe
Being charged for an AI answer you never got is one of the most common complaints about credit-based AI services. Here is what should and should not use credits, how Essevin handles errors, stopped replies and oversized requests, and how to check it yourself.
Poe's free plan is now 300 points a day. What does HK$28 a month get you instead?
Poe's free allowance dropped from 3,000 to 300 points a day in March 2026. If that no longer covers your day, here is what Essevin's HK$28 Taster plan includes, how many messages and images it works out to, and when it is not enough.
ComparisonLooking for a Poe alternative in Hong Kong? What to compare before you switch (2026)
Since Poe cut its free daily points in March 2026, more Hong Kong users are looking around. This guide lists the questions that matter when you compare AI subscriptions: what a message really costs, the per-message ceiling, payment and currency, what happens to unused credits, and where Essevin is and is not the better fit.
GuideWhy AI credits run out faster in long chats, and how to make them last
On credit-based AI services, every new message re-sends the whole conversation, so the twentieth message costs several times the first. Here is the arithmetic, a worked table for Claude Opus 5.5 and GPT-6.1 Sol, and five habits that make a monthly allowance last.
EssevinEssevin subscriptions are open: Claude, GPT, images and video on one monthly plan
Essevin subscriptions are now open. One monthly plan, priced in Hong Kong dollars, covers Claude, GPT, GPT Image and video models from one shared credit pool. Plans start at HK$28 a month, are paid by card and can be cancelled anytime in the console.
AI
Fable 5.1 and GPT Astra are now supported: one Essevin subscription for your next AI workflow
Essevin now supports Fable 5.1 and GPT Astra, with subscription plans, now open, that bring Claude, GPT and other models, shared monthly points, chat, images and video into one account.
AI
A Reproducible Blind Test for High-Risk Customer Replies: Publish the 100-Point Rubric Before the Result
A reproducible protocol for comparing AI-written high-risk customer replies using one synthetic incident, identical prompts, anonymous labels, a five-dimension 100-point rubric, counted revision rounds, and published raw outputs. No model result is reported until the runs are completed and documented.
AI
Before an Insurance Meeting: A Five-Step AI Workflow for a Needs Analysis Brief
Turn anonymised policy information and meeting notes into a traceable Needs Analysis Brief, information-gap list, follow-up questions and message draft. This workflow includes an editable prompt and clear boundaries for privacy, product advice and authorised human review.
AI
Healthcare Administration: What Can AI Handle in Rosters and Patient Guidance? Draw Three Lines First
AI can organise administrative roster data, identify missing fields, and turn approved patient guidance into a readable draft. It should not diagnose, triage, give treatment or medication advice, decide clinical rostering, or send unreviewed messages to patients.
AI
Do Not Ask AI for a Legal Answer First: Use a Risk Map to Prioritise a Long Contract
AI can map clauses, quote supplied text against an existing review lens, and organise questions for a long contract. It cannot determine legal effect or replace legal advice. This workflow keeps confidentiality, traceability, and qualified human review in the process.
AI
One Deck, Three Audiences: Build This Message Brief Before Asking AI to Rewrite
Leadership, clients, and delivery teams need different answers from the same campaign deck. Start with a traceable Message Brief, then use AI to create three source-bound outlines without inventing claims.
AI
An HR Template Factory: Turn One Job Brief into a JD, Interview Guide, and Scorecard
Start with one verified Job Brief, then use the same competency chain to draft a Job Description, structured interview questions, and an anchored scorecard without losing traceability.
AI
Helping with Primary Maths: Make AI Ask Before It Explains
Give AI the school level, full problem, and the child’s attempt, then make it ask one diagnostic question at a time, reveal hints gradually, and verify the method before offering a similar practice problem.
AI
The Role + Example Prompt Pattern That Makes AI Outputs More Consistent
“Write professionally” is too vague. Assign a useful working role, provide one or two representative examples, and add an acceptance check so an AI model has a clearer target and safer boundaries.
AI
Before Renewing Your Broadband, Use AI to Prepare the Conversation
The hardest part of a broadband renewal call is tracking the contract term, total cost, bundled services and your own limits at the same time. This guide provides a copy-ready AI prompt, a 90-second opener, four response branches and a comparison table.
AI
What Should You Ask AI First? Ten Openers That Work Immediately
A blank AI chat does not require prompt-engineering jargon. Ten copy-ready opening questions cover explanation, sorting, comparison, planning and verification, so the model can produce a useful first draft instead of guessing your intent.
AI
Why AI Sometimes Miscounts the r's in “strawberry”
“strawberry” contains three r's, yet an AI model may occasionally give a confident wrong count. The reason is not a single mysterious bug: tokenisation, character-level operations and language-model prediction are different jobs. This guide shows three ways to verify the answer.
AI
Claude Code /resume: Two Ways to Pick Up Yesterday's Work
Continue a half-finished travel itinerary, CV revision or product comparison without explaining everything again. This guide shows when to use /resume, --continue, /compact, /clear and session names, with practical everyday examples and the limits of session recovery.
AI
Five MCP Servers Ordinary People Can Actually Use
MCP is not only for programmers. These five popular GitHub projects can help with live web research, everyday browser work, mixed document formats, WhatsApp history, and Notion. This guide explains the useful hook, setup difficulty, and privacy trade-off behind each one.
AI
Stop Saying "Write Me a...": The Four Ingredients of a Prompt That Works
The same AI can produce brilliant work for one person and generic filler for the next. The difference is rarely the model — it's whether your prompt specifies a format. Four ingredients, three before/after rewrites, and a fill-in template to turn "write me a..." into an instruction the AI can actually execute.
AI
Claude Code's Plan Mode: Review the Plan Before It Touches Anything
The most expensive AI mistake isn't one wrong step — it's ten wrong steps executed in a row before you notice. Plan Mode makes Claude hand you a plan first and act only after you approve it. Here's how to turn it on and off, what your four approval options actually are, and why it's just as useful outside of coding.
AI
Meeting Minutes in Twenty Minutes: A Four-Step AI Workflow for Admin Staff
The slow part of writing minutes is not typing — it is restructuring a scattered discussion into decisions and owners. This guide gives admin and office staff a repeatable four-step workflow with copy-paste prompts, cutting a two-hour task to a ten-minute draft plus ten minutes of checking, and names the three kinds of meeting you should not hand to AI.
AI
What a Context Window Actually Is — and Why a Bigger One Doesn't Mean a Better Memory
When an AI forgets what you told it an hour ago, that is not a bug — the desk is full. This guide explains what a context window is, why token counts matter, why million-token windows still lose information in the middle, and five habits that immediately improve long conversations.
Claude Code
Set Up Claude Code from Hong Kong or China: The Complete Four-Step Path
Anthropic does not serve Hong Kong or China, but you do not need a VPN or any workaround to run Claude Code. This guide covers the full path — install, register, set two environment variables, verify — in four steps, no coding background required.
AI
The Resume Emergency Room: One CV, Three Tailored Versions in Half an Hour
Recruiters spend an average of 7.4 seconds on the first scan of a resume. Instead of mass-sending one CV to thirty jobs, tailor it to three. This guide gives you four copy-paste AI prompts — decode the job ad, map your gaps, rewrite with facts intact, then scan it through a hiring manager's eyes.
AI
Gemini 3.6 Flash: The Workhorse Gets Cheaper — and Hong Kong Can Use It Today in the Gemini App
Google shipped three models on July 21 — Gemini 3.6 Flash cuts output pricing from $9 to $7.50 per million tokens and uses 17% fewer tokens for the same work, while the flagship 3.5 Pro is still missing. What the release actually means for users in Hong Kong and China.
LLM
The July 2026 LLM Tier List: From GOAT to Cooked
GPT-5.6, Grok 4.5, Muse Spark 1.1 and Kimi K3 all shipped within a month, while Gemini 3.5 Pro missed its third deadline. We rank the mainstream frontier models of July 2026 on capability, price and real-world availability — and unpack the four most common mistakes people make when reading leaderboards.
AI
Why AI Makes Things Up — and Six Ways to Catch It
AI hallucination is not a bug — it is the personality of a technology built to predict the next word. This guide explains why large models fabricate facts, which six question types are highest-risk, and six defenses you can apply today.
AI
An Open-Source Model Just Beat the Paid Flagship — What That Means for You
Moonshot AI's open-source Kimi K3 hit #1 on the Frontend Code Arena within hours of release, overtaking Claude Fable 5. Here is what the win actually measures, where leaderboards mislead, and how to pick models by task now that open and closed models are this close.
AI
Fable 5 Joins Max Plans at Half the Limits: Top-Tier AI Pricing Is Shifting to Pay-As-You-Go
Anthropic announced that from July 20, Claude Fable 5 will be included in Max and Team Premium plans — at 50% of standard limits, while Pro users stay on usage credits. Here is the 39-day timeline, why flat-rate plans cannot absorb frontier models, three common misreadings, and what this means for users in Hong Kong and China.
AI
Why Claude Code Gets Expensive — and the Three Commands That Fix It
Most Claude Code cost and "memory loss" problems come down to context management. Here is how the context window actually bills you, and when to use /context, /compact, and /clear.
Tutorial
Claude Code Setup in China: Complete Guide — from Registration to First Autocompletion in 10 Minutes
No VPN, no code changes: create an API key for Claude, then use one-click setup or two environment variables to connect Claude Code to Essevin. This guide covers registration, creating your key, configuration and verification, plus the three most common pitfalls.
Review
GPT-5.6 vs Claude Sonnet 5 for Chinese Project Code: Which Should You Choose?
Both flagship coding models are available in one Essevin account, drawing on the same points. Here's what matters in practice about completion quality, instruction following, and token consumption — plus our selection advice.
Practice
How Much Can Prompt Cache Save You? Mechanics, Real-World Hit Rates, and Three Writing Techniques
Cache hit rate determines your bill. Here's how prompt caching actually works, the real hit rates we see in conversational tools, and three prompt organization techniques that can double your cache efficiency.
Product
Drop PDFs and Excel Files Straight Into Your Model: The Right Way to Use Attachments in AI Chat
Spreadsheets, scanned PDFs, raw email, saved web pages — which ones go straight to the model, and which need preprocessing? Here's everything about AI Chat's attachment capabilities and how to use them effectively.
Tutorial
Seedance 2.0 Video Generation: Getting Started in Creative Studio
Make Seedance videos in Essevin's Creative Studio without writing code: choosing a model, how resolution and duration affect points, prompting tips, and saving your finished clips.
Practice
One Account, Four Key Purposes: Pick the Right Key and Model to Make Your Monthly Points Last
Essevin API keys are created by purpose — Claude, GPT, Images or video — and every key draws from the same monthly points. Here's how purposes, model tiers and point usage fit together, plus point-saving setups for three typical user profiles.