by admin | Sep 5, 2026 | Opportunities
You finished a free AI course, you can write a decent prompt, and then a job listing asks for “proven experience with AI.” It’s a frustrating wall. How are you supposed to prove you can do the work when nobody has hired you to do it yet?
The honest answer is that you build the proof yourself. An AI portfolio is simply a small, public collection of things you have made that anyone can open with a link. It matters more than most people expect, because a certificate says you sat through a course, while a project shows you can actually use what you learned. And you can build a solid AI portfolio for free, with no job, no degree, and no expensive tools.
Why an AI portfolio beats a certificate
Certificates are useful, but they mostly prove attendance. A project proves ability. When someone can click a link and see a thing you built, the conversation changes from “trust me” to “look what I did.” Employers and clients trust what they can try for themselves.
From my own experience building websites and small online tools, the thing that got people to take me seriously was never a line on a CV. It was something they could open in a browser and use. A portfolio does the same job for AI skills.
What goes into an AI portfolio?
You don’t need much to start. A strong beginner AI portfolio usually has:
- Two or three small projects you actually finished.
- A short write-up for each one: what problem it solved, what you did, and what you learned.
- Links people can click, such as a notebook, a live demo, or a code repository.
- Optional badges from free courses, kept in their place.
Important tip: one finished project you can explain clearly beats ten half-built ones. Depth is what people remember, not the length of the list.
Start with small, real projects
Pick something you actually care about, then keep it tiny. A good first project can be as simple as taking a public dataset (movie ratings, weather, sports stats) and finding one interesting pattern in it. Or build a custom assistant for a hobby you know well. If you want a gentle starting point, our guide on how to make your own AI assistant for free walks through a project you can finish in an afternoon.
And no, you do not need to be a programmer. Plenty of real projects use no-code tools, prompt libraries, or a clear written analysis. If code feels like a barrier, start with our guide on how to learn AI without coding, then come back and build. If you still need the basics, learning AI for free is a good first step.
Use free platforms to show your work
Once you have made something, it needs a home online. These are all free and widely respected:
- Kaggle: free notebooks that run in your browser, thousands of open datasets, and a public profile. See Kaggle.
- GitHub: free public repositories for any code or files, where a clear README acts as your project’s front page. See GitHub.
- Hugging Face Spaces: when you are ready to go further, you can host a live demo people can actually try, on a free public link. See Hugging Face Spaces.
One habit worth keeping from the security side of my work: only use open datasets or your own data, and never put private, personal, or client information into a public project. Check a dataset’s license before you publish anything based on it.
Enter free competitions for practice and proof
Competitions give you two things at once: a finished project and a story to tell about it. Kaggle’s “Getting Started” competitions, like the well-known Titanic challenge, are built for beginners and never close, so there’s no pressure to rush. Free hackathons and student contests work the same way. We rounded up the best beginner-friendly options in our guide to AI competitions for beginners.
Add free course badges the right way
Badges are a nice supporting detail. On Microsoft Learn, finishing free learning paths earns badges and trophies. Google AI Essentials gives a shareable digital badge through Credly, and Kaggle Learn hands out free certificates too.
Just remember the order of things: a badge supports a project, it does not replace one. Put one or two on your profile, then let your actual work do the talking.
Write up each project so people understand it
The write-up is half the value, and it’s the part most people skip. A recruiter may never run your code, but they will read three clear sentences. For each project, answer three questions: what problem were you solving, what did you build, and what is one thing you learned or would improve next time?
Keep it honest. Don’t claim more than you did. A small, truthful project explained well beats a big one you can’t really talk about.
A simple 4-week plan to start
- Week 1: learn a little and pick one small project idea.
- Week 2: build the smallest version that actually works.
- Week 3: put it on Kaggle or GitHub with a clear write-up.
- Week 4: enter a beginner competition or start project two, then add the link to your CV.
When you do start applying, your portfolio becomes your strongest line. Our guide on how to use AI to apply for jobs shows how to point employers straight to it.
Common Questions
Do I need to know how to code to build an AI portfolio?No. No-code tools, custom assistants, prompt libraries, and clear written analyses all count. Coding helps for some projects, but a well-explained no-code project is still real proof of skill.
How many projects do I need?Two or three finished, well-explained projects are plenty to start. A clear write-up matters far more than the number of projects.
Where should I host everything?Pick one home base people can visit. A GitHub or Kaggle profile works well, and you can add a live demo on Hugging Face Spaces later. Then link to it from your CV and LinkedIn.
Is it safe to put my projects online?Yes, as long as you only use open or your own data. Never upload private, personal, or client information, and read a dataset’s license before sharing results based on it.
Final takeaway
You don’t need permission or a paycheck to start proving your AI skills. Pick one small idea this week, build the simplest version that works, write three honest sentences about it, and put it somewhere with a link. Do that a few times and you’ll have something most applicants never bother to make: real proof you can use AI, not just talk about it.
by admin | Sep 4, 2026 | AI Tools
You open ChatGPT, explain who you are, what you do, and the tone you want. The answer comes back good. Three days later you open a fresh chat and type the same background all over again.
That loop is the quiet reason a lot of people decide AI tools are more trouble than they are worth. The fix is not a cleverer prompt, it is a ten minute setup you do once. This guide shows you how to make your own AI assistant, for free, using a tool you probably already have open, no coding required.
What it really means to make your own AI assistant
When people hear “build your own AI” they picture training a model on a mountain of data. That is not this: you are not building anything from scratch, and you are not touching Python.
You are creating a saved shortcut with a name, a set of standing instructions, and often a few files attached. Every time you open it, the assistant starts with that background already loaded, like briefing a new colleague properly once instead of reintroducing yourself every morning.
This is not the same thing as an AI agent, which goes off and completes tasks on its own. A custom assistant does not act for you, it just stops forgetting who you are. Our guide to AI agents explained simply covers that difference.
Why a saved assistant beats a very long prompt
You could paste your background at the top of every chat. Plenty of people do, but it has three problems.
- You have to remember to do it, and you will not on the day you are rushed.
- Long background eats into the space the model has to work with, a limit we explained in what is a context window. Spending that room on the same introduction every time is waste.
- Small differences creep in. You describe yourself slightly differently each time and the answers drift with you.
A saved assistant fixes all three at once. The instructions sit outside the conversation, they are identical every time, and any files you attach stay attached.
Option 1: ChatGPT Projects
OpenAI calls these Projects, described in its help pages on Projects in ChatGPT as workspaces that keep chats, files and custom instructions in one place. They are available to all free and paid subscription types globally, so you do not need to pay to try one, just be signed in.
- Click New project in the sidebar and give it a name.
- Open the three dot menu, choose Project settings, and write your instructions there. OpenAI notes these apply only inside that project and override your global custom instructions while you are in it.
- Upload your reference files. OpenAI lists the limit as five files per project on a free account, twenty five on Go and Plus, and forty on Pro, Business, Edu and Enterprise.
Projects also keep their own memory of the chats inside them, and a setting can switch a project to project only memory if you would rather it ignored everything else in your account.
Option 2: Gemini Gems
Google’s version is called a Gem. Its getting started guide for Gems describes them as customised versions of Gemini for repetitive tasks or deep expertise in new areas. The only requirements listed are a personal Google Account and being 13 or over, or the applicable age in your country. No paid plan is required.
- In the Gemini web app, click Explore Gems, then New Gem.
- Name it and write the instructions.
- Under Knowledge, add files from your device or from Google Drive.
- Click Save. Google specifically warns that trying your Gem in the preview panel does not save it, which catches a lot of people out.
Two extras help if you are stuck: a button that asks Gemini to rewrite and expand your instructions, and premade Gems (Brainstormer, Coding partner, Writing editor) you can open and copy the pattern from.
Option 3: Claude Projects
Anthropic’s help page on projects, updated in July 2026, says projects are available to all users including free accounts, and that free users can create a maximum of five of them.
A Claude project is a self contained workspace with its own chat history and knowledge base: you upload documents, set project instructions, and every chat inside starts from that base. The heavier retrieval feature for very large amounts of uploaded material is limited to paid plans, and sharing with colleagues is a Team and Enterprise feature.
If you are not sure which of the three to start with, the honest answer is whichever one you already have open. Our ChatGPT vs Gemini vs Claude comparison goes into how they differ in day to day use.
How to write instructions that actually work
This is where most custom assistants fall down: people write “be helpful and professional”, then wonder why nothing changed.
Google’s own guidance on writing Gem instructions splits the job into four parts, and the same four work just as well inside ChatGPT and Claude:
- Persona. The role it should play and how it should speak to you.
- Task. What it should actually produce.
- Context. Your background, constraints and audience, and anything it would otherwise guess wrong.
- Format. Length, structure, bullet points or prose, and what to leave out.
You do not need all four. Two or three specific ones beat a paragraph of vague adjectives every time, the same habits that make a single prompt work. Our guide on writing better AI prompts applies directly here.
A short example you can copy
Say you write lab reports as a final year student. Rather than explaining that every week, the instructions might read:
You help me write and revise undergraduate biology lab reports. Use plain, precise academic English and British spelling. Never invent citations or results. When I paste a draft, point out unclear reasoning and missing method detail first, before you comment on grammar. Do not rewrite my text unless I ask you to. Give feedback as a short numbered list.
Attach your module handbook and marking rubric as files, and every chat in that project already knows the rules you are marked against. You never type any of it again.
What to keep out of your assistant
From my own experience working with websites, online tools and cybersecurity, this is the part people skip. A file you upload is not a one off. It sits there for every future chat until you delete it, and anyone you later share the project with can usually read it too.
Keep out anything you would not want sitting in a cloud account for months: passwords and API keys, ID or passport scans, client contracts you do not have the right to share, medical records, and unpublished confidential work. OpenAI also notes that on Free, Plus and Pro accounts, project information may train its models if “Improve the model for everyone” is switched on, so check that toggle before uploading anything sensitive.
Important tip: before you attach a document, ask yourself one question. Would I be comfortable if this file were still sitting in this account in a year, readable by anyone I ever share the project with? If the answer is no, paste in only the paragraph you actually need instead of the whole file.
Our guide on using AI safely and protecting your privacy goes further on the settings worth changing before you upload anything.
Common Questions
Do I need to pay to make my own AI assistant?No. OpenAI says Projects are available to all free and paid subscription types, Anthropic says projects are available to all users including free accounts with a limit of five, and Google’s Gems guide lists a personal Google Account and a minimum age rather than a paid plan. Paid tiers mainly raise the limits, such as how many files you can attach.
Is this the same as training my own AI model?No. You are not changing the underlying model at all. You are saving instructions and files that get applied at the start of each chat. The model doing the work is the same one everyone else is using.
How many assistants should I make?Fewer than you think. Two or three matching things you genuinely do every week will get used, twelve will not. Start with one and only add another when you catch yourself typing the same background again.
Will my assistant remember what I told it in an earlier chat?That depends on the tool and its settings. ChatGPT projects keep their own memory of chats inside them, and you can set a project to ignore everything outside it. Treat the standing instructions and uploaded files as the reliable part, and anything mentioned in passing as the part that may not carry over.
Can I share my assistant with someone else?Sometimes. OpenAI allows project sharing across its plans, with the number of collaborators depending on the plan. Anthropic limits project sharing to Team and Enterprise accounts. Before you share anything, remember that everyone you invite can usually see the files you uploaded.
Final takeaway
Making your own AI assistant is not a technical project. It is ten minutes of writing down what you would tell a new colleague on their first day, saved somewhere the tool reads it every time. Pick the chat tool you already use, create one assistant for the task you repeat most, and edit the instructions properly after a week of real use. That one setup will save you more time than any prompt trick you will ever read.
by admin | Sep 3, 2026 | Research & Productivity
It is 11pm, your draft is finished, and nobody you trust is awake to read it. So you paste the whole thing into a chatbot and type the four words most of us have typed at some point: “can you improve this?” A few seconds later you get back something smoother, tidier, and slightly stranger. It reads well. It just does not sound like you anymore.
There is a better way to use these tools, and it comes down to one small change. Ask for feedback instead of a rewrite. Good AI feedback on your writing works a bit like a patient reader who never gets tired: it can tell you where your argument wobbles, where a paragraph loses the thread, and what a reader might still be confused about after finishing. Then you decide what to change, in your own words.
This guide covers what to ask for, the prompts worth copying, what to ignore, and the rules you need to check first.
Why AI feedback on your writing beats “make this better”
When you ask an AI tool to improve a text, it will do exactly that, and it will usually do it by replacing your sentences with its own. You end up with a document you did not write and cannot fully defend if somebody asks you why you made a particular choice.
The Writing Center at the University of North Carolina at Chapel Hill puts the principle neatly in its handout on generative AI in academic writing: when instructors allow these tools, they assume the tools will help you think and write, not think or write for you. Feedback keeps you in the driving seat. A rewrite quietly takes the wheel.
There is a practical benefit too. Feedback teaches you something you can reuse next time. A rewrite teaches you nothing except how to press the button again.
Check the rules before you paste anything in
This step takes two minutes and saves a lot of trouble. Course policies differ wildly, sometimes between two modules in the same department, so read the assignment brief before you open a chat window.
Elon University’s Center for Writing Excellence asks students to check the policy for each assignment and disclose how they used AI when they bring a draft in for help, and it advises keeping a record of your prompts so you can explain your process later. That last part is good advice for anyone, student or not. If you cannot describe how a tool helped you, you probably leaned on it too hard.
Privacy matters just as much. From my own work building websites and handling client material, the rule I stick to is simple: if a document would embarrass me or somebody else in a leak, it does not go into a public chatbot. Unpublished research, confidential reports, anything with personal data in it, and anything covered by an employer agreement all belong in that category. Our guide to using AI safely and protecting your privacy walks through the settings that reduce the risk.
Give the tool the brief, not just the text
Most disappointing feedback comes from a missing brief. The tool cannot judge whether your essay answers the question if it has never seen the question.
Before you ask for comments, paste in four things: the actual task or assignment wording, the marking rubric or the criteria your reader cares about, who the audience is, and the word limit. Then add your draft. The difference in quality is dramatic, because the tool now has a standard to measure your work against instead of a vague idea of “good writing”.
The study skills team at the University of Roehampton also suggests breaking your prompts down and asking for one thing at a time, listing spelling and grammar, structure, argumentation and reasoning, and flow as separate jobs. Ask for all four at once and you get a shallow paragraph on each. Ask for one and you get something you can act on. If prompt wording is where you usually get stuck, our guide on writing better AI prompts covers the basics.
Five feedback prompts worth copying
These are written so the tool comments rather than rewrites. Notice that none of them say “fix” or “improve”.
- Structure: “Here is my assignment brief and my draft. Do not rewrite anything. List the main point of each paragraph in one line, in order, so I can see whether my structure makes sense.”
- Argument: “Act as a sceptical reader. What is my main claim, and where is the evidence weakest or missing? Quote the exact sentences that worry you.”
- Clarity: “Mark any sentence a tired reader would need to read twice, and say in a few words why. Do not suggest replacements yet.”
- Gaps: “What questions would a reader still have after finishing this? What did I assume they already know?”
- Voice check: “Describe the tone of this draft in three phrases. Does it match a piece written for [your audience]?”
The quoting instruction in the second prompt matters more than it looks. It forces the tool to point at real sentences in your text instead of producing generic advice that would fit any essay ever written.
Important tip: ask for the reasoning behind every suggestion, then decide for yourself. If the tool cannot explain why a change helps, treat the suggestion as an opinion and move on.
What to do with feedback you disagree with
You are allowed to say no. Some AI suggestions are wrong for academic or professional writing in specific, predictable ways, and the Roehampton guide flags two of them. The first is a push towards first person and direct personal pronouns, which can make writing clearer but can also weaken the tone your marker expects. The second is a habit of strengthening hedged language. Phrases like “the evidence suggests” exist for a reason, and turning them into confident claims can push you past what your data actually supports.
There is a useful exercise in the UNC handout for spotting this. Run a paragraph through the tool, then put the original and the edited version side by side and look at what changed. Do you agree with the changes? Did the edit make the meaning clearer, or did it just sand off the parts that sounded like you? Doing this a few times teaches you a lot about your own habits, which is the real prize here.
Where AI feedback goes wrong
Three failure modes come up again and again, and all three are worth watching for.
- Confident wrong facts. If you ask a tool to check a claim or suggest supporting sources, it may invent them. UNC’s handout warns that citations can look perfectly formatted and still be fictional. We covered how to catch this in our post on checking AI citations.
- Flattening. Rounds of “smoother” edits tend to converge on the same neutral house style. Two or three passes and your writing sounds like everyone else’s.
- Doing the thinking for you. The most comfortable failure mode. Accepting feedback without judging it is still outsourcing the work, which is exactly what our piece on AI and critical thinking digs into.
A simple routine that takes about twenty minutes
Finish your draft first, without any AI in the room. Then paste in the brief and the rubric, and run the structure prompt. Fix the structure yourself. Run the argument prompt next, and note which weaknesses you accept. Fix those yourself too. Only at the end, once the thinking is settled, ask about clarity and grammar at sentence level.
Elon’s guidance makes the same point about timing: used carefully, AI helps most at the beginning of the writing process, during brainstorming, and at the end, during proofreading. The middle, where you work out what you actually think, is yours. Keeping that middle for yourself is also the honest answer to the academic integrity question, which we look at in more detail in our guide to using AI tools as a student without cheating.
Common Questions
Is asking AI for feedback on my writing cheating?It depends entirely on your institution and the specific assignment, which is why you check the brief first. Many universities treat feedback and proofreading differently from generating text, but policies vary by module and by tutor. If the brief is unclear, ask before you submit, not after.
Which AI tool gives the best writing feedback?The prompt matters far more than the tool. The main free chat assistants all handle this task reasonably well. What changes the outcome is whether you supplied the brief and the rubric, and whether you asked for comments rather than a rewrite.
Should I paste my whole document in at once?For structure feedback, yes, because the tool needs to see the shape of the whole piece. For sentence level work, go section by section. Feedback on a short passage is almost always more specific and more useful than feedback on twenty pages.
How do I stop AI feedback from changing my voice?Never paste the suggested version back into your document. Read the comment, close the tab, and make the change in your own words. If a suggestion is good, you will remember it well enough to write it yourself.
Final takeaway
Used as an editor, AI takes over your writing. Used as a reader, it makes you better at it. Give it the brief, ask for comments instead of corrections, check the rules for your course or your workplace, and make every change yourself. Try one prompt from the list above on your next draft and see how much of the feedback you actually agree with. That disagreement is where your own judgement lives, and it is worth protecting.
by admin | Sep 2, 2026 | AI Guides
You paste a long report into ChatGPT, ask questions about it for twenty minutes, and then it answers something that flatly contradicts what you told it at the start. Most people assume the AI got confused. Usually it is simpler than that. The chat ran out of room, and that room has a name: the context window.
It takes five minutes to understand, and once you do, the strange behaviour stops looking random and starts looking predictable. That is the whole point, because predictable problems can be worked around.
What is a context window, in plain English
A context window is the total amount of text an AI model can look at while writing its answer. Google’s own developer documentation uses the clearest analogy: think of it as short term memory. Anthropic’s documentation calls it “working memory” and defines it as all the text the model can reference when generating a response, including the response itself.
Here is the part that surprises people. The model does not remember your conversation the way you do. Every time you send a message, the tool quietly re-sends the whole chat so far, and the model reads all of it again from scratch before replying. Nothing is stored in its head between messages. The context window is simply how much of that pile it can hold at once.
The pile is measured in tokens rather than words. A token is a chunk of text, usually a short word or part of a longer one. Our guide on what a token is in AI explains it with examples.
Everything counts, including things you forgot about
People assume only their own typing fills the window. According to Anthropic’s documentation, everything in the request counts: the hidden system instructions the company wrote, every message in the conversation, any files or images you attached, and the answer the model is currently writing.
So a chat where you uploaded three PDFs and got five long answers is far fuller than it looks. The scroll bar shows your side of it. The window is holding both sides plus the attachments.
Why the AI forgets what you told it
When a conversation gets close to the limit, something has to give. Anthropic notes that chat interfaces can manage the window on a rolling first in, first out basis, which is exactly what it sounds like: the oldest part of the conversation drops off the front to make space at the back.
That is your answer. The instruction you gave in message two, the one about writing in British English or never using bullet points, was not ignored. By message forty it was no longer in the window at all. The model was not being careless. It could not see it.
Some tools handle this more gracefully by summarising the earlier part of the chat and carrying the summary forward instead of the full text. Anthropic calls this compaction. It helps, but a summary is still lossy, so small details from early on can quietly disappear.
A bigger context window is not automatically better
This is the part most beginner articles skip, and it matters more than the headline numbers. Anthropic’s documentation says it plainly: more context is not automatically better, because as the token count grows, accuracy and recall degrade. They call the effect context rot, and their engineering team writes that while some models degrade more gently than others, the pattern shows up across all of them.
Google says something similar in its long context documentation. Finding one specific fact buried in a huge amount of text works well, often around 99 percent of the time. Finding several specific facts at once does not work as reliably, and performance varies a lot depending on the material.
So when a company advertises a million token context window, read it as “this much will fit” rather than “this much will be read carefully”. Both companies say so themselves, in their own developer docs.
How big are context windows now?
They have grown quickly. Google’s documentation traces the path: earlier models handled around 8,000 tokens, then 32,000, then 128,000, and Gemini was the first to accept a million. Google makes a million tokens concrete like this.
- All the text messages you have sent in the last five years
- Eight average length English novels
- Transcripts of more than 200 podcast episodes
These numbers change every few months, and free tiers often have a smaller window than paid ones, so treat any figure you read online as a snapshot. The shape of the problem does not change: there is a limit, everything counts toward it, and getting close to it costs you accuracy.
Context window and memory are two different things
These get mixed up constantly. The context window is the limit inside one conversation. Memory is a separate feature that saves facts about you and carries them across different conversations. OpenAI’s Memory FAQ describes it as ChatGPT automatically remembering useful context from your chats, files and connected apps, and says you can turn it off in Settings at any time.
The practical difference: memory is why a brand new chat already knows you are a nurse in Dublin. The context window is why that same chat forgets a formatting rule you gave it half an hour ago. We covered the memory side in how AI memory works, including how to see and delete what has been saved about you.
Five habits that fix most “the AI forgot” problems
1. Put your question at the end. Google’s own documentation recommends this: when the context is long, put your question after all the background material rather than before it. Paste the document first, then ask.
2. Start a new chat instead of arguing. If a long conversation starts going in circles, that is a room problem, not a reasoning problem. Open a fresh chat and paste a short summary of what matters.
3. Give each chat one job. One chat for the cover letter, one for the spreadsheet, one for the holiday plan. Long mixed conversations fill the window with material that is irrelevant to whatever you are asking right now.
4. Repeat the rule that matters. If a formatting or tone instruction is important, restate it in the message where you need it. One line, no guesswork.
5. Upload the ten relevant pages, not the whole book. Trimming the input is the most reliable improvement, because you are spending the model’s attention on the part you care about.
From my own work on client websites, this changed how I use these tools. I used to paste an entire plugin’s documentation into a chat and then wonder why the answers drifted by the fifth question. Now I paste the one page I need and start a new chat when the topic changes. The answers got noticeably better without changing tools or paying for anything.
Important tip: if a long chat starts contradicting itself, do not try to correct it in place. Open a new chat and paste a five line summary of what has been decided so far. You will get a better answer in less time than the argument would have taken.
What this means for the way you write prompts
Once you picture the window, good prompting stops being a list of tricks. You are deciding what deserves the space. Anthropic’s engineering team frames it as finding the smallest set of high value information that gets the outcome you want, and that scales all the way down to writing one email. For the practical version, see our guide to writing better AI prompts. For the wider picture, start with what a large language model is, and keep our AI glossary open if the jargon slows you down.
Common Questions
Does a longer chat make the AI slower?Usually yes, a little. Google’s documentation notes that longer inputs generally mean higher latency before the first word appears, because there is simply more to read.
Can I check how full my context window is?In most consumer chat apps, no. Developers can count tokens before sending, but the everyday apps do not show a meter. Watch for the warning signs instead: repeated questions, forgotten instructions, and answers that contradict earlier ones.
What happens if I go over the limit?In a chat app, the oldest messages usually drop out or get summarised, and the conversation carries on without telling you. If a single input is too big on its own, for example one very large file, you will normally get an error instead.
Does a bigger context window mean fewer wrong answers?No. A bigger window reduces forgetting, but it does not stop the model inventing things, and both Google and Anthropic report that recall gets less reliable as the window fills. Check important facts either way.
Final takeaway
The context window is the AI’s desk, not its brain. It only holds so much, everything you put on it competes for space, and the pile at the back gets pushed off the edge when new work arrives. Keep the desk tidy and the work gets better.
You do not need a bigger plan or a smarter model to see the difference. Trim what you paste, put your question last, give each chat one job, and start fresh when things drift. Those four habits are free, and they fix most of the moments where AI feels unreliable.
by admin | Aug 31, 2026 | AI Tools
You take a photo you actually like, and then you notice it. A stranger’s elbow in the corner. A bin by the wall. A wire across the sky. Ten years ago that meant learning Photoshop or letting it go. Today your phone removes it in about four seconds, for free.
That is the good news. The part almost nobody explains is what happens to the photo afterwards. AI photo editing does not only change the picture. In several of these tools it also writes a note into the file saying the picture was changed. This guide covers both halves: which tools genuinely help, where the free versions stop, and what your photo quietly remembers.
What AI photo editing actually means
Old photo editing moved pixels that were already there. You cropped, brightened, or cloned one patch over another.
AI photo editing generates pixels that were never in the shot. When you erase a person from a beach photo, the tool has to invent the sand and sea that were hidden behind them. It is making a confident guess.
That distinction matters twice over. Invented detail can be wrong, especially in faces, text, hands and repeating patterns. And invented detail is exactly what the newer transparency systems are built to flag. Our guide to AI image generators for beginners covers the creating side of the same technology.
The free AI photo editing you probably already have
If you use Google Photos, you already own most of what people pay for. In April 2024 Google announced that its AI powered editing tools would be available to anyone using Google Photos, with no subscription required, rather than staying locked to Pixel phones and paid Google One plans.
Google’s current help page for editing on Android documents the tools worth knowing:
- Magic Eraser removes distractions and unwanted people from the background.
- Unblur sharpens a photo that came out soft.
- Best Take blends a burst of group shots so nobody is mid blink.
- Auto frame widens or recomposes a badly framed shot by generating the missing edges.
- AI Enhance combines several fixes and offers you multiple results to choose from.
Two honest caveats. You need a personal Google Account, because these features do not work on Workspace or school accounts. And the branding moves constantly, so if a tutorial names a button you cannot find, look for the same job under a different label.
What an iPhone can do without any account
On Apple’s side, Clean Up in the Photos app does the same distraction removal job. Apple describes it as “a feature powered by Apple Intelligence in the Photos app that can help remove distracting objects in a photo.”
The catch is hardware. Apple lists iPhone 16 models, iPhone 15 Pro and Pro Max, an iPad with A17 Pro or M1 and later, or a Mac with M1 and later, running iOS 18.1, iPadOS 18.1 or macOS Sequoia 15.1 and above. On an older phone, Clean Up will not appear no matter how many times you update.
What makes it useful for privacy minded people is that it runs on the device. No upload, no service account, no credit counter. That is rarer than it sounds, and it is why I reach for it first with anything sensitive.
Where the free versions actually stop
This is where a lot of online listicles are out of date.
Adobe does have a free route. Adobe’s own generative credits FAQ says free users “get a limited number of free daily generations across all generative AI features, available on a curated set of models. These limits refresh each day.” Notice what that does not say. There is no published number, and Adobe states the limits and models can change. Treat it as a daily taste, not a plan.
Canva is the one people get wrong most often. Canva lists its one click Background Remover under Canva Pro, and the only route in from a free account is to start a free Pro trial. Older articles that list Canva’s background remover as simply free are out of date.
Important tip: before you upload a photo of another person to a free web editor, ask whether you would be comfortable telling them you did it. From building client websites, this is the mistake I see repeated. Someone runs a staff photo or a scanned document through a free tool they found on page one of Google, and nobody checks what that site does with the upload. Our guide on using AI safely and protecting your privacy covers the habits worth keeping.
Your edited photo now carries a record
Here is the part that changes how you should think about all of this.
Google Photos now supports Content Credentials. Its help page describes them as “a technology that provides media history and transparency about the use of artificial intelligence.” Open a photo, tap More, then About, and you may see a section called “How this was made” with a line such as “Edited with AI tools.”
The sentence worth reading twice is this one from the same page: if an original image does not have Content Credentials, Google Photos will add them when an AI edit is saved. The record is created by your edit, not inherited from the camera.
Content Credentials come from the C2PA, an open standard for showing “the origin and edits of digital content.” The same page has the clearest beginner description I have seen: they “function like a nutrition label for digital content.” The steering committee includes Adobe, Amazon, BBC, Google, Meta, Microsoft, OpenAI, Sony and TikTok, so this is not one company’s experiment.
Two limits. Google says Content Credentials are not available on Google Photos on the web, only in the apps. And Apple’s support pages do not document any AI edit marker for Clean Up, so do not assume every tool leaves a trail.
Will Instagram or Facebook label your edited photo?
Probably not, and it is worth being precise about why.
Meta’s transparency page on labelling AI content says the “AI Info” label is applied when it detects industry standard AI image indicators or when someone discloses AI content themselves. The same page adds that its methodology “may not capture labels on some content that is edited with AI.”
These systems were built to catch fully AI generated images, not a tidied up holiday photo. Metadata can also be stripped when a file is re-saved or re-uploaded, which is why a label is a helpful signal and never proof. To check an image you were sent rather than one you made, our post on how to check if a photo or video is AI generated walks through what works.
A workflow that keeps you out of trouble
- Start in the app you already have. Free, fast, and no upload to a stranger.
- Keep the original. Both apps let you revert, and you will want that the first time an erase invents something odd.
- Zoom in on the repaired area at full size before sharing. Repeated patterns and fingers are where these tools fail.
- Say so when it matters. For a listing photo, a news image or anything a person will act on, describe what you removed.
Point four sounds fussy until it is your reputation. Removing a bin from a garden photo is housekeeping. Removing damage from something you are selling is a different thing entirely, and the file may now say the picture was edited.
Common Questions
Is AI photo editing free?Partly. Google Photos gives the core AI edits to any personal Google Account with no subscription, and Apple’s Clean Up is free on supported hardware. Adobe gives free users a limited number of daily generations with no published quota, and Canva lists its background remover as a Canva Pro feature with a free trial.
Does AI photo editing ruin image quality?The edit itself is usually invisible at normal sizes. The failure mode is not softness but invention. Check text, faces, hands, straight lines and repeated patterns at full zoom, since that is where a generated patch gives itself away.
Can someone tell my photo was edited with AI?Sometimes. If the tool wrote Content Credentials into the file and nobody stripped them, a viewer in a supporting app can see a note such as “Edited with AI tools.” Screenshots, re-uploads and re-saves often remove that information, so the absence of a label proves nothing either way.
Which AI photo editing tool should a complete beginner start with?The one already on your phone. Learn Magic Eraser or Clean Up properly before installing anything else, since those two cover most of the fixes people actually need. For more everyday uses of the AI already in your pocket, see our guide to using AI on your phone .
Final takeaway
AI photo editing has quietly become a normal phone feature rather than a specialist skill. Use it. Remove the bin, fix the blur, straighten the group shot.
Just carry two facts with you. The free tier is generous inside Google and Apple and thinner everywhere else, so check before trusting a listicle. And your edit may now be written into the photo itself, which is fine if you were tidying up, and a reason to think twice if you were not.
