Claude Mastery — From First Prompt to Advanced Workflows

Week 1 — meet the tool, get an account, and learn the screen before you learn the prompting.

1. Meet Claude — what it is and who makes it

   Claude is Anthropic's assistant built for long documents and careful reasoning. It is at its best at reading something long and answering a narrow question about it without losing the thread. It is at its weakest when you want it to be reckless — it will decline, hedge, or ask what you mean — and knowing both halves is what separates somebody who uses it well from somebody who trusts it blindly.

   The lesson

   Claude is a assistant built for long documents and careful reasoning made by Anthropic. The models behind it are the Claude model family, including the fast Haiku, the balanced Sonnet and the largest for hard reasoning. None of that matters on its own — what matters is that you know what kind of worker you have hired. At reading something long and answering a narrow question about it without losing the thread is the job you hand it. When you want it to be reckless — it will decline, hedge, or ask what you mean is the job you keep.

   Most people come to a course like this expecting a list of magic words. There is no such list. What there is, is a tool that produces careful, well-structured prose that usually respects the limits you set, and produces it at a speed no human matches — which means the skill is not in writing the prompt, it is in knowing what a good answer looks like so you can tell the difference.

   Here is the first thing to try, worded the way you will word things for the rest of the course:

   PromptCopy

   Here is my current resume and a job description for a role I want. Tell me the five things the posting asks for that my resume does not prove, and for each one say whether I could realistically build that proof in three weeks.

   Read the answer twice. The first read is for the content; the second is for the shape — did it answer the question you asked, or the question it found easiest? That second read is the habit this whole course is built on.

   Example The answer is a gap list, not encouragement — which is the shape of answer that actually changes what you do next week.

   Practice Open Claude, ask it the one question you would normally put to a search engine about your own field, and write down two things: whether the answer was right, and whether it would have taken you longer to find it yourself.

2. Signing in: what is free, what is paid, and what you actually need

   You do not need the paid plan to finish this course. Start on the free tier — the free tier on claude.ai gives you the current models with a daily message allowance. Upgrade only when you hit a wall you can name: a longer file, a newer model, or a rate limit you keep meeting.

   The lesson

   Every one of these tools has a free tier that is good enough to learn on and a paid tier that removes a limit. the Pro plan raises the allowance and adds priority access at busy times. The mistake is buying the paid plan in week one, before you know which limit you hit — you end up paying to remove ceilings you were never going to touch.

   Work out your own honest usage first. How many questions a day do you actually ask? How big are the files you upload? Do you need the newest model, or the fast one? For revision, for drafting, for coursework, the answer is usually the free tier.

   If your college or workplace provides an account, use it: a Team or Enterprise workspace with administrative controls is how most people in a job get access, and asking your placement cell whether one exists costs nothing.

   Example A long PDF and twenty questions about it fits comfortably in one free session — Claude is one of the few tools where the free tier is enough for a whole study unit.

   Practice Create the account, find the plan page, and write down in one line which limit you would hit first in your own week. It is usually a message cap or a file-size cap, not the model.

3. The screen: where every control lives

   A tour of the interface you will live in — a chat beside a live panel, where long documents and generated files open next to the conversation instead of replacing it. Every panel has a reason to exist, and half of them are the difference between a chat and a system.

   The lesson

   The interface of Claude is a chat beside a live panel, where long documents and generated files open next to the conversation instead of replacing it. That sentence is worth slowing down on, because the single biggest cause of bad output is not a bad prompt — it is a good prompt typed into the wrong place.

   The history list is your memory of what worked. Name your conversations. The temporary or private mode is for anything you would not want in an account's history. The settings panel holds the personal instructions that apply to everything, which is where your context belongs rather than repeated at the top of every message.

   Do this once, properly: open one of your own documents in the side panel and edit it in place rather than copying text back and forth. It takes fifteen minutes and saves you those fifteen minutes every week after.

   Example The side panel is the whole point: a document you are editing stays visible while you argue with the model about paragraph four.

   Practice Spend fifteen minutes doing nothing but clicking. Open every panel, rename one conversation, and save one setting you will want again. Fluency with the screen is what stops you re-explaining yourself every session.

Week 2 — how Claude reads text, the four-part prompt, your own work, and what to do when the answer is wrong.

1. How Claude reads what you type

   Context, instructions and roles. Claude takes a very large working window, which is why it can hold a whole document in view — but a window is still not memory across conversations. Understanding what the model can see — and what it has already forgotten — explains almost every disappointing answer you will get.

   The lesson

   Claude takes a very large working window, which is why it can hold a whole document in view — but a window is still not memory across conversations. This is the machinery. A model does not remember your last conversation the way a person does; it is handed text and asked to continue it well. Everything you want it to know has to be in that text, in the same window.

   There is a difference between a system instruction — the standing context, set once — and a message, which is this request. Put your standing context in the standing place. "I am a final-year mechanical engineering student applying for data roles" belongs in your profile, not typed again at the start of every chat.

   And there is a hard limit. When a conversation gets long enough, the earliest turns fall out of view. Symptoms: it contradicts an instruction you gave ten messages ago, or forgets the file you uploaded. The fix is a new conversation with a written summary of where you got to, not a longer argument.

   Example Attach the same 80-page report in a new chat and it answers questions about page 60. Do that in a tool with a small window and page 60 was summarised away before you asked.

   Practice Ask the same question twice: once on its own, once after a short paragraph of setup about who you are and what you need. Compare the two answers and write down the difference. That gap is the thing you are learning to control.

2. The four-part prompt: role, task, context, format

   Almost every good prompt has four parts: who the model should be, what it must do, the facts it must use, and the shape of the answer you want. Leave out the fourth and you get an essay when you wanted a table.

   The lesson

   Write the four parts as four lines, in this order. ROLE: who it should answer as. TASK: the single thing you want done, as an instruction, not a wish. CONTEXT: the facts, pasted, not referred to. FORMAT: the exact shape of the answer — "a table with three columns", "five bullets, no more than twelve words each".

   FORMAT is the part everybody skips and the part that saves the most time. An answer you have to restructure by hand was not really an answer. Ask for the shape you are going to use: if it is going into a slide, ask for slide bullets; if it is going into a spreadsheet, ask for rows.

   Here is the same request done both ways — first as people usually write it, then in four parts:

   PromptCopy

   Weak:  tell me about data analyst jobs
   
   Strong:
   ROLE:    A hiring manager for entry-level analytics roles in India.
   TASK:    List what you screen for in a fresher's first 30 seconds.
   CONTEXT: I am a 2026 B.Com graduate with Excel, basic SQL and one
            dashboard project. No internship yet.
   FORMAT:  A table: skill | what a fresher shows | what most get wrong.
            Five rows maximum. No introduction.

   The second prompt is not longer because long is good. It is longer because it contains four things the model cannot guess, and the guess is where the useless answer came from.

   Example The instruction "quote the sentence you are answering from" works unusually well here, because the model is reading the source rather than recalling it.

   Practice Take a task you did last week without AI and write the prompt in four labelled lines. Then run it, and rewrite only the part that failed — not the whole prompt.

3. Claude for the work you actually have

   Assignments, revision, email, applications, meeting notes. A 60-page placement report becomes a two-page briefing with the numbers kept, and a draft email becomes one you would actually send. The test of a tool is whether it removes an hour from your week, not whether the demo looked clever.

   The lesson

   The highest-value use of Claude for a student or a fresher is not writing essays. It is compression: turning a 40-page chapter into the six things you actually have to remember, turning a messy set of notes into a revision sheet, turning a job description into a list of what to prove.

   The second highest is structure: given a blank page, ask for three possible outlines and pick one. Being stuck is usually a problem of options, not of effort.

   Here is a prompt worth keeping verbatim — it is the one that turns a document into something you can study:

   PromptCopy

   Attached: [document].
   
   Give me a 1-page briefing with three sections:
   DECISIONS   - what was actually decided, with the clause or page number.
   NUMBERS     - every figure, with what it refers to.
   OPEN        - what is unresolved, and who it is waiting on.
   
   Quote the line you took each item from. If something is ambiguous,
   say so rather than choosing an interpretation.

   Notice the last line. Asking for the gaps is asking the tool to mark its own work, and it is the single most useful line you can add to a study prompt: the material it could not summarise is the material you have not understood yet.

   Example Attach a long document and ask for a briefing with the decisions, the numbers and the open questions kept separate.

   Practice Pick the one task you repeat every week — the one that is boring rather than hard — and rebuild it in Claude today. Time it. Then keep the prompt that worked, saved and named.

4. When the answer is wrong: iterate instead of restarting

   A bad answer is information. Its characteristic failure is being too cautious: a refusal, a hedge, or a request for clarification where you wanted an answer. Keep the conversation, name the fault, and correct one thing at a time — restarting from scratch throws away everything the model has already got right.

   The lesson

   There are four things that usually went wrong, and each has a different fix. It answered a different question — restate the TASK as one sentence. It made things up — supply the facts yourself and say "use only these". It wrote too much — ask for the length first. It sounded like a machine — ask it to rewrite for one specific reader and cut every third word.

   Say the fault out loud, in the message. "This is too long for a WhatsApp message and it sounds like a brochure." A model cannot fix a problem you have not named, and naming the problem is also how you find out what you actually wanted.

   Follow-ups that work: "shorter", "only the parts that are true for a fresher", "rewrite the second sentence three ways", "what would you have to check before I send this?". That last one is worth using before anything goes out with your name on it.

   Example If it declines something ordinary, it is usually because the request reads as ambiguous or risky. Say what the material is for and who will read it — context it did not have.

   Practice Take the worst answer you have received this week and correct it in three follow-up messages without retyping the original prompt. Notice how much faster it converges.

Week 3 — documents and tables, Artifacts and document editing, the API, and one boring task automated.

1. Files, tables and long documents

   Uploading a PDF, a spreadsheet or a screenshot and asking questions about it: Claude reads attached PDFs, text files, spreadsheets and images, and can generate documents, spreadsheets and small runnable pages beside the conversation. This is where these tools stop being a chat and start being work, and where the failure modes are worth knowing.

   The lesson

   Claude reads attached PDFs, text files, spreadsheets and images, and can generate documents, spreadsheets and small runnable pages beside the conversation. The two failures to expect are the ones nobody warns you about: a long document is summarised as it is read, so a detail on page 60 can be missed; and a table with merged cells or a scanned page is likely to be read wrongly.

   So the working method is: ask narrow questions, and ask the tool to quote the line it is answering from. "From the attached file only, what does clause 4.2 let me do? Quote the sentence." If it cannot quote it, it did not read it.

   For a spreadsheet, ask for the formula and an explanation instead of the computed column — ask it to walk through the logic in words first, then give the formula — then you can fix it yourself next month when the columns change.

   Example Upload a 40-page government notification, ask which clauses apply to a 2026 graduate applicant, and it will answer clause by clause rather than in general.

   Practice Upload one real document you already own — a syllabus, a marksheet, a project report — and ask three questions whose answers you already know. When it gets one wrong, read the passage it quoted before you blame the file.

2. Artifacts and document editing — Claude's own feature

   An Artifact is a real file that opens beside the chat and updates as you talk — a draft, a table, a small web page, a spreadsheet. You edit it there, not in the message box. It is the difference between advice about a document and a document.

   The lesson

   This is the feature that makes Claude different from a chat window, and it is why people write long things in it. The conversation and the document live side by side, so every correction is a small edit rather than a re-ask.

   Ask for the document first, with a named structure — headings, a table, a word count. Then iterate in place: "tighten section 2", "move the risk table above the timeline", "cut the first paragraph entirely". Export when it is right, and keep the conversation as the record of why it looks that way.

   Here is the shape of it, in the form you will actually use:

   PromptCopy

   Create a one-page project brief as a document I can edit.
   
   Sections: Problem, Approach, What is finished, What is left, Risks.
   Length: under 400 words total.
   Audience: a non-technical hiring manager reading it for 60 seconds.
   Include one table of risks with a mitigation column.
   Tone: plain, no marketing words, no exclamation marks.

   The mistake is treating the Artifact as the answer and shipping it. It is a draft that is easier to edit than to write — and the parts you cannot explain are exactly the parts an interviewer will pick at.

   Example Ask for "a one-page project brief with headings and a table of risks" and you get an editable page in the side panel, which you then correct in place.

   Practice Turn one piece of your own writing into an Artifact, revise it in four steps inside the panel, then export it and use it for real this week.

3. The Anthropic API and your first script

   Claude is available over an API billed per token, with a large context window and native support for tool use and long documents. You do not need this to finish the course, and you do not need it for a fresher job either — but an afternoon here is what turns "I have used Claude" into "I have built with it", which is a different sentence in an interview.

   The lesson

   Claude is available over an API billed per token, with a large context window and native support for tool use and long documents. The idea is simple: the same model you have been chatting with also answers a web request, so you can put it inside a script, a spreadsheet or a page. A key identifies you; a request sends the text; a response comes back as data.

   The reason to try it once, even if you never build anything: it makes the chat version less mysterious. You see that the whole conversation is text in and text out, that your instructions are literally lines of a request, and that "the model" is one parameter among several.

   A first call looks like this:

   PythonCopy

   import anthropic
   
   client = anthropic.Anthropic()   # reads ANTHROPIC_API_KEY
   
   msg = client.messages.create(
       model="claude-sonnet-4-5",
       max_tokens=300,
       messages=[{
           "role": "user",
           "content": "In three sentences, what is a data analyst? Be concrete.",
       }],
   )
   
   print(msg.content[0].text)

   The mistake is sending a 200-page document on every request because the window is large. Tokens cost money and time; send the pages the question is about.

   Example A script that reads a folder of PDFs and returns a one-paragraph abstract of each is the classic first job for this API, and it is genuinely useful for a student with forty papers.

   Practice Get a key, run one request that works, and change one word in it to see the answer change. That is the whole of the first afternoon.

4. Automate one boring task with Claude

   Automation is not about building a system. It is about doing one repetitive job the same way every time, in less time than last time, and being able to do it again next month.

   The lesson

   Pick the task by how often it happens, not by how impressive it would be. A weekly report you can half-generate beats a clever pipeline you build once and never open again.

   Summarising every new file in a folder, or turning a weekly dump of notes into a formatted update in the same structure every time.. Whatever you choose, write the steps back out in plain English afterwards — "Step 1, open the sheet, Step 2, paste the names —" because the written steps are what you follow when the tool changes next quarter.

   And keep a copy of the prompt next to the task. A prompt that lives only in your chat history is a prompt you will rewrite from scratch in March.

   Example The automation that pays for itself is a weekly briefing template: same headings every Monday, new input document, five minutes instead of an hour.

   Practice Name the task you repeat most often that involves typing, then write the prompt for it and run it three weeks in a row from the same saved place. Three runs is the point at which you know whether it is genuinely automated.

Week 4 — a finished portfolio project, the privacy rules, the limits, and the Anthropic certification paths.

1. Build the portfolio project: a long-document briefing tool for your own subject

   Pick a subject with real documents — a government scheme, a syllabus, a set of standards — and build a reusable briefing format that turns any new document into the same one-page structure. It is the thing you will talk about in the interview, so it has to be small enough to finish in a fortnight and concrete enough to show a person in one minute.

   The lesson

   Pick a subject with real documents — a government scheme, a syllabus, a set of standards — and build a reusable briefing format that turns any new document into the same one-page structure. Finish it before you start the next one. A half-built idea shows nothing; a small finished thing shows that you can finish.

   Use the tool as a collaborator, not an author: ask it for a plan, a critique and a checklist, and write the work yourself. In the interview the questions will be about the decisions — why this, why not that — and only the work you did yourself has answers.

   Write one paragraph beside the project: what problem it solves, what you used, and what you would do differently next time. That paragraph is the interview.

   Example Finished, it is: a template that worked on three different documents, and three briefings you can show.

   Practice Write the one-paragraph summary of what you learned about reading primary documents. That paragraph is worth more in an interview than the tool.

2. Ethics, privacy and what never to paste

   These tools send what you type to somebody else's computer and keep it in a history. Never paste passwords, government ID numbers, bank or card details, medical records, or another person's private data — and never paste a company's confidential document.

   The lesson

   There is no version of this tool where your text stays on your laptop. Everything you type is sent to a server, kept in a history you can usually see, and may be reviewed or used to improve the product depending on the plan.

   An unpublished report, a client contract or an internal policy does not go into a personal account, however convenient the window size makes it. Ask whether there is a work account before you ask whether it is allowed.

   The practical rule for a fresher: replace the real thing with a stand-in. "Client A", "my friend's phone number", "the amount in the offer letter". The tool rarely needs the real value to do the work, and the stand-in costs you nothing.

   And the professional rule: if the document has "confidential" on it, the answer is your employer's approved account or nothing. If your employer has an approved plan or a policy, that policy is the answer, not your judgement about how sensitive a file really is.

   Example Long documents are exactly the material people assume is safe to paste, and exactly the material that usually belongs to somebody else.

   Practice Go through your last five conversations and delete anything containing a real phone number, a client name, or a document you did not write. If you cannot find the delete button, that is the lesson.

3. Limits, hallucinations and how to check

   These tools predict plausible text. It is careful, which is not the same as correct — a wrong number inside a careful paragraph is harder to spot, not easier That is a mechanism, not a moral failing — and the habit it demands is the habit of asking "where did this come from?" out loud, every time, before you use an answer.

   The lesson

   A model does not look things up unless it has been given a way to look things up, and even then it can attach a real number to the wrong claim. It is careful, which is not the same as correct — a wrong number inside a careful paragraph is harder to spot, not easier

   So the rule is: numbers, dates, names, citations and legal or medical claims get checked in a primary source before they leave your hands. Everything else — drafts, structure, explanations, practice — is fair game.

   Three questions to ask before you trust an answer. Where did this come from? What would make it false? Who is the original source, and can I open it? If the third one has no answer, you have writing material, not facts.

   On a long document, the fastest check is to ask for the page number with every claim and open two of them at random.

   Example Ask it to total a column in an attached spreadsheet and check the total yourself. Any model that is reading text can misread a column.

   Practice Ask for one statistic with its source, then open the source. Sometimes it exists. Sometimes the citation is invented, and the number is close enough to a real one to be dangerous. Either way you will remember the exercise.

4. Get certified: the official Anthropic paths

   A Way2Fresher certificate for this course is free and lives on this site. Beyond it, Anthropic publishes its own learning and certification material — and the rail on this course page links to it.

   The lesson

   There are two things called a certificate and they are not the same. The one this site issues records that you finished a structured course and built the project at the end of it — it is free, and it is yours to print. The ones Anthropic issues record that you passed their own material.

   Anthropic publishes free prompt-engineering and tool-use courses, including a public course repository, and is the most explicit of the labs about how its models are meant to be used. Start with their own material rather than a paid course.

   Get both, in that order. The project is what an interviewer asks about; the certificate is what gets past a filter that looks for keywords. The links to the official paths are in the rail beside this lesson, each labelled with who issues it.

   And put the work on the certificate, not the other way round: a certificate with no project behind it is a line on a resume, and it lasts exactly until the first technical question.

   Example A prompt asking it to quote the exact sentence that answers each interview question prepares you better than a list of model answers, because the source is in front of you.

   Practice Finish every lesson here, take your Way2Fresher certificate, then open one official path and work through it with the project you have already built. Being certified in the tool you can already use is a small additional step.