Skip to content
Mastering Claude

Home

Getting good work out of Claude9 lessons59 min
Three stacked blocks, role, context and task, snapping into an alignment frameGetting good work out of Claude
Path 2, module 2 of 5

Writing a request that works

  1. 01The three blocks of a request6 min

    A request that works separates three blocks: what Claude must be, what has already been said, and what is being asked now. For behaviour beyond the minimum, ask for it explicitly rather than counting on the model to guess. With a project, the role is set once, in its instructions.

  2. 02Being clear, direct, and giving the why6 min

    Claude behaves like a brilliant new employee who knows neither your habits nor your sector: be precise and give the why, not just the task. Name who will read or hear the answer too. To test clarity, show your request to a colleague with no context: if they are lost, Claude will be too.

  3. 03Assigning a role6 min

    A single role sentence placed at the start of a conversation or a project shapes Claude's tone, vocabulary and priorities more effectively than a long list of scattered instructions. A useful role names a specialism, an audience and at least one formal constraint, rather than a title that is too general.

  4. 04Separating data from instructions7 min

    Mixing instructions and data in a single block forces Claude to guess where the instruction stops: a sentence from the pasted text can pass for an instruction. Wrap each type of content in an explicit boundary, a tag, a Markdown heading or a marking line, and check that every opened tag finds its closing match.

  5. 05Formatting the output and speaking on Claude's behalf7 min

    Specify the format by saying what the response should contain rather than what it should not contain. To have it start with the result, name the first element expected: this replaces the old prefilling, which meant writing the start of Claude's response yourself and no longer works on recent Claude models.

  6. 06Making Claude reason before concluding7 min

    Asking Claude to write out its reasoning before its conclusion improves accuracy on multi-step questions, whether that reasoning is invited by a sentence in the request or is already active as a standalone mode, and both versions consume extra tokens.

  7. 07Showing the target rather than forbidding6 min

    Three to five input to output examples anchor a format or a tone better than a long list of rules, and a positive instruction gives a clear target where a purely negative instruction leaves Claude guessing what to replace it with.

  8. 08Composing a complex request without inventing8 min

    A complex request is composed piece by piece, who Claude should be, the context, the data to process, what is being asked, an example, the expected format, then a final line that allows Claude to say I do not know rather than invent an answer.

  9. 09Making a working request last and reusing it6 min

    Keep a request that works and adjust it in small touches, one part at a time, rather than rewriting it from scratch. Place a long document right at the top of the request, before the question. Then fix the request into a reusable template where only what changes from one task to the next is replaced.