liveBook · Manning

Amazon CodeWhisperer

As explained in AI-Powered Developer: Build software with ChatGPT and Copilot

AWS CodeWhisperer is an AWS programming assistant that generates code recommendations from developer comments and source context.

Amazon CodeWhisperer is an AWS programming assistant that works inside an IDE, using comments and source context to suggest code while keeping development in the editor. section 2.4 section 2.5

A practical CodeWhisperer workflow looks like this:

  • Disable competing Copilot extensions, restart the application, install or configure CodeWhisperer, and sign in to a developer account. section 2.3
  • Create a Python file and express the programming task in a comment or prompt; more specific prompts produce output closer to the intended solution. section 2.3 section 2.4
  • Accept suggestions as they unfold method by method, recognizing that the tool advises within the IDE rather than generating an entire project from a tiny prompt. section 2.4
  • Inspect the interpretation of requirements, especially conventions such as whether k means an array index or an element rank. section 2.3

Generating Quickselect

A prompt asking for the kth smallest element without full sorting leads to a partition-based Quickselect implementation. The demonstrated Python example partitions around a pivot, recurses into the relevant side, and returns 2 for k = 2 in [5, 2, 4, 6, 1, 3]. Here, k is treated as the zero-based index of the sorted result, so the output is the third-smallest element. section 2.3

Figure 2.3 Before we can switch to CodeWhisperer, we must disable Copilot. We turn off the extension in the Extensions tab.

Use the setup figure to locate the IDE extension controls needed before switching from Copilot to CodeWhisperer. section 2.3

How AI-Powered Developer: Build software with ChatGPT and Copilot covers it

How deep it goes
Demonstrates installation, prompting, and a complete Quickselect function, but stops short of whole-project generation.
Examples
Uses an interview-style Python Quickselect task and contrasts zero-based indexing with rank-based interpretation.
What it assumes
Assumes an IDE, plugin installation, a logged-in developer account, and enough programming knowledge to state and interpret tasks.
What you can do after
Apply it via an IDE plugin to turn commented programming requirements into method-level code suggestions.
How it connects
Connects IDE-based generation with comments, prompts, GitHub Copilot, ChatGPT, and prompt refinement.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI-Powered Developer: Build software with ChatGPT and Copilot. The section links point to the parts of the book it draws on.