implementation

System Context Setup

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Build a Repo-Context Coding Agent with LlamaIndex and OpenAI o4-mini

Format

Text-first

Lines

Sections

Linked challenge

Build a Repo-Context Coding Agent with LlamaIndex and OpenAI o4-mini

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Initialize a LlamaIndex PropertyGraphIndex using the OpenAI o4-mini model. Configure the agent to index the following repository path: './target-repo'. Use the SourceCodeReader to extract functions and classes as nodes. Define a tool 'search_codebase' and 'propose_edit' that allows the agent to navigate the graph before writing to disk.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

implementation

This prompt is mostly narrative and instruction-driven, so adapt examples and output constraints before you rewrite the structure.

Linked challenge

Build a Repo-Context Coding Agent with LlamaIndex and OpenAI o4-mini

Develop a sophisticated repository-context assistant that leverages LlamaIndex's PropertyGraphIndex to map code structures and conventions. This agent must ingest a local repository, build a semantic graph of dependencies and naming patterns, and then use the OpenAI o4-mini model to propose implementation plans for GitHub issues. The primary goal is to avoid 'dirty worktree' issues by strictly scoping file modifications to relevant modules identified through graph traversal. You will implement a custom evaluation harness that benchmarks the agent's ability to locate the correct file for a fix and generate a valid patch without side effects. The system must utilize LlamaIndex's Agentic RAG capabilities to query the codebase and ensure all proposed changes align with existing engineering patterns documented in the repo.

Open challenge

Related prompts

Browse library

Problem Definition and Requirements Gathering

To establish a clear understanding of the problem space and define comprehensive requirements for the AI solution.

AI Solution Architecture and Strategy

To create a comprehensive technical architecture and AI strategy that guides the implementation of the solution.

Implementation Plan and MVP Development

To provide a clear, actionable roadmap for implementing the AI solution from concept to deployment.