Free tools Windows power users keep installed
One-click scans. No signup required.
iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
An AI coding agent can help turn a scattered programming library into topic-based learning roadmaps—but the useful result comes from separating curriculum planning from file changes. In Ariel Bodan’s 2026 account, opencode organized a personal collection of more than 350 books and resources into 24 learning areas, then helped arrange the files. Bodan reports that the final collection contained 348 resources after four exact duplicates were removed. Those are the author’s figures, not an independent audit.
How the collection became a set of roadmaps
Bodan described a computer folder containing more than 350 programming books and resources, mixed across topics and with duplicates. The practical question behind the project was familiar: when you want to learn something such as backend engineering, data engineering, advanced Python, or C, what should you study next?
The author asked opencode to scan the folder recursively, group resources by subject, and create a roadmap for each subject. The resulting roadmaps covered 24 learning areas and used three stages: foundations, intermediate, and advanced. The article names C, backend engineering, data engineering, data analytics, and technical interviews among its learning goals. It does not provide the full list of 24 topics or the roadmaps themselves.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsUse two passes: plan the learning, then organize files
The key distinction is whether the agent is only classifying resources or is also changing the library. Generating a roadmap is a proposal to review. Moving or deleting files affects the originals, so it calls for a separate plan and verification.
#1 Best Overall
Pass 1: Generate and review topic roadmaps
Ask the agent to inspect the collection and propose a staged path for each topic. A reusable prompt can specify the desired organization and output, while making clear that the roadmap is a draft for human review:
Scan my programming-resource folder recursively, including subfolders. Classify each resource by technical topic and create a learning roadmap for each topic with foundations, intermediate, and advanced stages. State the learning goal for each stage and place each resource where it is most useful. Save the roadmaps to ROADMAPS_BY_TOPIC.md. Report what percentage of files you categorized and list files you could not classify. Do not move or delete files.This prompt reflects Bodan’s proposed improvements. The account does not establish that the completed project used every element of this version, and it does not report a categorization percentage. Treat the percentage and unclassified-file list as requested output to check, not as results already achieved.
Before relying on a roadmap, inspect whether the stages make sense for your goal. A collection can be grouped by topic without proving that every resource is necessary, that the sequence is pedagogically optimal, or that completing it will produce a particular skill level. The account does not report measured learning outcomes or a test of roadmap quality.
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Pass 2: Review and execute file changes
Once the proposed structure is acceptable, ask for a separate plan for moving files. Bodan recommends seeing the changes before execution, checking duplicates by contents rather than names, and updating roadmap paths after files move. A cautious request could be:
Using the approved roadmaps, propose a folder structure and list every planned file move in a table with the current path and proposed path. Identify possible duplicates by comparing file contents, not filenames. Do not move or delete anything until I approve the plan. After approval, move files, remove only confirmed exact duplicates, update paths in the roadmaps, and report file counts before and after.Review the proposed moves before authorizing them. Similar filenames do not establish that two books or resources are duplicates; the author’s safeguard is to compare contents and remove only exact duplicates. Keep a count of the files before changes and verify the resulting count against the removals. Also check that the roadmap paths still point to the resources’ new locations.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.What Bodan reports—and what it does not establish
After reviewing the roadmaps, Bodan asked the agent to make the folder structure match them. The author reports finding four exact duplicates and ending with 348 resources organized across 24 topics, with nothing lost. The article does not supply an inventory, audit trail, categorization-accuracy measure, or independent verification of those counts, so they should be understood as Bodan’s account of the outcome.
The example demonstrates a practical way to reduce the friction of choosing what to study next: use an agent to sort a personal collection into provisional topic paths, then retain human review before the agent changes files. It is one person’s use of opencode, not a comparison of AI tools or evidence that an AI can determine a universally correct curriculum.
Quick Recap
Best Value
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
