New article: AI Coding Agents: A Practical Guide for Software Developers#170
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughAdds a single new MDX blog page "AI Coding Agents: A Practical Guide for Software Developers" and registers it in the blog registry by updating Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
🧪 Generate unit tests (beta)
No actionable comments were generated in the recent review. 🎉 Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@src/app/blog/ai-coding-agents-practical-guide/page.mdx`:
- Line 286: Replace the misspelled word "commitable" with the correct spelling
"committable" in the sentence that lists AI review tools ("Tools like Graphite,
CodeRabbit, Devin Review, Cursor Bugbot, Snyk Code, DeepSource, Codacy, among
others, don’t just surface potential issues; they explain changes, group related
hunks, highlight bugs, enforce standards, and in some cases, offer commitable
suggestions.") so the phrase becomes "offer committable suggestions."
- Around line 357-401: Replace the invalid model identifier used in
OrchestratorAgent.execute (inside the client.messages.create call) with a valid
Anthropic Claude model string such as "claude-sonnet-4-20250514" (or another
supported alias like "claude-sonnet-4-0" / "claude-opus-4-0"); update only the
model parameter in the client.messages.create invocation so the example runs
with a real Anthropic model while leaving the rest of the OrchestratorAgent,
CRMAgent, and MarketingAgent code unchanged.
🧹 Nitpick comments (3)
src/app/blog/eloqdoc-vs-ferretdb-vs-mongodb-benchmark-guide/page.mdx (1)
54-99: Consider adding Tailwind classes for table styling consistency.The HTML tables here lack styling classes, whereas
src/app/blog/serverless-sql-databases/page.mdxuses Tailwind classes likeclassName="w-full text-sm"and border utilities. This creates visual inconsistency across blog posts.♻️ Example: Add consistent table styling
-<table> +<table className="w-full text-sm"> <thead> - <tr> + <tr className="border-b border-zinc-700">Apply similar patterns to both tables for a cohesive look.
src/app/blog/state-of-ai-code-review-tools-2025/page.mdx (1)
500-510: LGTM with a minor style suggestion.The expanded Qodo section provides comprehensive details on capabilities, integrations, and deployment options.
The static analysis tool flagged that multiple sentences begin with "Qodo." Consider varying the sentence structure slightly for readability, e.g., "The platform features..." instead of "Qodo offers..." in the third sentence.
src/app/blog/serverless-sql-databases/page.mdx (1)
180-186: Inconsistent URL formatting in related posts.Some links use absolute URLs (
https://www.devtoolsacademy.com/blog/...) while one uses a relative path (/blog/state-of-databases-2024). Consider using relative paths consistently for internal links to avoid hardcoding the domain.♻️ Proposed fix for consistent relative paths
-- [Supabase vs. Clerk](https://www.devtoolsacademy.com/blog/supabase-vs-clerk/) -- [CodeRabbit vs. Other AI Code Review Tools](https://www.devtoolsacademy.com/blog/coderabbit-vs-others-ai-code-review-tools/) -- [Neon vs. Supabase](https://www.devtoolsacademy.com/blog/neon-vs-supabase/) -- [MongoDB vs. PostgreSQL](https://www.devtoolsacademy.com/blog/mongoDB-vs-postgreSQL/) -- [Cody vs. Cursor](https://www.devtoolsacademy.com/blog/cody-vs-cursor-choosing-the-right-ai-code-assistant-for-your-development-workflow/) +- [Supabase vs. Clerk](/blog/supabase-vs-clerk) +- [CodeRabbit vs. Other AI Code Review Tools](/blog/coderabbit-vs-others-ai-code-review-tools) +- [Neon vs. Supabase](/blog/neon-vs-supabase) +- [MongoDB vs. PostgreSQL](/blog/mongoDB-vs-postgreSQL) +- [Cody vs. Cursor](/blog/cody-vs-cursor-choosing-the-right-ai-code-assistant-for-your-development-workflow) - [State of Databases for Serverless in 2024](/blog/state-of-databases-2024) -- [Cursor vs Windsurf ](https://www.devtoolsacademy.com/blog/cursor-vs-windsurf/) +- [Cursor vs Windsurf](/blog/cursor-vs-windsurf)
Owner
Author
|
@nirnejak kindly upload a new cover image for the article |
Contributor
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Fix all issues with AI agents
In `@src/app/blog/ai-coding-agents-practical-guide/page.mdx`:
- Around line 69-70: The sentence "The most significant change when working with
AI coding agents isn’t technical; , it’s mental." contains a stray "; ,"
sequence—remove the extra semicolon and comma so the sentence reads correctly
(e.g., "The most significant change when working with AI coding agents isn’t
technical, it’s mental." or use an em dash if preferred).
- Around line 260-262: In the sentence under the "**Correctness first.**"
heading where the text currently ends with the accidental `?.` token, remove the
extra period so the sentence ends with a single question mark (i.e., change `?.`
to `?`) to fix the double punctuation; locate the line containing the phrase
"Does the code actually do what was requested?" and update that punctuation
accordingly.
- Around line 315-326: The markdown block has spacing/formatting issues: remove
the stray space before the closing bold in the sentence starting "**Generate
test cases (especially edge cases). **" so it becomes "**Generate test cases
(especially edge cases).** Ask...", and add the missing space after the comma in
the sentence 'A human reviewer might say, “the test is wrong,fix the test.”' so
it reads '...“the test is wrong, fix the test.”'; also check adjacent paragraph
breaks around the AI-debugging paragraph to ensure consistent single blank lines
between paragraphs.
Comment on lines
+260
to
+262
| **Correctness first.** | ||
| Does the code actually do what was requested?. Half-implemented features and missing edge paths are common failure modes. | ||
|
|
Contributor
There was a problem hiding this comment.
Fix the double punctuation in the question.
The sentence ends with ?., which looks accidental.
🔧 Proposed fix
-Does the code actually do what was requested?.
+Does the code actually do what was requested?📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| **Correctness first.** | |
| Does the code actually do what was requested?. Half-implemented features and missing edge paths are common failure modes. | |
| **Correctness first.** | |
| Does the code actually do what was requested? Half-implemented features and missing edge paths are common failure modes. |
🤖 Prompt for AI Agents
In `@src/app/blog/ai-coding-agents-practical-guide/page.mdx` around lines 260 -
262, In the sentence under the "**Correctness first.**" heading where the text
currently ends with the accidental `?.` token, remove the extra period so the
sentence ends with a single question mark (i.e., change `?.` to `?`) to fix the
double punctuation; locate the line containing the phrase "Does the code
actually do what was requested?" and update that punctuation accordingly.
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@src/app/blog/ai-coding-agents-practical-guide/page.mdx`:
- Line 236: The file uses both "optimize" and British "optimise"; pick one
spelling (use American "optimize") and make it consistent across the article by
replacing all instances of "optimise" with "optimize" (e.g., change the
occurrence in the sentence "I learned this the hard way after asking an agent to
“optimize performance”…" and the earlier line that currently reads
"optimise")—search the page.mdx for both spellings and apply the chosen variant
uniformly.
- Around line 385-401: The model identifier passed to client.messages.create in
OrchestratorAgent.execute is invalid; update the model parameter from
"claude-sonnet-4-5-20250929" to a supported Anthropic ID (e.g.,
"claude-sonnet-4-20250514", "claude-sonnet-4-0", "claude-3-7-sonnet-20250219",
or "claude-3-7-sonnet-latest") so the call in client.messages.create succeeds;
locate the model="..." argument inside the execute method of class
OrchestratorAgent and replace with one of the valid identifiers.
| ### Why Incremental Delegation Works | ||
| Delegating incrementally gives you leverage without lock-in. After each step, you can review the diff, catch misunderstandings early, and adjust the plan if needed. If you ask for everything at once, you lose that flexibility and often end up redoing work. | ||
|
|
||
| I learned this the hard way after asking an agent to “optimize performance” and getting a massive, unfocused diff. Now I scope work precisely. The results are far better. |
Contributor
There was a problem hiding this comment.
Inconsistent spelling: "optimize" vs "optimise".
Line 106 uses British spelling "optimise" while this line uses American spelling "optimize". Pick one variant and apply it consistently throughout the article.
📝 Proposed fix (using American English)
At line 106:
-This is where many AI workflows break. Agents can help write tests, but they often miss edge cases or optimise for passing tests.
+This is where many AI workflows break. Agents can help write tests, but they often miss edge cases or optimize for passing tests.🧰 Tools
🪛 LanguageTool
[uncategorized] ~236-~236: Do not mix variants of the same word (‘optimize’ and ‘optimise’) within a single text.
Context: ... the hard way after asking an agent to “optimize performance” and getting a massive, unf...
(EN_WORD_COHERENCY)
🤖 Prompt for AI Agents
In `@src/app/blog/ai-coding-agents-practical-guide/page.mdx` at line 236, The file
uses both "optimize" and British "optimise"; pick one spelling (use American
"optimize") and make it consistent across the article by replacing all instances
of "optimise" with "optimize" (e.g., change the occurrence in the sentence "I
learned this the hard way after asking an agent to “optimize performance”…" and
the earlier line that currently reads "optimise")—search the page.mdx for both
spellings and apply the chosen variant uniformly.
…/tyaga001/devtoolsacademy into ai-coding-agents-practical-guide
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@src/app/blog/data.ts`:
- Around line 28-41: Remove the duplicate blog object with slug
"serverless-sql-databases" from the data array so each post.slug is unique;
locate the duplicated entry by its slug value in src/app/blog/data.ts and delete
the newly added object (the one with title "6 Best Serverless SQL Databases for
Developers (2026 Comparison)"), leaving the existing entry intact; ensure no
other entries share the same slug so the blog listing that keys on post.slug
continues to render and route correctly.
🧹 Nitpick comments (1)
src/app/blog/data.ts (1)
42-56: Minor formatting issue and identical excerpt/description.
- Line 50 has an unnecessary blank line within the object literal.
- The
excerptanddescriptionfields are identical. Consider making the description more detailed to differentiate it from the excerpt, as seen in other entries in this file.📝 Suggested improvement
{ author: "Ankur Tyagi", slug: "ai-coding-agents-practical-guide", title: "AI Coding Agents: A Practical Guide for Software Developers", excerpt: "A practical guide to working with AI coding agents without the hype.", description: - "A practical guide to working with AI coding agents without the hype.", - + "Learn how to effectively work with AI coding agents through planning, delegation, review, and testing workflows while maintaining code quality and developer judgment.", publishedAt: "2026-02-10T00:00:00Z", category: "AI Code Editor", image: AICodingAgent.src, isNew: true, isFeatured: false, },
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pull Request
Summary
Brief description of changes and motivation.
Type of Change
Changes Made
Testing
npm run build)Database Changes (if applicable)
Content Changes (if applicable)
src/lib/toolData.jsonUI/UX Changes (if applicable)
Checklist
Screenshots/Demo
Related Issues
Additional Notes
Summary by CodeRabbit