Augment Code
@augmentcode.com
The Developer AI that deeply understands your codebase and how your team builds software. Augment puts your team’s collective knowledge at your fingertips.
Read more: www.augmentcode.com/changelog/cl...
Claude Sonnet 4.5 is now available as the default model in Augment Code
The most powerful AI software development platform with the industry-leading context engine.
www.augmentcode.com
September 29, 2025 at 5:09 PM
Read more: www.augmentcode.com/changelog/cl...
Our early take on Sonnet 4.5 as compared to Sonnet 4?
✅ 34% fewer tool calls on average
✅ ~26% faster overall task completion time
The result: the same accuracy, delivered with more speed and flow.
✅ 34% fewer tool calls on average
✅ ~26% faster overall task completion time
The result: the same accuracy, delivered with more speed and flow.
September 29, 2025 at 5:08 PM
Our early take on Sonnet 4.5 as compared to Sonnet 4?
✅ 34% fewer tool calls on average
✅ ~26% faster overall task completion time
The result: the same accuracy, delivered with more speed and flow.
✅ 34% fewer tool calls on average
✅ ~26% faster overall task completion time
The result: the same accuracy, delivered with more speed and flow.
you like to be close to the metal, we get it.
August 28, 2025 at 10:55 PM
you like to be close to the metal, we get it.
The top 3 requests?
🧠 "error" (35%)
✅ "test" (21%)
✨ "improve" (18%)
AI isn’t starting from a blank file.
It’s jumping into messy code and making sense of it.
The real value? Debugging, refining, and unblocking.
🧠 "error" (35%)
✅ "test" (21%)
✨ "improve" (18%)
AI isn’t starting from a blank file.
It’s jumping into messy code and making sense of it.
The real value? Debugging, refining, and unblocking.
July 16, 2025 at 4:29 PM
The top 3 requests?
🧠 "error" (35%)
✅ "test" (21%)
✨ "improve" (18%)
AI isn’t starting from a blank file.
It’s jumping into messy code and making sense of it.
The real value? Debugging, refining, and unblocking.
🧠 "error" (35%)
✅ "test" (21%)
✨ "improve" (18%)
AI isn’t starting from a blank file.
It’s jumping into messy code and making sense of it.
The real value? Debugging, refining, and unblocking.
Agent prompting = engineering communication.
Don’t think “prompt engineering.” Think “design doc + task breakdown + pair programming.”
Good prompts are good collaboration.
Don’t think “prompt engineering.” Think “design doc + task breakdown + pair programming.”
Good prompts are good collaboration.
July 15, 2025 at 4:28 PM
Agent prompting = engineering communication.
Don’t think “prompt engineering.” Think “design doc + task breakdown + pair programming.”
Good prompts are good collaboration.
Don’t think “prompt engineering.” Think “design doc + task breakdown + pair programming.”
Good prompts are good collaboration.
Ask for a plan before action.
“I need to expose time zone settings. First, suggest a plan—don’t write code yet.”
This gives you control. And gives the Agent a checkpoint to align.
“I need to expose time zone settings. First, suggest a plan—don’t write code yet.”
This gives you control. And gives the Agent a checkpoint to align.
July 15, 2025 at 4:28 PM
Ask for a plan before action.
“I need to expose time zone settings. First, suggest a plan—don’t write code yet.”
This gives you control. And gives the Agent a checkpoint to align.
“I need to expose time zone settings. First, suggest a plan—don’t write code yet.”
This gives you control. And gives the Agent a checkpoint to align.
Don’t cram it all in at once.
❌ “Read ticket, build UI, write tests, update docs”
✅ Break into steps:
- Read ticket
- Build UI
- Write tests
- Update docs
Let the Agent finish before moving on.
❌ “Read ticket, build UI, write tests, update docs”
✅ Break into steps:
- Read ticket
- Build UI
- Write tests
- Update docs
Let the Agent finish before moving on.
July 15, 2025 at 4:28 PM
Don’t cram it all in at once.
❌ “Read ticket, build UI, write tests, update docs”
✅ Break into steps:
- Read ticket
- Build UI
- Write tests
- Update docs
Let the Agent finish before moving on.
❌ “Read ticket, build UI, write tests, update docs”
✅ Break into steps:
- Read ticket
- Build UI
- Write tests
- Update docs
Let the Agent finish before moving on.
Point the Agent to the right files.
❌ “Add JSON parser to chat backend”
✅ “Add JSON parser in LLMOutputParsing (services/ folder). It’ll be used to extract structured output from chat completions.”
Precision = performance.
❌ “Add JSON parser to chat backend”
✅ “Add JSON parser in LLMOutputParsing (services/ folder). It’ll be used to extract structured output from chat completions.”
Precision = performance.
July 15, 2025 at 4:28 PM
Point the Agent to the right files.
❌ “Add JSON parser to chat backend”
✅ “Add JSON parser in LLMOutputParsing (services/ folder). It’ll be used to extract structured output from chat completions.”
Precision = performance.
❌ “Add JSON parser to chat backend”
✅ “Add JSON parser in LLMOutputParsing (services/ folder). It’ll be used to extract structured output from chat completions.”
Precision = performance.
Give references to code, tests, or docs.
❌ “Write tests for ImageProcessor”
✅ “Write tests for ImageProcessor.Follow structure in test_text_processor.py”
The Agent learns better by example.
❌ “Write tests for ImageProcessor”
✅ “Write tests for ImageProcessor.Follow structure in test_text_processor.py”
The Agent learns better by example.
July 15, 2025 at 4:28 PM
Give references to code, tests, or docs.
❌ “Write tests for ImageProcessor”
✅ “Write tests for ImageProcessor.Follow structure in test_text_processor.py”
The Agent learns better by example.
❌ “Write tests for ImageProcessor”
✅ “Write tests for ImageProcessor.Follow structure in test_text_processor.py”
The Agent learns better by example.
Include why, not just what.
❌ “Use events instead of direct method calls”
✅ “Reviewers flagged tight coupling in SettingsWebviewPanel.statusUpdate(). Let’s refactor to events to improve modularity.”
Reasoning aligns the Agent with your intent.
❌ “Use events instead of direct method calls”
✅ “Reviewers flagged tight coupling in SettingsWebviewPanel.statusUpdate(). Let’s refactor to events to improve modularity.”
Reasoning aligns the Agent with your intent.
July 15, 2025 at 4:28 PM
Include why, not just what.
❌ “Use events instead of direct method calls”
✅ “Reviewers flagged tight coupling in SettingsWebviewPanel.statusUpdate(). Let’s refactor to events to improve modularity.”
Reasoning aligns the Agent with your intent.
❌ “Use events instead of direct method calls”
✅ “Reviewers flagged tight coupling in SettingsWebviewPanel.statusUpdate(). Let’s refactor to events to improve modularity.”
Reasoning aligns the Agent with your intent.
❌ “Fix bug in login handler”
✅ “Login fails with 500 on incorrect passwords. Repro: call /api/auth with wrong creds. Check auth_service.py. Add test if possible.”
Agents need context like humans do.
✅ “Login fails with 500 on incorrect passwords. Repro: call /api/auth with wrong creds. Check auth_service.py. Add test if possible.”
Agents need context like humans do.
July 15, 2025 at 4:28 PM
❌ “Fix bug in login handler”
✅ “Login fails with 500 on incorrect passwords. Repro: call /api/auth with wrong creds. Check auth_service.py. Add test if possible.”
Agents need context like humans do.
✅ “Login fails with 500 on incorrect passwords. Repro: call /api/auth with wrong creds. Check auth_service.py. Add test if possible.”
Agents need context like humans do.
Thanks for the feedback, Michael - agree we were overzealous here. We'll go ahead and delete all your info so you don't hear from us again.
July 11, 2025 at 4:12 AM
Thanks for the feedback, Michael - agree we were overzealous here. We'll go ahead and delete all your info so you don't hear from us again.
Ready to make your agent work the way you do? Create a .augment/rules/ folder in your repository and start customizing.
🔗 www.augmentcode.com/changelog/in...
🔗 www.augmentcode.com/changelog/in...
Introducing Augment Rules
The most powerful AI software development platform with the industry-leading context engine.
www.augmentcode.com
July 9, 2025 at 9:22 PM
Ready to make your agent work the way you do? Create a .augment/rules/ folder in your repository and start customizing.
🔗 www.augmentcode.com/changelog/in...
🔗 www.augmentcode.com/changelog/in...
Already using .augment-guidelines.md?
No changes required—your setup remains supported.
But Augment Rules offers even greater flexibility and control.
No changes required—your setup remains supported.
But Augment Rules offers even greater flexibility and control.
July 9, 2025 at 9:22 PM
Already using .augment-guidelines.md?
No changes required—your setup remains supported.
But Augment Rules offers even greater flexibility and control.
No changes required—your setup remains supported.
But Augment Rules offers even greater flexibility and control.
Three flexible ways to use Rules:
1️⃣ Always: Attach rules to every query automatically
2️⃣ Manual: Select rules per query as needed
3️⃣ Auto: Describe your task—the agent intelligently selects the most relevant rules
1️⃣ Always: Attach rules to every query automatically
2️⃣ Manual: Select rules per query as needed
3️⃣ Auto: Describe your task—the agent intelligently selects the most relevant rules
July 9, 2025 at 9:22 PM
Three flexible ways to use Rules:
1️⃣ Always: Attach rules to every query automatically
2️⃣ Manual: Select rules per query as needed
3️⃣ Auto: Describe your task—the agent intelligently selects the most relevant rules
1️⃣ Always: Attach rules to every query automatically
2️⃣ Manual: Select rules per query as needed
3️⃣ Auto: Describe your task—the agent intelligently selects the most relevant rules
Get started in seconds:
🧠 Smart Rule Selection: Agent Requested mode finds what’s relevant for each task
🚀 Seamless Migration: Import rules from other tools, or use your existing Augment guidelines
🧩 Flexible Organization: Use any file name or structure to match your workflow
🧠 Smart Rule Selection: Agent Requested mode finds what’s relevant for each task
🚀 Seamless Migration: Import rules from other tools, or use your existing Augment guidelines
🧩 Flexible Organization: Use any file name or structure to match your workflow
July 9, 2025 at 9:22 PM
Get started in seconds:
🧠 Smart Rule Selection: Agent Requested mode finds what’s relevant for each task
🚀 Seamless Migration: Import rules from other tools, or use your existing Augment guidelines
🧩 Flexible Organization: Use any file name or structure to match your workflow
🧠 Smart Rule Selection: Agent Requested mode finds what’s relevant for each task
🚀 Seamless Migration: Import rules from other tools, or use your existing Augment guidelines
🧩 Flexible Organization: Use any file name or structure to match your workflow