📰 Dev.to · BAOFUFAN
39 articles · Updated every 3 hours · View all reads
All
Articles 78,329Blog Posts 103,274Tech Tutorials 19,078Research Papers 16,900News 13,504
⚡ AI Lessons

Dev.to · BAOFUFAN
15h ago
Automating Agent Memory Regression with pytest & Vector DB: 5x Defect Discovery Speedup
It was 1 AM when my phone rang. "You updated the embedding model this afternoon, and now the agent’s...

Dev.to · BAOFUFAN
1d ago
LangChain Memory Pitfall: A Concurrency Race Condition That Cost Me 6 Hours
At 2:17 AM, I was jolted awake by a phone call. The ops team told me the production chatbot had...

Dev.to · BAOFUFAN
2d ago
LangChain + Chroma: Multi-turn RAG Memory and Automated Testing That Turned 2-Hour Bugs Into 5-Minute Fixes
At 1 a.m., the customer group chat exploded: “Does your customer service bot have only a 7-second...

Dev.to · BAOFUFAN
3d ago
How Automating RAG Memory Tests with ChromaDB Quadrupled Our Bug Discovery Rate
At 2 a.m., our ops group chat exploded — “The support bot is mixing up historical orders from the...

Dev.to · BAOFUFAN
3d ago
From Mock to Real Redis: Cutting Agent Memory Test Leakage from 30% to 0
Woken up by PagerDuty at 2 AM. The user group was on fire — our AI customer service agent suddenly...

Dev.to · BAOFUFAN
1w ago
50 pytest Tests That Caught Redis Cache Bugs Before Production — 90% Fewer Incidents
At 2:07 a.m., my phone vibrated three times. The alert channel lit up with a red message: “DB...

Dev.to · BAOFUFAN
1w ago
How I Built a Private Knowledge Base with LangChain + FastAPI — and the 3 Pitfalls That Cost Me 8 Hours
At 1:30 AM, my phone went crazy. The ops chat exploded: “The knowledge base QA endpoint is timing out...

Dev.to · BAOFUFAN
🤖 AI Agents & Automation
⚡ AI Lesson
4w ago
AI Chat Memory Pitfalls: 30% of Conversations Lost on Refresh
It was 1 a.m. when the product manager dropped a screenshot in the group chat: “A user chatted for 20...

Dev.to · BAOFUFAN
4w ago
How Moving Rate Limiting to Redis+Go 8x'd Our API Gateway Throughput (And Cost Us 3 Days of Debugging)
It was 2 AM. I was jolted awake by a cascade of alerts — our downstream order database was thrashing...

Dev.to · BAOFUFAN
🧠 Large Language Models
⚡ AI Lesson
4w ago
Stop Guessing Memory: How to Automate LangChain Memory Testing and Catch 80% of Multi-Turn Failures
2 a.m. The customer Slack channel explodes — the support bot just asked for the same order number...

Dev.to · BAOFUFAN
1mo ago
IndexedDB Automation Testing Pitfalls: 3 Hidden Bugs & 30 Wasted Hours
Last Thursday at 10 PM, our product chat exploded: more than a dozen users reported that all their...

Dev.to · BAOFUFAN
1mo ago
Debugging AI Agent Memory Loss: A 3-Day Investigation
I got paged at 2 AM. Our AI teaching assistant had "amnesia." A student had just explained their lab...

Dev.to · BAOFUFAN
1mo ago
How I Slashed Our LLM API Token Costs by 90% — From 1M to 100K Daily
Last week, finance dropped a screenshot into the group chat: this month’s LLM API bill was ¥5,368, up...

Dev.to · BAOFUFAN
1mo ago
Validating AI Agent Memory with ChromaDB: How a Misaligned Similarity Threshold Cost Me 3 Hours
It was 1 a.m. when a DingTalk alert yanked me out of sleep. Users were complaining that our AI...

Dev.to · BAOFUFAN
1mo ago
From 2 Hours to 3 Minutes: Eliminating Missed Tests in AI Memory Consistency Testing
At 2 a.m. I got woken up by an alert call – our online AI assistant suddenly “lost its memory.” A...

Dev.to · BAOFUFAN
1mo ago
Playwright Multi‑Tab IndexedDB Sync: The Browser Context Isolation Trap (6 Hours of Debugging)
At 1 a.m., the CI bot pinged me in our team chat for the tenth time: “Frontend multi-tab sync test...

Dev.to · BAOFUFAN
1mo ago
From 2-Hour Manual Regression to 4-Minute Playwright Automation for RAG Memory Tests—and 80% Fewer Misses
At 1 a.m., a colleague sent me a screenshot: a user had said, “My name is Xiao Ming, remember I take...

Dev.to · BAOFUFAN
1mo ago
Moving DeepSeek-R1 from Transformers to vLLM: A 14x Throughput Boost
At 2 AM, I was jolted awake by a call from operations: "Why did the billing system charge the user...

Dev.to · BAOFUFAN
1mo ago
Pytest + Docker: 3 Bugs That Broke My AI Agent's Memory (and Cost Me 8 Hours)
At 1:23 AM our ops group chat exploded—users were reporting that the agent had completely lost its...

Dev.to · BAOFUFAN
1mo ago
Building RAG with LangChain & Chroma: Two Hidden Pitfalls That Cost Me 6 Hours
At 10 PM, my product manager dropped 200 PDFs in my lap: “We need to demo an internal knowledge base...

Dev.to · BAOFUFAN
1mo ago
How I Cut LLM Memory Bug Diagnosis from 2 Hours to 5 Minutes with Playwright & Allure
At 2 a.m., the customer group chat erupted: "Your AI assistant completely forgot the client...

Dev.to · BAOFUFAN
1mo ago
I Rewrote Our Crawler with asyncio and Got a 15x Performance Boost
Last week, I finally snapped. Our “legacy” news aggregator was crawling 200 sites in 8 minutes, with...

Dev.to · BAOFUFAN
1mo ago
asyncio Pitfalls: The Mistake That Cost Me 3 Hours
Here’s the story: last week my boss threw a “simple” task at me — pull data from 120 internal APIs...

Dev.to · BAOFUFAN
1mo ago
The asyncio Mistake That Cost Me 3 Hours
It happened last year when I was adding a “batch domain liveness check” feature to our internal...
DeepCamp AI