Anti Patterns
Last updated
Last updated
Common failures that waste time and money. Extracted from by Chip Huyen
Teams adopt generative AI for status, not solutions. Companies want bragging rights: "we use AI."
Example: Energy startup built GenAI for optimisation. A simple algorithm checking cheap hours works better.
Teams rush to complex solutions first. "I must climb that mountain" mentality. Some common mistakes
Vector databases before basics
Agent frameworks too early
Fine-tuning before prompting
💡 Technical excellence ≠ product success.
Meeting summaries example:
❌ Summary length (3 vs 5 sentences)
✅ Action items from meetings
LinkedIn job recommendations example:
❌ Match accuracy scores
✅ Skill gap identification
Tax chatbot example:
❌ Users don't know what to ask
✅ Suggest relevant FAQs
User experience means understanding human behaviour.
💡 Users want help, not judgment.
Teams rush to vector databases.
Start here: Keyword search, clean data, smart chunking
Data prep matters: Add context, include titles and keywords
Agent frameworks create hidden complexity.
❌ Framework bugs become your bugs
❌ Starter prompts contain typos
❌ Performance fluctuates with framework changes
❌ Hard to diagnose root causes
Build core logic with direct API calls
Measure performance with 100+ test cases
Identify specific bottlenecks frameworks solve
Only then evaluate if framework complexity is worth it
AI judges help but have limits. Add human evaluation.
Limitations:
Models change
Hard to track progress
Teams lose touch with users
Tools score differently
Multi-step AI needs failure isolation.
❌ Resume extraction fails. Which step? PDF to text? Text to data?
✅ Debug each step separately.
Weekend demos don't predict launch timelines. Demo = 20% of total work.
Production needs:
Error handling
User testing
Performance tuning
Infrastructure
Security
Monitoring
...and more
Teams quit after first failures. Find root causes. Fix them. Common causes:
Bad product design
No user research
Poor evaluation
beat frameworks.
Teams on 0.0.* versions
One team built POC with LangChain,
cause unpredictable failures
by 25% on average
Frameworks add and harder to manage
due to complex state handling
When frameworks fail, you debug
Framework updates modify , breaking performance
rather than simplifies