← back
Why the Best AI Agents Are Built Without Frameworks (Primitives over Frameworks) — Ahmad Awais, CHAI
Original: Why the Best AI Agents Are Built Without Frameworks (Primitives over Frameworks) — Ahmad Awais, CHAI
Takeaway
Build agents from a small set of cloud-scaled primitives (memory, parser, chunker, threads, tools) rather than monolithic AI frameworks.
Summary
- Ahmad Awais (Langbase) argues production winners (Perplexity, Cursor, v0, Lovable, Bolt) avoid AI frameworks in favor of composable primitives — like S3 for object storage.
- Demos chai.new vibe-coding a PDF chat agent using Langbase primitives: memory (vector store), parser, chunker, threads, tools — all serverless and autoscaling.
- Frameworks bloat with abstractions that break in production; primitives are debuggable and scale via the underlying cloud.
- Covers eight agent architectures built only on primitives, drawing on stateofaiagents.com research across industries.
agentsprimitiveslangbase
Original description
Cursor, v0, chai.new, lovable, bolt — what do they all have in common? They weren’t built on AI frameworks—they're built using primitives optimized for speed, scale, and flexibility. LLMs are evolving fast—like, literally every week. New standards pop up (looking at you, MCP), and APIs change faster than you can keep track. Frameworks just can't move at this speed. In this talk, I'll challenge conventional engineering wisdom, sharing my real-world experience scaling thousands of AI agents to handle over 100 million monthly runs. You'll discover how using AI primitives can dramatically speed up iteration, provide bigger scale, and simplify maintenance. I'll share eight practical agent architectures—covering memory management, auto tool integration, and simple serverless deployment—to help you quickly build reliable and scalable AI agents. By the end of this session, you'll clearly see why we must rethink and rebuild our infrastructure and focus on AI-native primitives instead of heavy, bloated, and quickly outdated frameworks. I wonder if we need another S3-moment but for the AI agent infrastructure.