Comparing Code-Driven and LLM-Driven Workflows for Internal Agent Development
By
pavel_lishin
The bagel they save for the regulars. Don't skim, savour.
Summary
The article discusses the author's experience building internal agents and compares code-driven versus LLM-driven workflows. While initially believing LLMs with tool usage could solve arbitrarily complex workflows, the author now recognizes that many problems are simpler, cheaper, and faster to solve with traditional software. The post explains why determinism matters in workflow systems and describes an approach that supports both code and LLM-driven workflows, arguing this hybrid solution is necessary for practical implementation.
Key quotes
· 4 pulledWhen I started this project, I knew deep in my heart that we could get an LLM plus tool-usage to solve arbitrarily complex workflows.
I still believe this is possible, but I'm no longer convinced this is actually a good solution.
Some problems are just vastly simpler, cheaper, and faster to solve with software.
This post talks about our approach to supporting both code and LLM-driven workflows, and why we decided it was necessary.
You might also wanna read
Why Treating LLMs as Black-Box Problem Solvers Fails: Lessons from Processing 100 Compliance PDFs
The article discusses the author's experience transforming 100 messy compliance PDFs into structured JSON rules. It critiques the common app
towardsdatascience.com·4d ago
AI Integration in Software Development: How Claude Code and Agentic Workflows Are Transforming the Terminal into a Conversational Interface
The article discusses how AI is transforming software development by integrating large language models (LLMs) into development workflows, pa
Prototypr·4mo ago
How I Used Coding Agents to Automate My AI Research Work in Copilot Applied Science
An AI researcher shares their experience using coding agents to automate intellectual work, specifically building agents that automate parts
GitHub·2mo ago
A practical framework for deciding when to use AI in L&D workflows
The article addresses the confusion L&D teams face regarding AI adoption, caught between executive pressure to use AI everywhere and complia
drphilippahardman.substack.com·3d ago
Duolingo Engineers Implement Agentic Workflows to Scale Productivity
The article discusses how Duolingo engineers are implementing agentic workflows to scale engineering productivity. Instead of just using AI
Duolingo·5mo ago
Groovy: Unified Dashboard for AI Agents with Universal Search Across LLMs
Groovy is a unified dashboard for AI agents that offers universal search and signaling across different large language models (LLMs). The ar
Product Hunt·4mo ago