How I'm Adopting Agentic Coding

2026-06-09 · Source: AI Advances - Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

The author details their personal adoption of "agentic coding" and generative AI, marking a shift from their prior focus on data engineering. Initially a mild AI enthusiast, they quickly integrated ChatGPT into their workflow for coding assistance and to replace traditional search engine tasks. This journey included early experimentation with local large language models and the development of a small Retrieval Augmented Generation (RAG) prototype. This prototype utilized a Streamlit chat interface, GPT-3.5, OpenAI embedding models, and LangChain for orchestration, though it was ultimately abandoned due to company security concerns. The author continues to monitor advancements from new players such as Mistral AI, Meta, Google Gemini, and DeepSeek.

Key takeaway

For software engineers exploring AI integration, consider adopting generative AI tools like ChatGPT to streamline coding and information retrieval. You should experiment with local LLMs and build small RAG prototypes using frameworks like LangChain to understand their practical applications and limitations. This proactive exploration helps you adapt to evolving AI capabilities, even if initial projects face organizational hurdles.

Key insights

Generative AI tools like ChatGPT can significantly transform coding workflows and information retrieval.

In practice

• Use generative AI for coding assistance and search replacement.
• Experiment with local LLMs for custom applications.
• Build RAG prototypes using tools like Streamlit and LangChain.

Topics

• Agentic Coding
• Generative AI
• ChatGPT
• Large Language Models
• Retrieval-Augmented Generation
• LangChain
• Streamlit

Best for: AI Engineer, Software Engineer

Related on AIssential

• We Evaluated ChatGPT vs. Google on 500 Search Queries — ChatGPT significantly outperforms Google on coding queries and ties it on general informational queries, despite not being optimized for search.
• 🤖AI Agents Weekly: Claude Opus 4.6, GPT-5.3-Codex, Agent Primitives, METR Long Tasks, Codex App, OpenAI Frontier, C Compiler with Parallel Agents — Agentic workflows can automate end-to-end image generation and iterative refinement using LLM plugins.
• The RAG Industry Is Selling Complexity While the Best Coding Agents Are Going the Other Way — Agentic search offers a simpler, more reliable alternative to RAG for AI coding agents by focusing on intent translation.
• OpenAI says Codex is coming to your phone — OpenAI's Codex now offers mobile and desktop control, intensifying competition in agentic coding tools.
• Writing Code with Github Copilot and ChatGPT Together — III — AI code agents excel at routine tasks but require human oversight for novel or complex problems.
• AI Chatbot Development Services for Enterprise Data-Sensitive Processes — Custom generative AI chatbots are becoming functional infrastructure for enterprises handling sensitive data and complex workflows.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AI Advances - Medium.