The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
why every #AI engineer needs #Pydantic:
LLMs don’t return data. They return text that looks like data, most of the time. And “most of the time” is how production systems break.
I made a 6-minute video on why Pydantic is the one library every AI engineer should know:
→ One class does three jobs: it tells the model what to produce, validates what comes back, and powers autocomplete
→ Your function signature becomes the tool definition
→ Validation errors become feedback the model can fix itself
→ It’s already in your stack (OpenAI, Anthropic, LangChain, FastAPI…)
Plus a quick look at Pydantic AI, which runs that whole loop for you.
Prompts are suggestions. Schemas are contracts. 🎯
text that looks like data.. painfully accurate
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
SES AI is a battery technology company accelerating the energy transition through AI-powered material discovery, battery development, manufacturing, and management.
SES AI approached us with a website redesign driven by its new “All-in on AI” strategy. As AI became central to the company’s work across safety, manufacturing, and science, the existing website still focused primarily on its battery-hardware side. We redesigned the experience to clearly communicate the three AI pillars, while making the website simpler, more direct, and easier to navigate.
This looks insane. The robotic arm with the battery cell is such a strong visual. Love how clean you kept it despite it being AI heavy.
CRAG — Self-Correcting Research Assistant
Overview
A research-assistant project exploring how AI applications can retrieve information and improve the quality of their responses through a self-correction workflow.
Project focus
Python-based AI application development.
Retrieval and research workflow design.
Improving answer reliability through evaluation and correction.
Technologies: Python, AI, retrieval-augmented generation.
Self-correcting retrieval is the upgrade RAG has needed, Daniel. Most systems stop at the first retrieval and hope for the best, so building evaluation and correction into the workflow is a real reliability win. The live telemetry dashboard makes it feel production-ready.
AI Agent vs Body
One AI agent is single-player.
Work is multiplayer.
Start with one agent. I explain it as a body.
The LLM is the brain.
It reads, writes, and reasons. It knows nothing about your business.
RAG is the brain with a library.
It looks things up in your documents before it answers.
MCP is the nervous system.
Model Context Protocol. One standard way to wire the brain to tools and data. Build the connection once, and any agent that speaks MCP can use it.
Skills are muscle memory.
Know-how saved once and loaded when a task calls for it.
The agent is the brain with hands.
It plans the steps, then carries them out in your tools.
