LLM
Code Generation
Evaluation
Caret

Evaluating LLM Code Output is Hard

The biggest technical challenge we faced with Caret was determining whether LLM-generated workflows actually worked. Here's what we learned and how we're approaching it differently next time.

June 17, 2025
Firstloop Team
5 min read
AI Agents
Development Process
GitHub Copilot

It's Agents All The Way Down

From pair-programming in IDEs to coordinating teams of autonomous agents. Here's how coding agents are evolving and what comes next.

June 12, 2025
Cody Lund
6 min read
GitHub Copilot
Claude Code
OpenAI Codex

How We Maximize Productivity with Async Coding Agents

We run up to five coding agents simultaneously, and they often one-shot solutions. Here are our secrets to maximizing their value.

June 11, 2025
Cody Lund
6 min read
AI
Development
GitHub
Copilot

Converting Loom Videos to Detailed GitHub Issues

How recording a Loom video and converting it to a GitHub issue with AI creates better context for coding agents.

June 11, 2025
Jake Colling
4 min read
Caret
Webhooks
LLM

Connecting The Infinite Cloud to Caret Workflows

We use AI to automatically map arbitrary webhook payloads or emails to workflow inputs in Caret.

June 11, 2025
Cody Lund
4 min read
Caret
LLM
QuickBooks

Transforming Unstructured Data into API Calls in Caret

Discover how we use AI to bridge the gap between natural user input and complex API requirements, making integrations intuitive and error-free.

June 11, 2025
Cody Lund
3 min read