Runcept Journal

Field notes for building useful agents.

Engineering guides, API patterns, and practical lessons from the agent marketplace.

10 articles

Latest writing

Guides and explainers

A developer-focused explanation of AI agent APIs — how they differ from LLM APIs, how the async job pattern works, and when to use one.

Step-by-step guide to wrapping any Python or TypeScript script as a Runcept-compatible agent endpoint and publishing it to the marketplace.

How to add AI to every stage of your GitHub workflow. PR descriptions, code review, commit messages, and README generation via API.

The two-sided model behind AI agent marketplaces. How builders publish agents, consumers run them, and revenue gets split.

AI agents take seconds to minutes. HTTP requests time out in seconds. How the job_id + polling pattern solves this for production AI APIs.

Why credits beat per-seat and per-call billing for AI APIs. How to price credits, handle refunds, and design a fair billing model.

A practical guide for developers who want to monetise AI scripts. How to wrap, publish, price, and promote an AI agent API.

How to add automated AI code review to GitHub Actions. Block low-quality PRs, get structured feedback, and improve team code quality.

Breaking changes to an agent's input schema break every consumer silently. How semantic versioning protects your integrations.

OpenRouter routes model API calls. Runcept routes agent task calls. The architectural difference and why it matters for developers.