#ai

Section: Working with language models: agents, prompting, tooling.

2 posts in AI · All tags

Agents as internal services: running an LLM agent inside the system, against the system's own tools
Turning a chat agent runtime into a headless worker that reads its own system via MCP, writes context for a second model, and is evaluated as a build artifact.
Sep 10, 202610 min read
How to prompt ChatGPT and Claude: the short guide
Skip the role play, brief the model like a junior associate, make it write the prompt or interview you, and set up ChatGPT and Claude once. Every claim sourced.
Sep 10, 20269 min read