Jack Gordley
Software Engineer at Grafana Labs working on AI evals, observability, and incident investigation. Previously Amazon Bedrock. Go Irish 🍀
Every word typed out on this blog is my own, by hand, not by an LLM. I still believe blogging and most writing to be a uniquely human activity.
Recent writing
Recent pieces from this blog and external articles I wrote for companies or projects.
Introducing o11y-bench: an open benchmark for AI agents running observability workflows
Build reliable AI agents with Amazon Bedrock AgentCore Evaluations
LLM Context-Friendly Test Suite Outputs (build-output-tools-mcp)
The Most Cost-Effective LLM Coding Loadout for the Casual Developer
From Text to Action: How LLMs Became AI Agents
On this blog
Posts published here on AI systems, developer tools, agents, and side projects.
LLM Context-Friendly Test Suite Outputs (build-output-tools-mcp)
Post covering an MCP tool to run tests/builds and routes the output to a smaller, specialized LLM for summarization to avoid flooding the main context thread of Claude Code.
The Most Cost-Effective LLM Coding Loadout for the Casual Developer
TLDR; Claude Pro with Claude Code + OpenRouter Zen MCP
From Text to Action: How LLMs Became AI Agents
A mini-history lesson on how LLMs gained the ability to execute actions and the state of Agents in 2025
Calvin - An Open-Source Google Calendar Assistant
In-depth project rundown of a Langchain assistant that can manage your Google Calendar
External writing
Articles I wrote or co-wrote for a company, product, or project outside this blog.
Introducing o11y-bench: an open benchmark for AI agents running observability workflows
Open benchmark for evaluating AI agents on observability workflows.
Build reliable AI agents with Amazon Bedrock AgentCore Evaluations
A practical walkthrough of agent evaluation across development and production.
Game dev projects
A few game jams I've participated in.