Introducing The Fastly Agent Toolkit

The Agent Toolkit Fastly agent toolkit a collection of skills for ai coding agents to work with the fastly platform and edge computing tools. We just launched the fastly agent toolkit. watch our lead engineer, frank denis, walk through a before and after breakdown of token performance and output accuracy from testing the skills.

The Agent Toolkit It is a collection of skills that teach ai coding agents how to work with fastly. if you’ve used the fastly mcp server, you already gave your agent the ability to act on fastly. skills are the other half: they give your agent the knowledge to get things right. Covers the full fastly development lifecycle — from writing and linting vcl, to running compute applications locally, to managing services, caching, security, and deployment via the fastly cli and api. Introducing the fastly agent toolkit: an open source set of ai agent skills for platform concepts, cli workflows, vcl patterns, deployment, and more. Fastly released an open source agent toolkit of curated skills that teach ai coding agents platform specific workflows and patterns.

The Agent Toolkit Introducing the fastly agent toolkit: an open source set of ai agent skills for platform concepts, cli workflows, vcl patterns, deployment, and more. Fastly released an open source agent toolkit of curated skills that teach ai coding agents platform specific workflows and patterns. Ai coding agents struggle with platform specific knowledge that isn't in training data. this toolkit bridges that gap by encoding fastly expertise as reusable skills, making agents dramatically more effective at edge computing tasks. The agent toolkit is an open source collection of ai agent skills. these are curated knowledge files that teach your coding agent how to work with the fastly platform. Lints, tests, simulates, and formats fastly vcl code using the falco tool. also serves as the authoritative vcl reference via the falco go source, which implements fastly's full vcl dialect. Evaluation dataset for the fastly agent toolkit. measures how well ai models complete fastly specific engineering tasks, with and without toolkit skills loaded. each entry is a full evaluation run: a task prompt, model configuration, the model's output, tool call traces, and grading results.

The Agent Toolkit Ai coding agents struggle with platform specific knowledge that isn't in training data. this toolkit bridges that gap by encoding fastly expertise as reusable skills, making agents dramatically more effective at edge computing tasks. The agent toolkit is an open source collection of ai agent skills. these are curated knowledge files that teach your coding agent how to work with the fastly platform. Lints, tests, simulates, and formats fastly vcl code using the falco tool. also serves as the authoritative vcl reference via the falco go source, which implements fastly's full vcl dialect. Evaluation dataset for the fastly agent toolkit. measures how well ai models complete fastly specific engineering tasks, with and without toolkit skills loaded. each entry is a full evaluation run: a task prompt, model configuration, the model's output, tool call traces, and grading results.

The Agent Toolkit Lints, tests, simulates, and formats fastly vcl code using the falco tool. also serves as the authoritative vcl reference via the falco go source, which implements fastly's full vcl dialect. Evaluation dataset for the fastly agent toolkit. measures how well ai models complete fastly specific engineering tasks, with and without toolkit skills loaded. each entry is a full evaluation run: a task prompt, model configuration, the model's output, tool call traces, and grading results.