Weave Blog

Implementation notes from the Weave codebase

Engineering write-ups about orchestration, evals, workflows, and the systems behind Weave.

pgermishuys · 6 min read

Rising AI Subscription Costs Make Tool Choice More Important

As AI subscriptions and usage-based pricing get more expensive, teams need better judgment about which model to use for which task.

Rising AI Subscription Costs Make Tool Choice More Important ​ For a while, the default posture around AI tooling was simple: pay for the best plan you can justify, point the strongest model at everything, and move fast. That posture is getting more expensive.

April 28, 2026

AI PricingGitHub CopilotAnthropicDeveloper Tools

pgermishuys · 7 min read

Agent Evals in Weave

What agent evaluations are, the main types that matter, and how Weave structures them to keep comparisons useful and honest.

Agent Evals in Weave ​ It is easy to build an impressive agent demo. It is much harder to know whether the agent is actually improving. That is the role of an agent evaluation: taking a behavior you care about and turning it into something you can measure repeatedly.

April 14, 2026

Agent EvalsCIArchitecture