Quesma is researching the economics of AI agents and agentic coding costs. A personal deep research setup burned through the entire limit of the Claude Max 5x plan in 30 minutes, leading to a focus on cost reduction and trust improvement using existing subscriptions.

Upgrading to Opus 4.6 has reduced operational costs compared to Sonnet 4.0. The new architecture allows a low-cost agent to determine the necessity of engaging the more expensive model, preventing 80% of failures from reaching it.

Reco utilized AI to rewrite JSONata in one day, resulting in a cost savings of $500,000 per year. The process involved using an existing specification and test suite to guide the AI in implementing the code until all tests passed.

Open source MCP plugin that automatically injects prompt cache breakpoints into Claude Code sessions. Up to 90% token cost reduction — zero config.

MCP agents incur high costs due to the inclusion of an extensive tool catalog in JSON Schema format. A CLI generated from an MCP server using CLIHub performs the same functions at a significantly reduced cost.