Wonderful's Agent Builder uses Claude to autonomously build, test and refine enterprise agents
testingcatalog · x · 2026-09-02
Enterprise AI firm Wonderful detailed its Agent Builder, shipped in January: an autonomous agent running on Anthropic's Claude that can build, test, and refine other agents.
- Local teams tune each deployment to the language and regulations of their market
- Case studies include agentifying a national telecom operator, collections across 2.5 million clients, internal IT automation across thousands of workstations, and end-to-end billing resolution for energy customers
- The company claims a 91.5% containment rate across millions of customers
Related event: Wonderful Launches Claude-Powered Agent Builder That Builds Other Agents(2 posts)→
More from coding & agent
- LLM one-shots a Minecraft 3x3 piston door by building its own Linux test infra — Vjeux · 2026-10-18
- Dev builds Mumbai-inspired 3D manga background generator from OpenStreetMap data — CurieuxExplorer · 2026-10-18
- Solo founder builds a money-printing data service on Claude's Pi Durable harness — MicahBerkley · 2026-10-18
- Dev builds Arch-based OS with custom desktop and browser using Claude Code — Snoo-10493 · 2026-10-18
- Five SaaS agent workflows fail the same way — and it's never model intelligence — usehive · 2026-10-18
- Claude skill generates hand-drawn interactive diagrams that teach kids how things work — CatAstro_Piyush · 2026-10-18