How Cresta turned CX expertise into an agent builder on the Claude Agent SDK
- ID
- 31939
- Status
- summarized
- Published
- 05 Oct 2026, 8:00 AM
- Fetched
- 06 Oct 2026, 1:46 AM
- Provider
- Claude
- Category
- ai-labs
- Original URL
- https://claude.com/blog/how-cresta-turned-cx-expertise-into-an-agent-builder-on-the-claude-agent-sdk
- Source URL
- https://raw.githubusercontent.com/leontloveless/ai-rss-feeds/main/feeds/claude.xml
Summary
- Score
- 3.5
- Created
- 06 Oct 2026, 1:46 AM
- Tags
- Audience
- developersai_agent_usersai_ml_learnerssaas_founders
What happened
Anthropic's startup case-study post describes how Cresta (founded 2017, CEO Ping Wu, $270M+ raised, $100M+ ARR, with customers named as United Airlines, CVS Health and Marriott) built 'Conductor', a natural-language agent builder that takes a grounded blueprint through implementation, evaluation and optimization. Cresta first built Conductor internally on Claude Sonnet and Claude Opus to support customer deployments, then moved it onto the Claude Agent SDK as a general-purpose harness for open-ended development work. The excerpt cuts off mid-sentence at that point, with no benchmarks, pricing, latency or evaluation numbers.
Why it matters
The only transferable detail here is the architectural pattern: using an agent SDK as a general-purpose harness so an agent can build and refine other agents, rather than hard-coding a fixed pipeline. Everything else is vendor framing - Cresta's revenue, funding and customer logos are context, not evidence, and the post supplies no eval scores, token costs or failure modes, so there is nothing concrete to adopt or budget for. If you are comparing agent-builder tooling, ask for measured accuracy and cost-per-agent numbers before treating this as a reference.
Discussion angle
Is an 'agent that builds agents' loop (natural language brief → grounded blueprint → implementation → eval → optimization) meaningfully different from a prompt-template library wrapped around a model SDK - and what specific numbers (eval pass rate, cost per agent, latency) would you demand before shipping one to a client?