Cresta Opens Its AI Agent Platform With End-to-End Self-Service for Developers

Businesses can now build and optimize customer-facing AI Agents with enterprise-grade developer tools and infrastructure on the Cresta platform.

SUNNYVALE, Calif., Oct. 29, 2026 /PRNewswire/ -- Cresta, the AI operating system for customer experience, today announced end-to-end self-service for developers building AI agents in-house or for their clients. Teams can now build, test, deploy, and optimize customer-facing AI agents on the Cresta platform. Enterprise developers using Cresta have taken AI agents from first requirements to production on their own in as little as one week.

With Cresta Conductor, developers build agents through their own repo and CI/CD pipeline. Companies then get the infrastructure to run those agents with confidence: controlled releases, access control, and visibility into AI usage and cost, backed by proven enterprise compliance.

"Cresta has deployed AI Agents with the world's leading companies. Now all of those best practices, breakthroughs, and insights have been productized, so in-house developers can build customer-facing agents to that same standard themselves," said Ping Wu, CEO of Cresta. "We've handed them the keys, and love what they're already building."

Engineering teams increasingly want to build AI agents themselves. Many already work with coding agents like Claude Code, and they expect AI agents to go through the same code review, testing, and release process as any other production software. Agent builders often keep agents in a visual interface outside that process, and building directly on AI models means creating guardrails, testing, and release tooling from scratch. Self-service is for teams that want to do the work in-house, with Cresta's tools, training, and support.

With the Cresta platform, developers get:

• Full self-service: Developers take an agent from discovery through build, testing, and go-live, then keep improving it on their own timeline. Cresta makes it possible for any team that writes and ships software to build production-grade AI agents on Cresta without a dedicated team of AI specialists. For example, a developer at an Australian telecom provider rebuilt an existing production chat agent, with more than 10 subagents and custom code, from another platform onto Cresta in under a week. Teams that want hands-on help can still work with Cresta's forward-deployed engineers at any stage.
• Agent deployment, productized: Built on the Claude Agent SDK in collaboration with Anthropic, Conductor was developed to enable Cresta's forward-deployed teams  to build AI agents faster and more effectively for Cresta customers. Those product managers and engineers still build and deploy production agents with Conductor and Cresta CLI, spending up to 5x less time on custom tools, code, and deployments. Customer and partner developers get the same tools to build their own agents, along with the Cresta AI Agent SDK for writing custom code in standard Python that connects agents to their own systems. They work from their own terminals and coding assistants, and because Conductor supports the open Agent Skills standard, skills a team already wrote for those assistants carry over.
• A platform enterprises can trust with customers: Cresta gives technical leaders the infrastructure to trust AI agents in front of customers: the controls they expect from any production system, backed by proven enterprise compliance. Releases are controlled so teams can send a share of conversations to a new version, A/B test versions, and roll back if needed. Builder and reviewer permissions set who can build, review, test, and inspect each agent. Cresta holds SOC 2 Type II, ISO 27001, and ISO 27701 certifications, is PCI DSS and HIPAA compliant, and was the first customer experience AI provider to achieve ISO 42001, the international standard for AI management systems.
• Training and certification for teams building on Cresta: Cresta has launched Cresta Academy, which trains and certifies customer and partner engineers to build AI agents on Cresta. Engineers learn how to design and test an AI agent using Cresta tools, prepare it for launch, and keep improving it once it's live, so teams know what a production-ready agent looks like and how to make it better over time. Certification gives technical leaders a clear standard for which engineers are ready to build and ship agents on their own. Academy is available to customers and partners through the Cresta Help Center.

These same developer tools are empowering a rich partner ecosystem to build and deploy agents at scale with the Cresta platform.

"Scaling AI agents in enterprise CX takes more than technology," said Paul Ignasinski, Chief Digital Transformation Officer at Atento. "It takes the operational discipline to design, test, and refine them continuously. Cresta Conductor gives our teams a self-serve platform to do exactly that as we build an AI agent workforce for our clients."

"Our engineers started building on Cresta Conductor in June, learning from the docs, hands-on work, and Cresta's team," said Jamie Timm, Global SVP, Service Delivery & Operations at TELUS Digital. "We're deeply invested in platform depth, because that expertise is what turns AI capabilities into customer experiences that work at scale. Cresta's developer tooling gives our engineers that depth without sacrificing the accessibility they need to ship quickly."

Learn more about building your own AI agents on Cresta.

About Cresta:
Cresta is the AI operating system for customer experience, where human and AI agents work together to power the entire customer lifecycle. Cresta automates conversations and back-office processes, augments human work, and puts insight into action, so each conversation makes the next one better. Companies like United Airlines, CVS Health, and Marriott use Cresta to turn every interaction into a competitive advantage. Learn more at Cresta.com.

SOURCE Cresta