Decagon Feature Trails

Decagon's AI Support Agent Platform now features Proactive Agents, integrating user memory and outbound voice capabilities. Guided Discovery enhances these by enabling AI agents to navigate exploratory conversations across product discovery, retention, and expansion. Agents can ask follow-up questions, understand context, and guide users toward the right outcome using natural language instructions defined in Agent Operating Procedures (AOPs). This allows for more adaptive and helpful experiences. The platform has also seen significant improvements in reducing 'barge' rates (callers demanding a human agent) in complex workflows like billing disputes through advanced conversational design, focusing on concise responses, relevant questions, and maintaining conversational state to avoid repetition.

Decagon is introducing Browser Actions, a new capability that allows AI agents to interact with and complete tasks within web-based systems that lack traditional API integrations. This feature enables agents to log in, navigate, and perform actions by directly interacting with the user interface of any accessible web system, mimicking manual user interaction. It aims to resolve tasks previously trapped in manual workflows or requiring complex integrations, thereby extending the agent's capabilities to a wider range of business systems. Security is maintained through a containerized sandbox within Decagon's existing compliance framework, and all agent actions are logged for full visibility and auditability.

Decagon has developed novel statistical methods to improve turn detection in voice AI pipelines. This includes addressing miscalibrated probabilities in Voice Activity Detection (VAD) models using isotonic regression and replacing heuristic-based turn ending decisions with a Bayesian hazard statistic. These improvements have led to significant reductions in broken turns and transcription errors, enhancing the reliability of voice AI agents in production environments. The company is also focusing on scaling voice agent development by transforming tribal knowledge into playbooks, automating manual configurations into product features, and leveraging simulations to reduce manual testing. This has resulted in a ~37% reduction in time-to-go-live and a halving of engineering hours per launch, enabling customers to build sophisticated outbound flows independently.

Decagon is increasingly leveraging open-source Large Language Models (LLMs) for production workloads, particularly for customer service AI agents. This strategy is driven by the need for low-latency, highly specialized models that can be customized for specific tasks. The company's experience suggests a maturity curve for AI use cases, where early-stage applications benefit from general-purpose frontier models, while mature, high-volume use cases transition to fine-tuned open-source models for improved performance and cost-efficiency. Decagon Labs is developing a network of specialized models trained in-house, outperforming foundation models on their real-world use cases, focusing on precision, speed, and reliability for enterprise CX. This includes custom model architectures for functions like speech end detection, workflow execution, and hallucination detection, enabling low latency and high accuracy. The team is also developing frontier post-training techniques and agent architectures, with a current focus on voice agents and expanding proprietary model stack investments in evaluation, training infrastructure, and research.

Decagon is developing systematic approaches to prompt engineering optimization, moving beyond manual iteration. The GEPA (Reflective Prompt Evolution) framework, built on DSPy, uses LLM reflection to automatically improve prompts. Key findings from production deployment include identifying an optimal sample size range (20-100 examples), the critical need for frontier LLMs as reflection models, and the effectiveness of length constraints as regularization to prevent prompt bloat and improve generation. This capability has been extended with automatic optimization of Agent Operating Procedures (AOPs), brand guidelines, and guardrails based on best practices from hundreds of enterprise deployments, and Root Cause Analysis to automatically identify high-impact improvements based on live conversations.

Decagon is developing a robust voice authentication system that addresses the unique challenges of identifying callers in voice AI interactions. This system balances security with user experience by offering flexible authentication models, including pre-authenticated and mid-conversation approaches. It focuses on selecting reliable voice identifiers, optimizing information collection methods (SMS, DTMF, voice transcription), and implementing incremental agent authentication to adhere to least privilege principles. The goal is to enhance security, improve resolution rates, and provide a seamless customer experience.