Four research capabilities position Agentic AI as a trustworthy decision partner for enterprises

SINGAPORE, April 29, 2026 /PRNewswire/ -- As AI systems become more capable of answering questions and executing tasks, the central question for enterprises has shifted from whether AI can be used to whether it can be trusted. Many AI systems continue to deliver confident responses even when uncertain—an issue that, in business contexts, can escalate from a poor user experience into operational risk.

Appier, an AI-native Agentic AI as a Service (AaaS) company, today announced new research from its global AI team focused on a critical capability: AI self-awareness. The research enables AI to ask more precisely, assess risk, and recognize the limits of its own knowledge. These capabilities are embedded across its Ad Cloud, Personalization Cloud, and Data Cloud—accelerating the transition from usable AI to trustworthy AI, and positioning AI as a reliable decision partner for enterprises.

Enterprise AI risk is no longer hypothetical. From customer service errors to content hallucinations, a consistent pattern has emerged across the industry: AI frequently fails to recognize when it should not respond at all. "As AI agents increasingly connect people, tools, and software into more complex systems, the true source of enterprise advantage will be whether AI can be trusted to make decisions," said Dr. Chih-Han Yu, Chief Executive Officer and Co-Founder of Appier. "Through our proprietary data, domain expertise, industry-specific models, and frontier research, Appier is bringing trustworthy Agentic AI into real-world business scenarios and enabling enterprises to make decisions alongside AI with confidence."

Appier has long invested in academic–industry collaboration and frontier research, publishing over 400 papers in leading international journals and conferences. Its recent work on trustworthy Agentic AI has been recognized at top-tier venues including NeurIPS, ACL, and EMNLP.

Appier has identified four key barriers to enterprise AI adoption: Models lose previously learned capabilities after fine-tuning, AI either guesses without sufficient information, or asks too many clarifying questions when faced with ambiguity. Systems lack the risk awareness required to determine when to respond. Traditional benchmarks fail to measure whether AI can actually solve a given task.

To address these challenges, Appier has developed four corresponding capabilities that enable AI to ask precisely, evaluate risk, retain prior knowledge, and accurately assess its own limits.

For precise inquiry, Appier's research found that internal model judgment alone is insufficient. By incorporating verifiable external feedback and cross-model validation prior to responding, AI can ask more relevant questions and improve the balance between task accuracy and user experience by over 30%.

For risk assessment, Appier applies a "skill decomposition" approach that separates problem-solving, confidence estimation, and expected-value decision-making—allowing AI to act more rationally under uncertainty and reduce high-risk expected loss by 60–70%.

For capability calibration, Appier has introduced a novel mechanism that predicts the probability of a correct answer before responding, providing clearer visibility into capability boundaries at near-zero inference cost (less than one token).

To address catastrophic forgetting, Appier developed a fine-tuning method that identifies and avoids high-perplexity tokens, preserving prior reasoning and instruction-following abilities. This approach reduces performance degradation on non-target tasks to near zero, with a preprocessing time of approximately eight minutes—enabling more stable and efficient deployment in enterprise environments.

These research advances are already integrated into Appier's AI Agent workflows. In consumer-facing scenarios, a beauty brand's AI agent without self-awareness might respond to a Mother's Day restaurant inquiry with off-brand content, fabricate product details, or over-promote its offerings—damaging brand trust.

By contrast, Appier's Sales and Service Agents understand their boundaries, decline to answer beyond their expertise, clarify ambiguous queries before responding, and recommend products only when appropriate, reducing the risk of misinformation and inappropriate interactions.

The same principle applies in enterprise operations. When a marketer requests an audience of over 100,000 users spanning five years for a Mother's Day campaign — but the system has access to only one year of data — Appier's Audience Agent does not fabricate a response. Instead, it flags the data limitation, clarifies the requirement, and proposes viable alternatives with a clear explanation of the trade-offs, reducing operational decision risk. In current deployments, Appier AI Agents block 80%^[1] of risky responses for enterprise users, with performance continuing to improve as data evolves.

The future of enterprise AI will be defined not by capability alone, but by trust. As AI evolves from a tool into an "AI colleague," enterprises require agents that know when to answer, when to ask, and when to decline. By integrating research, technology, and product innovation, Appier is closing this critical gap—transforming AI into a trustworthy partner that delivers measurable, sustainable business outcomes.

About Appier

Appier (TSE: 4180) is an AI-native Agentic AI as a Service (AaaS) company that empowers business decision-making with cutting-edge AdTech and MarTech solutions. Founded in 2012 with the vision of "Making AI Easy by making software intelligent," Appier endeavors to help businesses turn AI into ROI with its Ad Cloud, Personalization Cloud, and Data Cloud solutions. Now Appier has 17 offices across APAC, the US and EMEA, and is listed on the Tokyo Stock Exchange. Visit www.appier.com for more company information, and visit ir.appier.com/en/ for more IR information.

CONTACT: pr@appier.com