Educating Dora: teaching conversational AI in healthcare to sound right Applied linguists from Newcastle University have been helping a conversational artificial intelligence (AI) automated voice system to sound right.

A @newcastleuni.bsky.social blog post on my and Spencer Hazel's collaborative research with Ufonia. We are using Conversation Analysis to inform the design of their automated clinical assistant, Dora.

#conversationalAI #conversationdesign #digitalhealth #EMCA #HCI

from.ncl.ac.uk/educating-do...

Transforming Outdoor Streaming Discovery: The Launch of Conversational AI Search by ViewLift and MyOutdoorTV Discover how ViewLift and MyOutdoorTV are enhancing outdoor content discovery with AI-powered search, tailored for outdoor enthusiasts across various platforms.

Transforming Outdoor Streaming Discovery: The Launch of Conversational AI Search by ViewLift and MyOutdoorTV #USA #New_York #ViewLift #ConversationalAI #MyOutdoorTV

Agentic commerce runs on truth and context Successful organizations will implement an architectural decision encoded in identity, context, and control.

Digital agents like AI can now go beyond assistance to execution, planning trips and making purchases based on user instructions.
www.technologyreview.com/2026/03/25/1134516/agent...
#AI #ArtificialIntelligence #AIDevelopment #GenerativeAI #ConversationalAI

#SmartHiring #TalentAcquisition #ConversationalAI #PrerecordedInterviews #TraditionalInterviews #VideoInterviews #AIinHiring #FutureOfWork #HiringInnovation

Released: CDE Lite v0.1

A narrow local prototype for conversational drift handling:
deterministic signals, scoped baselines, persistence, freeze behavior, evidence spans, and conservative routing.

Repo: github.com/putmanmodel/...

Feedback welcome.

#ConversationalAI #AIGovernance #NLP #OpenSource

Must Read: A Comprehensive Survey of Computational Persuasion Persuasion is a fundamental aspect of communication, influencing decision-making across diverse contexts, from everyday conversations to high-stakes scenarios such as politics, marketing, and law. The rise of conversational AI systems has significantly expanded the scope of persuasion, introducing…

Must Read: A Comprehensive Survey of Computational Persuasion – Persuasion is a fundamental aspect of communication, influencing decision-making across diverse contexts. The rise of conversational AI systems has significantly expanded the scope of pe... https://tinyurl.com/296dfvmv #ConversationalAI

Imagine chatting with AI assistants directly in your Messages app. Apple could revolutionize conversational AI by integrating it into Messages. #Apple #AI #MessagesApp #ConversationalAI Link: thedailytechfeed.com/apple-consid...

Scaling Multimodal Agentic AI in Medical Education: Multisite Cross-Sectional Study of Simulation Effectiveness in Primary Care Background: Conversational artificial intelligence (#AI) (AI) systems offer potential solutions to traditional constraints in medical consultation skills training, including high costs, scheduling difficulties, and varied standardization. There is limited evidence evaluating medical professionals’ perceptions of AI-generated patient interactions across multiple fidelity dimensions and assessing the educational value of conversational AI for consultation skills training. Objective: This study aimed to evaluate perceptions of conversational AI patient simulations in primary care consultation training, examining functional fidelity, conversational realism, educational value, and implementation readiness. Methods: A cross-sectional evaluation study at a UK medical school (medical students and general practitioners) yielded 47 grouped and individual responses. Participants completed standardized clinical scenarios using the SimFlow conversational AI system, a conversational AI system, followed by a multidomain questionnaire evaluating AI realism, medical content, educational value, feedback, and #usability. Data were analyzed using the Wilcoxon signed rank test, Spearman correlation, and Firth logistic regression to assess domain performance and participant characteristics. Results: Medical content received the highest ratings (median 4.5, IQR 4.0-5.0), with 97.8% (45/46) rating clinical plausibility highly. Educational value was rated positively (median 4.0, IQR 3.0-4.0), although AI realism received moderate scores (median 3.0, IQR 2.0-4.0). Participants with prior AI experience gave significantly higher ratings for AI realism than those without prior experience (mean 3.81, SD 0.63 vs 3.07, SD 0.72; P=.03). Concordance analysis demonstrated moderate-to-strong agreement between individual- and group-level domain rankings (mean Spearman ρ=0.685), supporting consistency between collaborative and individual survey evaluations. Qualitative analysis revealed 4 themes: clinical authenticity, interactional limitations, educational potential, and implementation considerations. Conclusions: Conversational AI demonstrates strong capabilities in functional fidelity (clinical accuracy) despite limitations in conversational fidelity (realism). The technology shows promise as a supplementary tool for clinical skills training rather than higher-stakes assessment, with future development needed in dialogue naturalness and feedback capabilities.

JMIR Formative Res: Scaling Multimodal Agentic AI in Medical Education: Multisite Cross-Sectional Study of Simulation Effectiveness in Primary Care #MedicalEducation #AIinHealthcare #ConversationalAI #SimulationTraining #PrimaryCare

Support that never sleeps! 🤖
AI agents now resolve tickets instantly, guide users, and automate workflows.

The future of customer support is autonomous.

🔗 Learn more: chatboq.com/blogs/conver...

#AIChatbots #ConversationalAI #FutureOfBusiness #Chatboq

AI Psychosis: Does Conversational AI Amplify Delusion-Related Language? Conversational AI systems are increasingly used for personal reflection and emotional disclosure, raising concerns about their effects on vulnerable users. Recent anecdotal reports suggest that prolonged interactions with AI may reinforce delusional thinking -- a phenomenon sometimes described as A…

AI Psychosis: Does Conversational AI Amplify Delusion-Related Language? – Conversational AI systems are increasingly used for personal reflection and emotional disclosure, raising concerns about their effects on vulnerable users. Recent anecdotal rep... https://tinyurl.com/29nktbbc #ConversationalAI

Quantitative Introspection in Language Models: Tracking Internal States Across Conversation Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear probes and other white-box methods compress high-dimensional representations imperfectly and are harder to apply with incr…

Quantitative Introspection in Language Models: Tracking Internal States Across Conversation – tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare. Current methods are... https://tinyurl.com/23zegd4f #ConversationalAI

VoiceInfra - Conversational AI Voice Agents for Enterprise | Voice AI Platform Build and deploy conversational AI voice agents for enterprise telephony. Automate inbound and outbound calls with VoiceInfra's voice AI platform. Reduce call resolution time by 73%, handle unlimited ...

Bonus: We handle token refreshes automatically. Connect once, it just works.

Your customers get instant solutions. Your team saves time. Everyone wins.

Try it free: voiceinfra.ai

#VoiceAI #AIAgents #ConversationalAI

Evaluating AI Agents in Contact Centers: Introducing the Multi-modal Agents Score  Introducing the Multimodal Agent Score (MAS)—a unified, absolute measure of end‑to‑end conversational quality designed for AI agents operating across modalities. MAS is grounded in a simple observation: every service interaction, whether handled by a human or an AI agent, progresses through three fundamental stages. First, the agent must understand the input, accurately interpreting content, intent, and contextual signals. Next, it must reason over that input, determining the correct actions, maintaining conversational continuity, and resolving ambiguity responsibly. Finally, the agent must respond effectively, delivering clear, natural, and confident communication in the appropriate tone and format. The post Evaluating AI Agents in Contact Centers: Introducing the Multi-modal Agents Score  appeared first on Microsoft Dynamics 365 Blog.

Evaluating AI Agents in Contact Centers: Introducing the Multi-modal Agents Score : Introducing the Multimodal Agent Score (MAS)—a unified, absolute measure of end‑to‑end conversational quality designed for AI agents operating across… @MSFTDynamics365 #AI #ContactCenters #ConversationalAI

Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval Large Language Models (LLMs) have achieved unprecedented fluency but remain susceptible to "hallucinations" - the generation of factually incorrect or ungrounded content. This limitation is particularly critical in high-stakes domains where reliability is paramount. We propose a domain-grounded tie…

Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval – Large Language Models (LLMs) have achieved unprecedented fluency but remain susceptible to "hallucinations" - the generation of factually incorrect or ungrounded content. We pro... https://tinyurl.com/28t4wdxt #ConversationalAI

Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models As conversational AI systems become more realistic and widely deployed, users are increasingly uncertain about whether they are interacting with a human or an AI system. When AI identity is unclear, users may unwittingly share sensitive information, place unwarranted trust in AI-generated advice, o…

Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models – As conversational AI systems become more realistic and widely deployed, users are increasingly uncertain about whether they are interacting with a hum... https://tinyurl.com/28y8hu8b #ConversationalAI

Natural Language Processing in Contact Centers How NLP and AI improve customer support with chatbots, automation, routing, and analytics for faster contact center service.

mascallnet.ai/natural-lang...
#AIchatbots #AIcontactcenter #AICustomerService #AIcustomersupport #AIVoiceAssistants
#contactcenterautomation #ConversationalAI #CustomerExperienceTechnology

Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more impatient, incoherent, or skeptical, can cause sharp drops in agent performance, revealing how brittle current AI agents are. Today's benchmarks fail…

Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents – Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more imp... https://tinyurl.com/2xr8tnp7 #ConversationalAI

Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications LLM applications are AI systems whose non-deterministic outputs and evolving model behavior make traditional testing insufficient for release governance. We present an automated self-testing framework that introduces quality gates with evidence-based release decisions (PROMOTE/HOLD/ROLLBACK) across…

Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications – LLM applications are AI systems whose non-deterministic outputs and evolving model behavior make traditional testing insufficient for release governan... https://tinyurl.com/23mjudbh #ConversationalAI

Are your chatbots ready for real conversations?

Without testing, chatbots can:
• Misunderstand user intent
• Give inaccurate responses
• Break conversation flow

Testing powers reliable AI interactions.

Read more: bitl.to/5m2Z

#AI #Chatbots #ConversationalAI #AITesting

💬 GPT-5.3 Instant: Conversaciones cotidianas más fluidas y útiles

La nueva versión instantánea para diálogos más naturales y eficaces.

https://openai.com/index/gpt-5-3-instant

#GPT53 #AI #ConversationalAI #RoxsRoss

ConCISE: A Reference-Free Conciseness Evaluation Metric for LLM-Generated Answers Large language models (LLMs) frequently generate responses that are lengthy and verbose, filled with redundant or unnecessary details. This diminishes clarity and user satisfaction, and it increases costs for model developers, especially with well-known proprietary models that charge based on the n…

ConCISE: A Reference-Free Conciseness Evaluation Metric for LLM-Generated Answers – Large language models (LLMs) frequently generate responses that are lengthy and verbose, filled with redundant or unnecessary details. This diminishes clarity and use... https://tinyurl.com/25rzghxg #ConversationalAI

TURA: Tool-Augmented Unified Retrieval Agent for AI Search The advent of Large Language Models (LLMs) is transforming search engines into conversational AI search products, primarily using Retrieval-Augmented Generation (RAG) on web corpora. However, this paradigm has significant industrial limitations. Traditional RAG approaches struggle with real-time ne…

TURA: Tool-Augmented Unified Retrieval Agent for AI Search – Traditional RAG approaches struggle with real-time needs and structured queries that require accessing dynamically generated content. Academic research has focused on optimizing RAG for sta... https://tinyurl.com/2bg9qfj7 #ConversationalAI

Conversational AI-Enhanced Exploration System to Query Large-Scale Digitised Collections of Natural History Museums Recent digitisation efforts in natural history museums have produced large volumes of collection data, yet their scale and scientific complexity often hinder public access and understanding. Conventional data management tools, such as databases, restrict exploration through keyword-based search or…

Conversational AI-Enhanced Exploration System to Query Large-Scale Digitised Collections of Natural History Museums – System uses conversational AI to query nearly 1.7 million digitised specimen records from the life-science collections of the Austra... https://tinyurl.com/22pnmd2s #ConversationalAI

Not every AI agent problem is a model problem.

If users keep complaining but the system “looks fine,” the issue may be UX misalignment.

A useful triage path:
intent → context → missing tool/data → fix

Most fixes are not magical:
clarify, constrain, route, escalate.

#AgenticAI #ConversationalAI

Goal Alignment in LLM-Based User Simulators for Conversational AI User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that they struggle to consistently demonstrate goal-oriented behavi…

Goal Alignment in LLM-Based User Simulators for Conversational AI – User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. Large Language Models (LLMs) struggle to consis... https://tinyurl.com/256q9fmw #ConversationalAI

A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic Large language model (LLM)-based AI systems have shown promise for patient-facing diagnostic and management conversations in simulated settings. Translating these systems into clinical practice requires assessment in real-world workflows with rigorous safety oversight. We report a prospective, sing…

A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic – Large language model (LLM)-based AI systems have shown promise for patient-facing diagnostic and management conversations in simulated s... https://tinyurl.com/25xkpxr6 #ConversationalAI

AiSA-X AI Chat and Voice agents

Customer conversations are becoming automated.

AiSA-X AI Agents help businesses handle inquiries, capture leads, and provide instant support through intelligent chat and voice conversations.

AI is redefining customer experience.

🌐 aisa-x.ai

#AI #ConversationalAI #AiSAX

Can personalized #conversationalAI persuade on contested science topics like #GMfoods?

New paper tests DeepSeek-style chats experimentally in China:
▶️AI chats shift attitudes
▶️effects differ by segments
▶️personalization can provide boost if done right

Paper: www.cogitatiopress.com/mediaandcomm...

Doctoral Consortium – CUI 2026 The CUI 2026 Doctoral Consortium is a half-day session where doctorate students of conversational user interfaces can discuss their research with other students and experts within the field. Doctoral…

📢 CUI 2026: Doctoral Consortium

PhD students working on conversational user interfaces are invited to apply. Present your research, receive mentorship, and connect with peers and experts.

⏳ Deadline: 9 April 2026
🔗 cui.acm.org/2026/submission/doctoral-consortium/

#CUI2026 #ConversationalAI #HCI

Doctoral Consortium – CUI 2026

📢 Call for Doctoral Consortium – CUI 2026

PhD students researching Conversational User Interfaces are invited to apply to the CUI 2026 Doctoral Consortium.

📅 Deadline: April 9, 2026 (AoE)

🔗 Learn more: cui.acm.org/2026/submiss...
📧 Submit: cui2026-dc@cui.acm.org

#CUI #PhD #HCI #ConversationalAI