Introducing Parloa’s Agent Skills: a better way for CX leaders to connect AI agents to the enterprise systems they need to get real work done. To resolve customer issues, your agent needs to talk to your CRM, booking engine, ticketing platform, and compliance requirements. These connections typically require significant engineering work, delaying AI agent go-lives. To accelerate the deployment time, we built Agent Skills on MCP (Model Context Protocol). Now, business teams can configure full integration chains directly in Parloa’s AI Agent Management Platform (AMP), with no code or middleware: > Time to build integrations drops from up to 4-8 weeks to a matter of hours > Every tool call follows the same logic and self-heals when something goes wrong > Success Conditions let you define what “done” means for each task and track real outcomes > Every execution chain is auditable, retryable, and owned by your business team The early results speak for themselves: - 67-second reduction in average handle time - 39% improvement in customer communication during call transfers - 20% more reliable routing in multi-tool environments Learn more about how Parloa’s Agent Skills work: parloa.com/blog/agent-skills…

70 to 80% of agent builders’ time goes into optimization, not building. When something breaks, they use external tools to troubleshoot, re-explaining context from scratch every time and spending hours on a single failure. That’s the expertise bottleneck. Parloa Navigator changes that. We built an AI agent design copilot that works for every builder, from first idea to production: -> Existing procedures, decision trees, and knowledge files can be turned into a working agent in minutes. Ready-made industry templates provide a proven starting point. -> Every unexpected behavior is traced to its exact root cause, with a precise, line-level fix recommendation entirely inside the platform. Prompt health checks proactively catch contradictions and structural issues before they reach a customer. -> Conversational Analytics lets builders ask questions about agent performance in plain language and get instant answers, with prioritized next steps and a downloadable report. Learn more about Parloa Navigator: parloa.com/blog/parloa-navig…

For decades, APIs have been the workhorse of SaaS. That’s kept a lot of developers busy, making enterprise integrations expensive and slow. Parloa’s new and improved Agent Skills are here, and now, service agents can quickly get AI-native access to the tools they need to automate specific tasks, built on model context protocol (MCP). A global travel company using Parloa saw a 67-second reduction in average handle time with routing, authentication, and cancellation skills working together. Learn more about how Parloa’s Agent Skills work: parloa.com/blog/agent-skills…

Introducing Parloa’s Agent Skills: a better way for CX leaders to connect AI agents to the enterprise systems they need to get real work done. To resolve customer issues, your agent needs to talk to your CRM, booking engine, ticketing platform, and compliance requirements. These connections typically require significant engineering work, delaying AI agent go-lives. To accelerate the deployment time, we built Agent Skills on MCP (Model Context Protocol). Now, business teams can configure full integration chains directly in Parloa’s AI Agent Management Platform (AMP), with no code or middleware: > Time to build integrations drops from up to 4-8 weeks to a matter of hours > Every tool call follows the same logic and self-heals when something goes wrong > Success Conditions let you define what “done” means for each task and track real outcomes > Every execution chain is auditable, retryable, and owned by your business team The early results speak for themselves: - 67-second reduction in average handle time - 39% improvement in customer communication during call transfers - 20% more reliable routing in multi-tool environments Learn more about how Parloa’s Agent Skills work: parloa.com/blog/agent-skills…

Next up: SF. After our New York office, we're excited to open our second US office in San Francisco. Looking forward to being even closer to our West Coast customers!

Enterprise AI conversations are hitting the limits of fragmented architectures. As customer expectations rise and AI continues to evolve, enterprises need more than new models. They need a conversational foundation built for natural, real-time interactions. That’s why we built Parloa’s Conversational Platform. parloa.com/blog/parloa-s-con… By unifying conversation orchestration, runtime infrastructure, and real-time interaction handling into a shared foundation, the Conversational Platform enables faster, more natural customer conversations today while creating the flexibility to support future AI models and modalities tomorrow.

"There is no truth out there. If the truth is out there, you wouldn't reinvent things or think about things differently." That mindset led @maltekosub and @o_stefan to build @parloa_ai on voice when everyone said chat would change everything, and to turn down $7.7M to keep building. Watch GC's @max_rimpel in conversation with Malte. Chapters 00:00 — Introduction 00:22 — The 15-Year-Old Entrepreneur 01:26 — Betting on Voice Before Anyone Else 03:50 — Turning Down $7.7M 05:32 — Burning It Down and Building from Scratch 08:26 — Navigating Constant Reinvention 09:35 — One Personal AI Agent for Every Customer 11:47 — Partnering with SAP 12:43 — The European Advantage 16:22 — There Is No Truth Out There 17:52 — Hiring People Who “Go To Olympia”

Very excited to formally announce our London office! No one, king or queen alike, should have to sit on hold for 90 minutes. Opening our London office brings us closer to the enterprises and customers shaping some of the highest expectations for CX, in one of the world's largest software markets. Proud of the team making this next chapter happen. P.S. We’re hiring in the UK. Come join us. parloa.com/careers/

When life gives you latency, squeeze every last bit out 🍋 Today, we’re introducing Parloa’s Conversational Platform 🚀 Customer conversations don’t stay in one lane. Callers switch from voice to chat, change their minds mid-sentence, and want to be able to pick up where they left off. Historically, customer service stacks have rarely been able to keep up. Most are built channel by channel, with disconnected workflows, isolated logic, and fragmented systems. Parloa’s new Conversational Platform tears down these channel walls. Voice and text run on the same conversational layer, with orchestration and infrastructure unified underneath. It’s one platform doing the work that fragmented systems couldn’t. Here’s what the new Conversational Platform delivers: ✅ Faster, more natural conversations, with low-latency streaming responses and natural interruption handling ✅ One design across channels: build the experience once, deploy it everywhere. ✅ A foundation ready for whatever multimodal experiences come next. Parloa’s Conversational Platform drastically cuts down on lag time by leveraging the latest audio streaming technologies to further lower latency and better manage barge ins. The fragmented era of customer service has ended. Explore Parloa’s Conversational Platform: parloa.com/blog/parloa-s-con…

24% faster time-to-call-resolution on average, with some conversations up to 47% faster. That's what one Parloa customer is seeing with Subtask Agents in production. The approach: instead of one bloated prompt trying to handle everything, specialized subtask agents are each responsible for a specific stage of the conversation. Less context passed back and forth to the LLM. Faster resolutions, with the same coherent brand voice across handoffs. More on how Parloa's Subtask Agents work 🔗 okt.to/H1Kd7Y

We’ve lifted the ceiling on reliable AI automation. Meet Subtask Agents: a new multi-agent orchestration model within Parloa's Agent Management Platform (AMP). With Subtask Agents, prompts don’t break when they move from single-use pilots to large-scale production. Generalized agents are broken up into a team of specialized agents. They're bound to each other, working together to share context, be experts at their own job, and deliver resolutions more quickly. Two-layer routing allows for both deterministic behavior and LLM flexibility, making AI Agents work for complex use cases of even the most regulated of industries. Whether you're automating a simple FAQ or a 24-step multi-stage workflow, Subtask Agents keep your AI reliable, compliant, and fast as you scale. 🔗 Learn more: parloa.com/blog/subtask-agen…

A new story published by @OpenAI on how we're building our AI Agent Management Platform (AMP) on top of frontier models like GPT-5.4, and what it takes to make them reliable for real-time, multilingual, enterprise-grade customer conversations 🔗 okt.to/Aq3YLN Our AI agents power millions of conversations across retail, travel, insurance, and other industries. We need to make sure that each one performs reliably from the first second to the last, because in customer service, every interaction counts. Our approach: We continuously evaluate and stress-test new model iterations in production-like environments before rolling them out to live customer interactions. That means simulating real customer calls before agents go live, evaluating every interaction with a mix of LLM-as-a-judge scoring and deterministic checks, and only deploying models that hold up under realistic conditions, not just on abstract benchmarks. Read the full story to learn more.

🌟 Editor's Choice 🌟 "Sometimes, people don’t want to search, click or type. They just want to talk to someone and sort it out." Read more from Latane Conant, CMO of @parloa_ai: hubs.li/Q04fyb7-0

For years, operationally focused automation metrics looked strong while customer outcomes lagged behind. That gap is now visible, measurable, and worse for the enterprise, it’s unforgivable. We just published a first-of-its-kind State of Agentic CX study. stateofcx.parloa.com/ It is an agent-led, human-augmented benchmark of enterprise CX across web, chat, and voice. The findings were truly alarming. What shocked us most was that the breakdown starts before a conversation even begins. Parloa’s AI agents tested global enterprises on how easy it was to get support. The pattern was clear across the board: getting help is harder than it should be. - More than half of websites required scrolling and clicks to locate support. - A third of phone numbers were buried in footers. - 37.8% presented multiple phone numbers with no clear guidance or alignment. Chat is even more constrained. Fewer than 30% of companies offer it at all. And when they do, it is often just for show, placed on the homepage but missing from the pages where customers actually need help. Ready to discover some uncomfortable truths about CX in 2026? Check out the full report.

We just published a first-of-its-kind State of Agentic CX study. We deployed AI agents to analyze thousands of interactions with enterprise CX systems across web, chat, and voice. What did we find? Well. It’s brutal. 99% percent of voice experiences operate like it’s 1990. In 2026. The gap between what customers expect and what companies deliver is enormous, BUT not impossible to close. We wrote about it in our State of Agentic CX report: stateofcx.parloa.com/

We just conducted the largest agent-led customer experience study to-date, and what our discovery agents found shocked us: 💡46% of websites bury the service phone number. 💡9% of chatbot experiences achieve the customer’s goal. 💡99% of voice experiences operate like it’s 1990. 💡1% of enterprises are ready for the agentic future. The gap between what customers expect and what companies deliver is enormous, but not impossible to close. Those who move first will be the ones to win customer loyalty. 👉 Curious how your company compares? Benchmark your readiness in our State of Agentic Customer Experience in 2026 report: stateofcx.parloa.com

Want to join a team that's pushing the boundaries of Agentic CX? If you're based in NYC (or ready to make the move), we’re doubling down and growing fast. Can't make NYC work? No problem, we're hiring for 85 roles globally across Berlin, Munich, London, and beyond. Check out our career page if you're interested! okt.to/slpFSJ

When AI talks to your customers, it becomes your brand voice. One hallucination can undo years of trust-building. Our CMO, Latané Conant, on why crossing the AI divide requires AI you can actually stand behind 👇 okt.to/W2ztsB