Rasa

The enterprise platform for building and operating AI agents across chat and voice channels

[Rasa @Rasa_HQ]

What if the goal isn't teaching marketers to use AI, but teaching AI to speak marketing?

This week, Lauren Goerz its down with Eugenia Zeibig (EZ), Marketing Analytics, Strategy & Innovation Lead at Pfizer, on what it takes to bring AI into pharma marketing — and why compressing weeks of tab-switching into natural-language dialogue is the bar the industry is moving toward.

Inside the episode:
→ Why quality over quantity is how AI earns trust with marketers
→ The "push and pull" design — from reports to responses
→ Why an AI rollout in pharma is really a marketing transformation in disguise

A practical look at going narrow before going wide in regulated industries. Listen now 👇
📺 YouTube: https://t.co/SxGFdyPNvS
🎧 Spotify: https://t.co/GisHKSjmbq

Views shared are Eugenia Zeibig's own.

#AI #MarketingAI #PharmaMarketing #GenerativeAI #EnterpriseAI #AIAgents

[Rasa @Rasa_HQ]

@jetbrains tools are used by over 12 million developers across 92 of the Fortune Global Top 100.

Their support team was answering every ticket by hand.

See how they scaled with Rasa without giving up the quality service their customers expect: 👉 https://t.co/pHmhhfOUXV

#ConversationalAI #DeveloperTools

[Prof Rod @profrodai]

Why does your AI agent demo beautifully and break later? It's the harness, not the model.

Starting Friday at 11 AM EDT, free weekly office hours with @Nebius_Academy and @rasa_hq builders on exactly this.

Share your questions. I will answer live on Zoom for 60 minutes.

RSVP: https://t.co/9uxBHZHZKc

[Prof Rod @profrodai]

If you're in Munich on Saturday 02/05 and would like to understand Why AI agents fail? And what you can do about it!

Come to our free workshop!

We will discuss failure modes and how to counter them and many of our learnings at @Rasa_HQ.

RSVP: https://t.co/2s0X820G7I

[Arklex AI @ArklexAI]

You’ve built your Rasa agent. But no matter how much you test, you can’t predict every path a real user will take. Nobody can.

That’s exactly why Arklex AI and Rasa are teaming up.

Rasa’s CALM architecture gives your agents the flexibility to understand users and the reliability to act predictably. Arksim closes the last mile, automatically running quality tests across thousands of simulated conversations to catch errors before real users ever do.

No more holding your breath at launch.

Try Arksim on your next Rasa project:
https://t.co/pLxccE1t1m

#rasa #AIagent #opensource #AIEval

[Rasa @Rasa_HQ]

Edinburgh folks 👇

We're hosting a gathering today for engineers building in conversational AI, agents & voice AI.

🕓 Mar 18 · 4:30 PM
📍 Salisbury Arms, EH16 5AD
🍕 Food & drinks on Rasa

Spots are limited: https://t.co/mv0VMzKZHN

[Rasa @Rasa_HQ]

Albert Heijn reduced customer service contacts by 50% using Rasa.

The Dutch retail leader achieved a +0.5 CSAT increase and 2x faster dev cycles by moving to a free-text AI agent. No more button-heavy menus.

Join our community for more case studies: https://t.co/V3yCk4SFWY

[Rasa @Rasa_HQ]

New in Rasa Pro 3.14 & 3.15!

✨ Smart Slot Persistence: No more lost data for MCP agents
🛡️ Amazon Bedrock: Now supports "strict: True" tool calling
📝 Cleaner Configs: Unquoted env vars now accepted
🧪 Better E2E: New conftest-style fixtures

Join us: https://t.co/V3yCk4SFWY

[Rasa @Rasa_HQ]

💻 Build a Smart Concert Booking Assistant with Rasa 🚀

@ArjanCodes walks through how to structure a scalable Rasa project, use flows/slots/actions, and bring everything together into a fully working booking agent.

👉 Watch the tutorial: https://t.co/h5mKmcJUqO

[Rasa @Rasa_HQ]

How did Groupe IMA turn a chaotic call center into a CALM one?

With Rasa’s CALM voice architecture, they now serve 30M drivers while cutting call volume and speeding up responses.

👉 Read the case study: https://t.co/1ScYqjO0sR

#CallCenterAI #AI #VoiceAI

[Rasa @Rasa_HQ]

AI security starts with architecture, not patches. ���️

CALM builds safety into the design with:
🔒 controlled execution
🧭 deterministic flows
🧱 schema validation
📜 full audit trails

Stronger architecture = faster approvals.
👉 https://t.co/Vez1dPXnqa

[Rasa @Rasa_HQ]

AI agents ≠ equally secure.

Lakera tests show gaps: data leaks, infra attacks, goal hijacking. Join “Mind the Security Gap” w/ Rasa DevRel Rod Rivera & @LakeraAI Matt Fiedler—Nov 18, 11am ET.

👉 Register: https://t.co/kdgRccnJTF

[Rasa @Rasa_HQ]

We’re excited to announce our placement in the CMP Research Prism
technology assessment for Conversational IVR/Voicebot as a Leading provider. This
evaluation underscores our commitment to top-tier #CX and customer contact innovation.

👉 Download now: https://t.co/UUSe11IOxL

[Rasa @Rasa_HQ]

Building reliable conversational AI demands control, transparency, and validation.
Our 5-minute assessment shows your AI's strengths, gaps, and a practical roadmap for scaling from pilot to production. 🎯

→ Start the assessment: https://t.co/Bg0vPudFdr

[Rasa @Rasa_HQ]

Providence needed AI that could handle patients switching topics mid-conversation. 💬

Their solution: LLMs for conversation + structured flows for execution. ✅
Result: 160K monthly conversations, 59% task completion. 📊

👉Read the full story: https://t.co/Gen2KxMssL

[Rasa @Rasa_HQ]

How secure are different AI agent designs?
Independent research by @LakeraAI tested 2 agents:
❌ Prompt-driven - critical vulnerabilities
✅ Rasa process-guided - attacks contained

It’s not about the LLM.
It’s the architecture.

🔗 Lakera’s assessment: https://t.co/5f9VL0KECe

[Rasa @Rasa_HQ]

"What can this AI agent do—and what can't it do?"

Every security team asks this. Most AI can't answer.
CALM enables complete traceability with policy enforcement through code, not prompts. 🔐

👉Get the white paper: https://t.co/PnOL62nsdr

[Rasa @Rasa_HQ]

A leading insurer needed AI that could scale across service, sales, and voice.
With Rasa CALM, they consolidated logic, and now support 1M+ voice conversations annually.

The result: Higher deflection, fewer fallbacks, full control.

Read the case study: https://t.co/nratR7KqyD

[Rasa @Rasa_HQ]

How do security teams approve AI agents for production?

LLM-first setups blur rules + actions, making policies tough to enforce and decisions hard to trace.

👉 White paper: https://t.co/3O6CZ9AGVR

[Rasa @Rasa_HQ]

Enterprise teams struggle to prove ROI.

Technical teams track accuracy and execs want cost savings.

Result: AI projects look like expenses, not investments.

👉 Get the ROI framework: https://t.co/ccBvrzllAg