Akka

Adopting agentic AI systems for financial services applications - Agentic AI has potential to reshape the financial services landscape, but challenges remain in moving from current “human in the loop” to the fully autonomous systems that can reason and take independent action. Eric Newcomer of Intellyx writing for Akka. https://xmrrwallet.com/cmx.plnkd.in/eybFYCWH

I sold my soul and used AI to produce this demo. I wonder if you can tell when it's actually me talking and when it's not. The world is changing ... Would agents dominate the software landscape? I don't know. I know that Akka fits really well with this concept.

𝗖𝘂𝗿𝗶𝗼𝘂𝘀 𝗵𝗼𝘄 𝗠𝗖𝗣 𝘄𝗼𝗿𝗸𝘀 𝘄𝗶𝘁𝗵 𝗔𝗸𝗸𝗮? The 𝗠𝗼𝗱𝗲𝗹 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗣𝗿𝗼𝘁𝗼𝗰𝗼𝗹 enables LLM-based agents to interact with external tools and data sources in a 𝗰𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝘁, 𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 way. Check out two demo projects:   • Customer registry project   • Customer service assistant With the 𝗔𝗸𝗸𝗮 𝗦𝗗𝗞, these workflows become applications that are: ✅ Cost efficient ✅ Scalable ✅ Resilient 👇 Watch now and try it yourself. #Agents #Developer #AI #AgenticAI #DistributedComputing

𝗧𝘂𝗿𝗻 𝗿𝗮𝘄 𝗱𝗮𝘁𝗮 𝗶𝗻𝘁𝗼 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲 𝗶𝗻𝘀𝗶𝗴𝗵𝘁𝘀 𝘄𝗶𝘁𝗵 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜. Our new demo reveals how the 𝗔𝗸𝗸𝗮 𝗦𝗗𝗞 and 𝗢𝗽𝗲𝗻𝗔𝗜 are used to create a system to stream temperature readings and instantly flag anomalies. 𝗦𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗱𝗮𝘁𝗮, 𝘀𝗺𝗮𝗿𝘁𝗲𝗿 𝗼𝗽𝗲𝗿𝗮𝘁𝗶𝗼𝗻𝘀. 👇 Watch the demo and see intelligence in action #Agents #Developer #AI #AgenticAI #DistributedComputing

𝗠𝗲𝗲𝘁 𝘁𝗵𝗲 𝗔𝗸𝗸𝗮 𝗔𝗴𝗲𝗻𝘁 𝗰𝗼𝗺𝗽𝗼𝗻𝗲𝗻𝘁! A new 𝗔𝗸𝗸𝗮 𝗦𝗗𝗞 𝗰𝗼𝗺𝗽𝗼𝗻𝗲𝗻𝘁 designed to:   • Interact with AI models like LLMs   • Run with or without durable memory   • Operate autonomously and integrate seamlessly with other Akka components Key features: ✓ Support for multiple LLM models ✓ Memory out of the box ✓ System message templating ✓ Response transformation ✓ Function tools & RAG ✓ Multi-modal streaming in/out & multi-agent orchestration 🎥 Watch the demo: https://xmrrwallet.com/cmx.pbit.ly/4lLcWrn #Agents #LLMs #AI #AgenticAI #DistributedComputing

Don't miss the demo of the new #Akka #Agentic #DevEx we did last week—the simplest way to build agents on the market today. Let me know what you think. https://xmrrwallet.com/cmx.plnkd.in/dGa_dqM3

𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗔𝗜 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝘀𝘁𝗿𝘂𝗴𝗴𝗹𝗲 𝘄𝗶𝘁𝗵 𝗹𝗮𝘁𝗲𝗻𝗰𝘆 𝗮𝗻𝗱 𝗰𝗼𝗻𝗰𝘂𝗿𝗿𝗲𝗻𝗰𝘆. 𝗔𝗸𝗸𝗮 𝗦𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 brings asynchronous, backpressure-managed streams to agentic AI, enabling: • 𝗥𝗲𝗮𝗹-𝘁𝗶𝗺𝗲, 𝗵𝗶𝗴𝗵-𝗰𝗼𝗻𝗰𝘂𝗿𝗿𝗲𝗻𝗰𝘆 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻𝘀 with LLMs • 𝗦𝗰𝗮𝗹𝗮𝗯𝗹𝗲, 𝗯𝗶-𝗱𝗶𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝗮𝗹 𝗱𝗮𝘁𝗮 𝗳𝗹𝗼𝘄𝘀 without bottlenecks • 𝗖𝗼𝗻𝘁𝗿𝗼𝗹𝗹𝗲𝗱 𝗿𝗲𝘀𝗼𝘂𝗿𝗰𝗲 𝘂𝘀𝗲 for resilient and responsive AI systems 💡 Build agentic AI that stays 𝗳𝗮𝘀𝘁, 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁, and 𝗿𝗼𝗯𝘂𝘀𝘁—even under massive loads. Explore how 𝗔𝗸𝗸𝗮 𝗦𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 handles complex LLM interactions at scale: https://xmrrwallet.com/cmx.pbit.ly/46U4G3u #AkkaStreaming #AgenticAI #AI #Technology #Developer

🧠 AI agents can’t act intelligently if they can’t remember. 𝗔𝗸𝗸𝗮 𝗠𝗲𝗺𝗼𝗿𝘆 gives your agents durable, distributed memory so they can: • 𝗥𝗲𝗰𝗮𝗹𝗹 and 𝗿𝗲𝗮𝘀𝗼𝗻 across short-term and long-term contexts • 𝗦𝘁𝗮𝘆 𝗰𝗼𝗵𝗲𝗿𝗲𝗻𝘁, 𝗮𝗱𝗮𝗽𝘁𝗶𝘃𝗲, and 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘇𝗲𝗱 over multiple interactions • 𝗦𝘁𝗿𝗲𝗮𝗺 𝘂𝗽𝗱𝗮𝘁𝗲𝘀 in real time with event-driven subscriptions • 𝗦𝗰𝗮𝗹𝗲 𝗲𝗳𝗳𝗼𝗿𝘁𝗹𝗲𝘀𝘀𝗹𝘆 with sharded, in-memory data for sub-millisecond reads Build agentic AI systems with 𝗮𝘂𝗱𝗶𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆, 𝘁𝗿𝗮𝗰𝗲𝗮𝗯𝗶𝗹𝗶𝘁𝘆, and 𝗿𝗲𝘀𝗶𝗹𝗶𝗲𝗻𝗰𝗲 baked in. 📖 Read the blog to explore features like 𝗰𝗼𝗺𝗽𝗮𝗰𝘁𝗶𝗼𝗻, 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗲𝘃𝗲𝗻𝘁𝘀, and 𝘃𝗶𝗲𝘄𝘀: https://xmrrwallet.com/cmx.pbit.ly/44ZOJGq #AkkaMemory #AgenticAI #AI #Technology #Developer

𝗘𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 — get to production 𝗳𝗮𝘀𝘁𝗲𝗿 and 𝘀𝗽𝗲𝗻𝗱 𝗹𝗲𝘀𝘀. Our on-demand webinar shows how leading enterprises: ✓ Meet demanding SLAs and eliminate the risks of uncertainty ✓ Deliver agentic systems 3x faster ✓ Consume 1/3 the compute ✓ Lower token consumption 𝗕𝘂𝗶𝗹𝗱, 𝗿𝘂𝗻, and 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗲 enterprise agentic systems with 𝗰𝗲𝗿𝘁𝗮𝗶𝗻𝘁𝘆, 𝘀𝗰𝗮𝗹𝗲, and 𝗿𝗲𝘀𝗶𝗹𝗶𝗲𝗻𝗰𝗲. 𝗪𝗮𝘁𝗰𝗵 𝗼𝘂𝗿 𝗼𝗻-𝗱𝗲𝗺𝗮𝗻𝗱 𝘄𝗲𝗯𝗶𝗻𝗮𝗿: https://xmrrwallet.com/cmx.pbit.ly/45gmiVW #AgenticAI #Agents #AI #DistributedComputing #Technology

System architecture for agentic AI. What does it take to make AI safe and scalable? This is a collaboration with Anand Nimkar - AI partner @ Deloitte - on enterprise considerations that we have both encountered while building reliable, scalable agentic systems. Start with how you will host models ... SLMs ... LLMs ... model registry ... LLM proxy for external commercial models ... will you be self-hosting GPU compute Establish semantic knowledge store ... vector DB cluster ... kafka, A/V, IOT, even streams of real-time knowledge How will you run multi-agent clusters for scale and resilience? What will be cross-cluster, and cross-agent protocols supported? Establish a memory persistence model (cough, it's implicit with Akka). Will you have private, shared, or external MCP servers? What is their auth? Agentic orchestration will need to be front-ended by an API serving and gateway layer that supports HTTP, gRPC, JSON-RPC, MCP, etc. You'll need to have auto-elasticity, multi-team access controls, and persistence mgmt policies. (cough, Akka Automated Operations handles all this for you). Deployment requires a registry for staging assets within each region. Will you have multi-region operations? Multiple regions to isolate data sovereignty or to execute failover? What is the replication strategy between regions? Akka's memory is active-active replicated across regions with data filters and disaster recovery. Coordinate security (access of systems, and filtering of data) with corporate key value for secrets, AD/IDP provider that controls all inbound / outbound service access. Wire up code repositories to CI/CD. What will be your AI-assisted DevEx. (cough, Akka provides AI-assistance that can generate entire Akka systems through prompts). Evaluation must be integrated inline to agentic clusters (so that agents can make performance, accuracy or cost control flow decisions) but also integrated to 3rd party observability and evaluation vendors. Writing agents is a lot of fun. What's more fun is watching scale, safely in production. System architecture (and Akka and Deloitte) is how you do that.