Systems | Development | Analytics | API | Testing

When building AI experiences, choosing between WebSockets and HTTP isn't always straightforward. Which protocol is better for streaming LLM responses? How do you maintain continuity when users switch devices mid-conversation? Should you use both? The answer depends on the type of AI experience you're building. Modern AI applications often require both protocols, each serving different purposes. The key question is: how do you decide which communication pattern fits each scenario in your AI stack?

Editing or removing a message after it’s been published sounds simple. In realtime systems, it usually isn’t. Once a message has been delivered to multiple clients, cached locally, and written into history, changing it safely becomes a coordination problem. Clients need to agree on what’s current. History needs to stay consistent. Reconnects and refreshes can’t bring back stale content. That’s why many systems treat messages as immutable by default.

Streaming tokens is easy. Resuming cleanly is not. A user refreshes mid-response, another client joins late, a mobile connection drops for 10 seconds, and suddenly your “one answer” is 600 tiny messages that your UI has to stitch back together. Message history turns into fragments. You start building a side store just to reconstruct “the response so far”. This is not a model problem. It’s a delivery problem That’s why we developed message appends for Ably AI Transport.

Complex user tasks often need multiple AI agents working together, not just a single assistant. That’s what agent collaboration enables. Each agent has its own specialism - planning, fetching, checking, summarising - and they work in tandem to get the job done. The experience feels intelligent and joined-up, not monolithic or linear. But making that work means more than prompt chaining or orchestration logic.

When you're building agentic AI applications with multiple agents working together, the infrastructure challenges show up fast. Agents need to coordinate, users need visibility into what's happening, and the whole system needs to stay responsive even as tasks branch out across specialised workers. We built a multi-agent travel planning system to understand these problems better. What we learned applies well beyond holiday booking.

Start typing, change your mind, redirect the AI mid-response. It just works. That is the promise of realtime steering. Users expect to interrupt an answer, correct its direction, or inject new instructions on the fly without losing context or restarting the session. It feels simple, but delivering it requires low-latency control signals, reliable cancellation, and shared conversational state that survives disconnects and device switches.

Today we’re launching Ably AI Transport: a drop-in realtime delivery and session layer that sits between agents and devices, so AI experiences stay continuous across refreshes, reconnects, and device switches - without an architecture rewrite.

Most companies talk about being “AI-first.” At Ably, we decided to actually become one. We build realtime infrastructure for AI applications. To do that credibly, we need to live and breathe AI ourselves – not just in our product, but in how we work every day. Two years ago, we began a company-wide push for AI adoption.

When you’re building realtime systems, blind spots slow you down. The new dashboard gives developers self-serve visibility into everything happening inside their apps, from high-level usage to individual connections, channels and messages. No setup. No external tools. Just open your browser and observe your data in motion.

We're entering a new era of anticipatory customer experience – one that's not just reactive, not just responsive, but truly predictive. In this new model, systems don't wait for friction to appear; they recognise signals early and step in before the user ever feels a slowdown or moment of uncertainty. The bar has shifted: customers now expect brands to predict their needs and act before friction even surfaces.