Build a Cloudflare Workers + Durable Objects Voice Agent
Per-call state with Durable Objects, voice transport with Cloudflare Realtime, and tools via the Agents SDK. Real Workers code that scales globally.
13 min read
Agentic AI & LLMs
Agentic AI & LLMs archive page 310 of 631
Agentic AI & LLMs
Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
Latest articles
Chaos Engineering for AI Voice: Gremlin Patterns and Agent-Specific Failure Injection
Pod kills don't break voice agents — they break tool retries and barge-in. Real chaos for voice means corrupting tool results and cutting LLM streams mid-response. Here's how to do it safely.
11 min read
Kamailio Dispatcher for AI Voice Scaling in 2026: Round-Robin Is Not Enough
Kamailio 6.0's dispatcher module is how you horizontally scale AI voice bridges behind a SIP front-end. Round-robin is the easy answer; call-load and weight-based dispatching is the right one.
10 min read
BigQuery + Pub/Sub for AI Call Analytics: Continuous Queries and ADK Agents in 2026
BigQuery continuous queries + Pub/Sub direct subscriptions + Vertex AI ADK agents form a fully managed pipeline. We show how to triage calls in real time, with autonomous investigation when sentiment crashes.
11 min read
Agent Behavioral Diff Testing: Surviving Model Swaps in 2026
Anthropic shipped a diff tool for AI in March 2026 to find behavioral differences across model versions. Here is how we use the same idea to swap models without breaking customers.
11 min read
Recursive Sub-Agents: When Agents Spawn Their Own Children (2026)
Inline tool, spawn-wait, parallel, quality-gated — the four sub-agent patterns from 2026 production systems. We cover RecursiveMAS's 8.3% accuracy lift, OpenPlanter's IMPLEMENT-THEN-VERIFY judge, and CallSphere's nested OneRoof shape.
11 min read
Postgres + Citus for Sharding: Scale AI Workloads Past 10TB (2026)
Citus turns Postgres into a distributed database via row-based or schema-based sharding. Pick the right model for AI workloads, distribute pgvector tables, and watch query plans actually parallelize.
12 min read
WebGPU for AI Inference in the Browser: Sub-3B Voice Models Run at 3-10x Speedup (2026)
WebGPU shipped Baseline in November 2025. Transformers.js v4 delivers 3-10x speedups on Whisper, Silero VAD, and Kokoro TTS — voice agents now run end-to-end client-side with no server inference.
11 min read
The Future of Claude Clinical Abstraction Agents
Where Claude clinical abstraction is heading — longitudinal reasoning, multi-agent registries, graduated autonomy — and how to prepare your team today.
8 min read