Articles tagged “cx-agents”
24 articles
Your agent doesn't need more memory. It needs a graph.
Session memory forgets. RAG retrieves but doesn't reason. Context graphs give your CX agent a persistent, queryable model of every customer, issue, and relationship it's ever encountered -- at a fraction of the token cost.
MCP now uses round-trips, not streams, for user input
The July 28 spec deprecated elicitation and sampling. Multi Round-Trip Requests (SEP-2322) replace both with a stateless pattern: the server returns InputRequiredResult, the client collects input, the client re-submits. Here's how to migrate.
How LLM Routing Cuts Agent Costs 40-85% in Production
Most CX agents send every request to their priciest model. Routing simple queries to a cheap model cuts costs 40-85%, at 90-95% of single-model quality.
The Five Eyes Published an Unusually Specific AI Agent Advisory
The Five Eyes published the first joint guidance on agentic AI security. For CX builders it's specific: tool permissions, schema injection, and human oversight.
Testing AI agent handoffs before they break in production
Multi-agent CX systems fail at the seam between agents. Here's how to build handoff tests that catch context loss, duplicate actions, and loop failures before your customers feel them.
The trace-to-dataset loop: turning live conversations into eval cases
Your best eval cases are already in your production traces. Here's how to automatically curate the interesting ones into a test suite that gets better every week without manual effort.
How to rescue a stuck CX agent conversation
Conversations get stuck in four predictable patterns: clarification spirals, topic drift, assumption deadlocks, and initiative mismatches. Here's how to detect each one mid-flight and apply the repair move that actually works.
A2A and MCP: the agent protocol stack explained
MCP connects agents to tools. A2A connects agents to other agents. Together they form the full protocol stack for multi-agent CX systems. Here's how they work and why you need both.
When vector search fails: GraphRAG for complex CX agent queries
Flat vector search breaks on multi-hop CX queries like 'what discount applies to premium customers in California who signed up before 2024?' GraphRAG uses a knowledge graph to answer these correctly.
MCP's 2026 spec changes what your tools can do
The MCP spec RC is out with Extensions, Tasks, MCP Apps, and OAuth hardening. Here's what changes for CX agent builders before the July 28 final.
On-device AI agents for CX: what edge deployment unlocks
On-device AI agents are no longer a research project. Here's what running your CX agent on local hardware actually unlocks in 2026, and what it doesn't.
The OWASP Top 10 for agentic AI: a CX builder's field guide
OWASP published its first Top 10 for Agentic Applications in 2026. Here's what every team building CX agents needs to know, including the three risks that traditional AppSec was never designed to catch.
Extended thinking for CX agents: when slow beats fast
Reasoning models (Claude Opus 4.7, o3, Qwen 3) let your agent think through complex problems before acting. For some CX tasks that's a major improvement. For others, it's a 4-second pause before telling someone their order ships Thursday.
Your CX agent needs an autonomy level before it goes live
Not all CX agents should be equally autonomous. Here's a practical L0-to-L4 framework for deciding how much independence to give your agent for each action type, and what eval thresholds to hit before promoting.
The delegation gap: what you can hand off to your agent
Anthropic's 2026 report found teams use AI in 60% of work but fully delegate only 0-20%. The same gap hits CX teams. Here's a framework for closing it.
Enforcing runtime policies on production CX agents
Guardrails filter what your agent says. Runtime policies constrain what it's allowed to do. Here's why that distinction matters and how to build an enforcement layer your LLM can't override.
Five things your CX agent needs that its framework won't provide
LLM frameworks handle conversations. They don't handle memory, tool reliability, pre-production testing, or observability. Here's what every production CX agent actually needs.
Context engineering: why your agent gets dumber mid-conversation
82% of AI teams say prompt engineering alone no longer works for production. Context engineering decides what your agent sees, when, and what gets removed as conversations grow.
Agent containment: what Microsoft's MXC means for CX
Microsoft unveiled MXC at Build 2026: OS-level sandboxes for AI agents with policy-driven containment and Entra-backed identity. Here's what it means for teams building CX agents.
The OpenAI Assistants API shuts down August 26
The OpenAI Assistants API sunsets on August 26, 2026. If you built a CX chatbot or support agent on it, here's what's actually changing, your migration options, and why this is the right time to build the architecture you should have had from the start.
Why your eval scores don't predict real conversation quality
Your agent passes 91% of your eval suite but customers keep escalating. The problem is almost always the same: you're measuring single-turn quality, and customers experience multi-turn conversations. Here's how to build evaluation that reflects what actually happens.
When voice becomes chat: carrying context across channels
When a customer switches from a call to chat, your AI agent loses everything it learned on the phone -- unless you package and transfer context deliberately. Here's how to build channel context handoffs that actually work.
CX agent personas: why brand voice is an infrastructure problem
Generic AI agents erode the brand identity you spent years building. Here's the system prompt architecture that gives your CX agent a consistent, testable, on-brand voice -- across every session and channel.
How to Build the Context Package for AI-to-Human Handoffs
AI agents escalate every day, and most send the human in blind. Here's how to build the context package that makes handoffs invisible to customers.
Learn Agentic AI
Weekly. Patterns for shipping agents that work. MCP, scorecards, regression tests, prompts, model comparisons.
