Articles tagged “production-agents”
19 articles
Your Agent Is Only as Good as Its Harness
Upgrading the model rarely fixes a failing agent. The harness, the code that manages tools, memory, and context, is where agent quality actually lives.
How to manage AI agent configs across environments
Your AI agent's system prompt, model settings, and tool definitions are config — and they deserve the same version control, review, and promotion workflow as your code. Here's how to build it.
Why 40% of multi-agent systems fail in production
Nearly half of multi-agent CX pilots fail within six months of production — not because the AI is wrong, but because teams don't understand how multi-agent systems break. Here are the five failure modes and how to diagnose each.
The Six Agent Observability Platforms That Matter in 2026
Most observability platforms were built for LLM apps, not agentic CX systems. Here's how the six that matter in 2026 hold up against the criteria that count.
Most of your agent traffic doesn't need your best model
Routing 100% of agent traffic to your most capable model is costing you 6-10x what it should. Here's how to build a cascade router that handles simple tasks cheaply and escalates to stronger models only when the task demands it.
When your LLM provider goes down, your agent shouldn't
LLM providers go down. Anthropic's 90-day uptime is 98.95% -- that's 44 hours of potential outage per year. Here's how to build provider failover into production AI agents so a cloud incident doesn't become a customer experience incident.
Why most AI agents in production are flying blind
57% of organizations have AI agents in production. Only a third are satisfied with their observability. Here's what's wrong with single-call LLM logging and how to build a monitoring stack that actually works.
Context engineering for reliable CX agents
Context engineering is the discipline of deciding what information your AI agent sees, when it sees it, and how it's formatted. Here's how to apply it to production CX systems.
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.
AI agents blew their 2026 budget by April. Here's the fix.
One company burned through its entire 2026 AI budget by April. Here's why agent costs run away and how to stop it: per-session token caps, prompt caching for CX, model routing, and circuit breakers.
Your AI agents need their own identity
Most CX agents share a single API key with every other service on your stack. Here's how to implement proper agent identity: OAuth 2.0, scope minimization, JIT provisioning, and instant kill switches.
Design agent tools that won't double-charge on retry
Agents retry when tools fail. Without idempotency, retries create duplicate records, double charges, and corrupted state. Here's the engineering pattern that makes every mutating tool safe to retry.
How to Build Agent Interrupt and Approval Checkpoints
How to pause an AI agent before high-stakes actions, persist full state through the approval window, and resume cleanly. Covers interrupt gates, approval queues, checkpointing, and EU AI Act compliance for production CX agents.
How to Build Idempotent Tool Calls for AI Agents
Naive retry logic charges customers twice, sends duplicate emails, and fires double webhooks. Here's how to build idempotent tool calls for AI agents with idempotency keys, deduplication, and safe retries.
Your Agent's Context Window Is RAM, Not Storage
Most agent failures trace back to one mistake: treating the context window like a database. Here's the RAM model that fixes attention dilution, latency spikes, and ballooning costs.
MCP Without a Gateway Is a Production Liability
Raw MCP is great for prototyping. But production agents need audit trails, per-user identity, tool-level RBAC, and rate limiting, none of which the spec provides. Here's the gateway pattern that fills the gap.
How to Build Production-Safe Credentials for AI Agents
After PocketOS lost its production database to a nine-second AI agent error, here's the credential model that would have stopped it: vaults, scoping, RBAC, and boundary tests.
The Agent Development Lifecycle: Ship, Observe, Improve
Shipping an AI agent is easy. Keeping it reliable after launch is where most teams struggle. The ADLC gives you a structured approach: Intent, Build, Evaluate, Deploy, Observe -- and then do it again.
How MCP Tool Descriptions Break Your Agent
New research shows 97% of MCP tool descriptions have quality issues that hurt agent accuracy. Here's what the smells look like, why they matter, and how to fix them.
Learn Agentic AI
Weekly. Patterns for shipping agents that work. MCP, scorecards, regression tests, prompts, model comparisons.
