📰 Dev.to · Austin Vance

The agent harness is becoming the real lock-in layer for enterprise AI because routing, traces, evals, memory, policy, and credentials live above the

Salesforce MCP moves CRM integration into the agent runtime, where identity, approvals, retries, idempotency, and traces decide whether CRM side effec

AI agent governance belongs in the runtime path, where identity, policy, traces, and approvals meet before production side effects.

AI agent accuracy should be managed as observable production evidence: traces, evals, side-effect receipts, and release gates, not one average score.

Agent rubrics move evaluation from offline scoring into runtime QA with verifier loops, criteria ownership, and observable verdicts.

At LangChain Interrupt, the agent conversation shifted from models to runtime. LangSmith Engine, SmithDB, Deep Agents v0.6, Managed Deep Agents, MCP,

Agentic payments move spending authority into the runtime, where policy, approvals, receipts, and revocation sit before a wallet signs.

Agent UI is runtime infrastructure: event streams give products typed handles for tools, state, approvals, subagents, errors, and observability.

Agent monitoring has become production infrastructure: traces must carry state, side effects, cost, ownership, checkpoints, rollback context, and SRE

Recurring AI agent workflow failures should become named issues with linked traces, owners, regression evals, and release evidence.

Agent observability breaks when traces stop at the MCP tool boundary. Pass W3C trace context through MCP to connect planner, tool, and service spans.

Agentic AI architecture needs model routing, telemetry, and policy so production agents can send each workload to the right model instead of one defau

MCP servers should not eagerly load every tool schema into an agent's context window. Lazy-load tools by intent, then govern and audit execution.

Cut agent response times in half with parallel sub-agents in LangGraph. plus the failure modes that'll bite you in production with evals to prevent fu

Implement human-in-the-loop patterns in LangGraph for enterprise AI agents. Build approval workflows, escalation paths, and audit trails.

Learn how to stream LangGraph agents in production with node updates, progress events, and token streaming using FastAPI and SSE.

Learn how to use LangSmith Insights to analyze production agent behavior, detect errors, and prioritize improvements based on real user interactions.

Learn how to build evaluation pipelines for LangGraph agents using LangSmith. Implement datasets, LLM evals, and regression detection to safely ship a

A step-by-step walkthrough of debugging a RAG application built with LangChain LCEL. Learn practical techniques for tracing conversational memory bugs

An honest review of OpenAI Assistants with Retrieval for RAG applications. Learn about its ease of use, accuracy benchmarks, beta limitations, and tip

How returning from maternity leave gave one developer a fresh appreciation for pair programming and its benefits for ramping back up.

A conference talk exploring parallels between Queer Eye's consulting approach and software consulting, focusing on empathy, expertise, and client empo

How hackathons drive innovation, team building, and technical discovery in organizations, with practical tips for running successful events.

Debugging an echo cancellation bug in Chromium when using the Web Audio API for spatial audio processing on conferencing streams.