# LangChain Blog

Thought leadership, news, tutorials, and case studies on agent engineering.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Why agent governance starts with observability

DevFeed: [Why agent governance starts with observability](<https://devfeed.tech/articles/why-agent-governance-starts-with-observability-146227.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/agent-governance-observability>)

Author: LangChain Accounts

Published: 2026-11-20T00:57:43Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [agent-security](<https://devfeed.tech/tags/agent-security.md>), [ai](<https://devfeed.tech/tags/ai.md>), [governance](<https://devfeed.tech/tags/governance.md>), [observability](<https://devfeed.tech/tags/observability.md>)

### AI overview

Agent governance depends on observability: centralized traces and run trajectories let teams see which agents are operating, inspect their actions, and check whether guardrails hold. The excerpt distinguishes preventative controls--runtime limits and policies, plus pre-deployment evaluations and red-teaming--from detective measures such as online evaluations, dashboards, alerts, drift checks, and human review. Traces support both: they help explain failures before release and audit production behavior, including alternate paths that may bypass intended restrictions. Production findings can feed back into tighter guardrails or regression tests. The article also names LangSmith Insights reports for clustering trace patterns and LangSmith Engine for analyzing recurring failures and testing proposed fixes. These are presented as vendor capabilities; the excerpt does not establish comparative performance against other tools.

### Source excerpt

A strong AI agent governance strategy

## Your coding agent bill doubled. Here's how to fix it.

DevFeed: [Your coding agent bill doubled. Here's how to fix it.](<https://devfeed.tech/articles/your-coding-agent-bill-doubled-here-s-how-to-fix-it-142925.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/fix-your-coding-agent-bill>)

Author: LangChain Accounts

Published: 2026-11-18T19:33:12Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [codex](<https://devfeed.tech/topics/codex.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [claude-code](<https://devfeed.tech/tags/claude-code.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cost-management](<https://devfeed.tech/tags/cost-management.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [engine](<https://devfeed.tech/tags/engine.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [trace](<https://devfeed.tech/tags/trace.md>)

### AI overview

Coding agent costs become hard to assess when teams use multiple tools that record activity in incompatible formats. The article proposes a cycle of shared visibility, cost comparison, optimization, and spending controls. LangSmith normalizes traces from Claude Code, Codex, Cursor, GitHub Copilot Chat, Pi, and OpenCode, including model usage, tool calls, and subagent activity, so teams can query and compare sessions in one place. Engine analyzes sessions for waste such as repeated context retrieval and suggests changes; LangSmith's LLM Gateway provides user, team, and organization cost caps, with open source model routing described as forthcoming. The article recommends starting with observability and adding optimization and governance as needed. It says teams standardized on one tool with an adequate native dashboard may not need another layer until they adopt a second agent.

### Source excerpt

Learn why coding agent bills spiral out of control -- and how to trace, compare, and govern spend across Claude Code, Cursor, Copilot, and more in one place.

## Catch production failures early with LangSmith Alerts

DevFeed: [Catch production failures early with LangSmith Alerts](<https://devfeed.tech/articles/catch-production-failures-early-with-langsmith-alerts-142926.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/langsmith-alerts>)

Author: LangChain Accounts

Published: 2026-11-18T19:33:12Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Prometheus alert rules](<https://devfeed.tech/topics/prometheus-alert-rules.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-apps](<https://devfeed.tech/tags/agentic-apps.md>), [agents](<https://devfeed.tech/tags/agents.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [alert](<https://devfeed.tech/tags/alert.md>), [alerting](<https://devfeed.tech/tags/alerting.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [apis](<https://devfeed.tech/tags/apis.md>), [app](<https://devfeed.tech/tags/app.md>), [applications](<https://devfeed.tech/tags/applications.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [docs](<https://devfeed.tech/tags/docs.md>), [error](<https://devfeed.tech/tags/error.md>), [failures](<https://devfeed.tech/tags/failures.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [latency](<https://devfeed.tech/tags/latency.md>), [notifications](<https://devfeed.tech/tags/notifications.md>), [production](<https://devfeed.tech/tags/production.md>), [real-time](<https://devfeed.tech/tags/real-time.md>)

### AI overview

LangSmith Alerts can notify teams about production LLM application issues using error count or rate, average latency, and average feedback score. Alerts can be narrowed with filters such as model, tool call, or run type, then tuned with 5- or 15-minute aggregation windows and thresholds. Notifications can go through PagerDuty or a custom webhook, such as one connected to Slack. The article frames alerts as a way to catch dependency outages, rate limits, latency increases, and output-quality regressions; setup requires production traces already being sent to LangSmith. Run-count and token-usage alerts, relative-change alerts, and custom time windows are listed as future additions.

### Source excerpt

Set up real-time notifications on error rates, run latency & feedback scores to spot failures before your customers do.

## Announcing Data Annotation Queues

DevFeed: [Announcing Data Annotation Queues](<https://devfeed.tech/articles/announcing-data-annotation-queues-142924.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/announcing-data-annotation-queue>)

Author: LangChain Accounts

Published: 2026-11-18T19:33:12Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [human feedback](<https://devfeed.tech/topics/human-feedback.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [annotation](<https://devfeed.tech/tags/annotation.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [app-performance](<https://devfeed.tech/tags/app-performance.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [beta](<https://devfeed.tech/tags/beta.md>), [classification](<https://devfeed.tech/tags/classification.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [llm](<https://devfeed.tech/tags/llm.md>), [logs](<https://devfeed.tech/tags/logs.md>), [performance](<https://devfeed.tech/tags/performance.md>), [production](<https://devfeed.tech/tags/production.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [queues](<https://devfeed.tech/tags/queues.md>), [review](<https://devfeed.tech/tags/review.md>)

### AI overview

LangSmith's Data Annotation Queues let teams select filtered logs, review each datapoint, annotate it, or edit it before explicitly adding it to a dataset. Reviewers can move a datapoint to the end of the queue to revisit later or mark it done. The feature addresses the need for application-specific examples to inspect performance, build test datasets, and support techniques such as few-shot prompting or fine-tuning. The text also highlights langfree, an open-source package for extracting, transforming, and curating ChatOpenAI runs from LangSmith traces for fine-tuning and evaluation; it offers a customizable alternative for annotation and dataset curation workflows.

### Source excerpt

Review logs, annotate data, and build datasets with LangSmith's Data Annotation Queues. Improve LLM app performance from prototype to production.

## LangSmith for Coding Agents: Now track spend by outcome

DevFeed: [LangSmith for Coding Agents: Now track spend by outcome](<https://devfeed.tech/articles/langsmith-for-coding-agents-now-track-spend-by-outcome-140986.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/langsmith-coding-agents-roi>)

Author: LangChain Accounts

Published: 2026-11-18T16:27:01Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cloud-coding](<https://devfeed.tech/tags/cloud-coding.md>), [coaching](<https://devfeed.tech/tags/coaching.md>), [code](<https://devfeed.tech/tags/code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cost](<https://devfeed.tech/tags/cost.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [offers](<https://devfeed.tech/tags/offers.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [reporting](<https://devfeed.tech/tags/reporting.md>)

### AI overview

LangSmith for Coding Agents links traced agent spend to GitHub pull requests or GitLab merge requests, including cases where one thread contributes to several PRs or a PR requires several threads. Its dashboard aggregates costs across supported agents--Claude Code, OpenAI Codex, Cursor, GitHub Copilot in VS Code, and Deep Agents--and breaks them down by PR status, work type, model, skills, and thread length. Metrics link to the underlying sessions for investigation; work without a PR is tracked as unattributed, since reviews and investigations may still be useful. Teams can compare cost and outcomes over time, including before and after model changes. The service is in public beta on LangSmith Cloud, and coding-agent traces count toward regular tracing usage. Setup requires installing an agent plugin, connecting GitHub, and opening the overview page.

### Source excerpt

LangSmith now offers reporting built for coding agents, along with new capabilities that tie their spend to the pull requests they produce.

## How to Choose the Right Sandbox for AI Agents

DevFeed: [How to Choose the Right Sandbox for AI Agents](<https://devfeed.tech/articles/how-to-choose-the-right-sandbox-for-ai-agents-139468.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/how-to-choose-the-right-sandbox-for-your-agent>)

Author: LangChain Accounts

Published: 2026-11-18T00:46:14Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [AI Sandbox](<https://devfeed.tech/topics/ai-sandbox.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [filesystem](<https://devfeed.tech/tags/filesystem.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [isolation](<https://devfeed.tech/tags/isolation.md>), [limits](<https://devfeed.tech/tags/limits.md>), [network](<https://devfeed.tech/tags/network.md>), [resource](<https://devfeed.tech/tags/resource.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>)

### AI overview

AI agent sandboxes reduce the risk of prompt-injected code by limiting the data and systems it can reach, though they do not eliminate the risk. The guide recommends an isolated filesystem, configurable network access, compute and memory limits, control over sandbox reuse, and kernel-level isolation; it cautions that Kubernetes Agent Sandbox needs a cluster with kernel isolation, which most clusters do not enforce. Two connection patterns are described: running the agent inside the sandbox mirrors local development but requires rebuilding and redeploying for agent updates; calling a sandbox as a tool keeps API keys and agent state outside execution and allows independent agent updates, at the cost of network latency. LangSmith Sandboxes are described as dedicated microVMs with separate filesystems, configurable lifecycle and network access, and an authorization proxy that adds credentials to outbound traffic after it leaves the sandbox.

### Source excerpt

Learn how to choose a secure sandbox for AI agents, with guidance on filesystem isolation, network access, resource limits, and microVMs.

## Protect sensitive data in your traces: new controls in LangSmith

DevFeed: [Protect sensitive data in your traces: new controls in LangSmith](<https://devfeed.tech/articles/protect-sensitive-data-in-your-traces-new-controls-in-langsmith-139469.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/protect-sensitive-data-in-your-traces-new-controls-in-langsmith>)

Author: LangChain Accounts

Published: 2026-11-17T21:31:36Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [sensitive data](<https://devfeed.tech/topics/sensitive-data.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Data Management](<https://devfeed.tech/topics/data-management.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [about](<https://devfeed.tech/tags/about.md>), [access-control](<https://devfeed.tech/tags/access-control.md>), [access-controls](<https://devfeed.tech/tags/access-controls.md>), [added](<https://devfeed.tech/tags/added.md>), [admin](<https://devfeed.tech/tags/admin.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [all](<https://devfeed.tech/tags/all.md>), [controls](<https://devfeed.tech/tags/controls.md>), [data](<https://devfeed.tech/tags/data.md>), [help](<https://devfeed.tech/tags/help.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [manage](<https://devfeed.tech/tags/manage.md>), [more](<https://devfeed.tech/tags/more.md>), [sensitive-data](<https://devfeed.tech/tags/sensitive-data.md>), [teams](<https://devfeed.tech/tags/teams.md>), [trace](<https://devfeed.tech/tags/trace.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

LangSmith Enterprise adds three controls for managing access to complete production traces: admins can hide trace inputs and outputs while leaving run trees, performance statistics, and metadata visible; assign workspace-specific permissions to user groups, layered on existing RBAC and ABAC; and define trace-level ABAC policies from root run metadata. Layered together, these let teams grant, for example, support staff access to relevant customers' inputs and outputs while engineers can inspect run and performance data across traces with sensitive content hidden. Policies can be adjusted as team responsibilities change. The text says full-fidelity traces can be stored without redacted or duplicate copies; the controls determine what each user can view. These features are available on LangSmith Enterprise plans.

### Source excerpt

New controls are now in LangSmith to help teams manage access to sensitive trace data. Learn more.

## From tasks to goals

DevFeed: [From tasks to goals](<https://devfeed.tech/articles/from-tasks-to-goals-137784.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/from-tasks-to-goals>)

Author: LangChain Accounts

Published: 2026-11-16T23:53:29Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Human-AI evaluation](<https://devfeed.tech/topics/human-ai-evaluation.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [To-Do](<https://devfeed.tech/topics/todo.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [act](<https://devfeed.tech/tags/act.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [background](<https://devfeed.tech/tags/background.md>), [based](<https://devfeed.tech/tags/based.md>), [best](<https://devfeed.tech/tags/best.md>), [better](<https://devfeed.tech/tags/better.md>), [blog](<https://devfeed.tech/tags/blog.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [browser](<https://devfeed.tech/tags/browser.md>), [bug](<https://devfeed.tech/tags/bug.md>), [but](<https://devfeed.tech/tags/but.md>), [goals](<https://devfeed.tech/tags/goals.md>), [more](<https://devfeed.tech/tags/more.md>), [moving](<https://devfeed.tech/tags/moving.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Goal-focused agents take on ongoing responsibility: they break a user's desired outcome into tasks, choose when to act, and update their plan. This shifts the user's role from specifying each action to setting direction, boundaries, and feedback. The excerpt identifies practical needs: a visible task list and varied task selection; controls over which tools agents can call, since goal-level requests make future tool use less predictable; a way for background agents to ask people for clarification; progress measures paired with human feedback to avoid blindly optimizing metrics; wake-up triggers such as heartbeats, recurring or one-off cron jobs, and event streams, plus ways to pause or stop; and memory that carries decisions and feedback across runs. The article cautions that ongoing responsibility does not mean acting constantly: sometimes doing nothing is appropriate.

### Source excerpt

LangChain CEO and Co-founder Harrison Chase shares how we're moving from task-specific agents to goal-focused agents. Learn more.

## Why we rebuilt LangSmith around the agent

DevFeed: [Why we rebuilt LangSmith around the agent](<https://devfeed.tech/articles/why-we-rebuilt-langsmith-around-the-agent-137785.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/we-rebuilt-langsmith-around-the-agent>)

Author: LangChain Accounts

Published: 2026-11-16T18:37:11Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-fleet](<https://devfeed.tech/tags/agent-fleet.md>), [agent-sprawl](<https://devfeed.tech/tags/agent-sprawl.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-leaders](<https://devfeed.tech/tags/ai-leaders.md>), [ai-platform](<https://devfeed.tech/tags/ai-platform.md>), [ai-platform-teams](<https://devfeed.tech/tags/ai-platform-teams.md>), [annotation](<https://devfeed.tech/tags/annotation.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [audio](<https://devfeed.tech/tags/audio.md>), [audit](<https://devfeed.tech/tags/audit.md>), [build](<https://devfeed.tech/tags/build.md>), [cost](<https://devfeed.tech/tags/cost.md>), [costs](<https://devfeed.tech/tags/costs.md>), [framework](<https://devfeed.tech/tags/framework.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [run](<https://devfeed.tech/tags/run.md>), [runtime](<https://devfeed.tech/tags/runtime.md>)

### AI overview

LangSmith reorganizes agent development and governance around one record per agent, linking its owner, immutable ID, type, environments, traces, evaluations, deployments, and issues. Teams can build with LangSmith Studio, open-source harnesses, or other frameworks; run agents on Agent Server or existing runtimes; and use tracing, evaluation, datasets, annotation, and Engine for agents that send traces to LangSmith. The registry and LLM Gateway provide organization-level visibility and controls, including for connected agents on platforms supporting OTLP. Agent types tailor dashboards, evaluation criteria, and data connections: general-purpose and coding types are available, with coding agents able to connect GitHub to track outcomes. The platform is composable, though validation across Agent Server previews is an example for teams building and running there. Org-level dashboards, more agent types, and identity-provider registration are described as forthcoming.

### Source excerpt

We reorganized LangSmith around a single agent record. Build, run, improve, and govern every agent from one place, on any framework or runtime.

## Goal Engineering

DevFeed: [Goal Engineering](<https://devfeed.tech/articles/goal-engineering-134141.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/goal-engineering>)

Author: LangChain Accounts

Published: 2026-11-14T16:00:01Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [design](<https://devfeed.tech/tags/design.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [goal-oriented-agents](<https://devfeed.tech/tags/goal-oriented-agents.md>), [goals](<https://devfeed.tech/tags/goals.md>), [human-review](<https://devfeed.tech/tags/human-review.md>)

### AI overview

Goal-oriented agents learn more effectively when their scope makes human review and feedback easy. The article argues that access to documents and APIs can supply explicit context, while subjective knowledge--such as a salesperson's preferred outreach style or deal strategy--must be learned from feedback. In Actively AI's first design, one agent per prospective account handled varied tasks over time. This caused review context switching and made it awkward to share lessons across accounts. The revised design uses "motions," each covering a recurring job such as outbounding or early-stage deal progression across multiple accounts. Sales reps can review similar tasks together, and feedback from one can transfer to others. Background agents gather each account's more objective, documented context, which motions draw on as needed. The broader recommendation is to align agent goals with work humans can review and teach, supported by an intuitive review experience; the article presents this as a way to improve learning and enable greater autonomy over time.

### Source excerpt

The future of agents is them taking on open ended goals and driving towards completion of those goals. Learn more.

## LangChain Raises $300M Series C at $3B Valuation

DevFeed: [LangChain Raises $300M Series C at $3B Valuation](<https://devfeed.tech/articles/langchain-raises-300m-series-c-at-3b-valuation-133502.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/series-c>)

Author: LangChain Accounts

Published: 2026-11-13T16:06:29Z

Content type: news

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [observability](<https://devfeed.tech/topics/observability.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [company](<https://devfeed.tech/tags/company.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [platform](<https://devfeed.tech/tags/platform.md>), [raises](<https://devfeed.tech/tags/raises.md>), [series-c](<https://devfeed.tech/tags/series-c.md>), [valuation](<https://devfeed.tech/tags/valuation.md>)

### AI overview

LangChain says it raised $300 million at a $3 billion valuation in a round led by existing investor CapitalG, with participation from GIC, DFJ Growth, IVP and Sapphire Ventures. It presents LangSmith as a framework-agnostic platform for running, improving and governing agents, organized around runtime, improvement and governance. Described tools cover deployment and execution across cloud or customer environments, observability and evaluation, automated fixes and regression monitoring, trace-based fine-tuning, and centralized controls for model budgets, fallbacks, sensitive data and tool access. The announcement says more than 7,000 organizations use LangSmith and cites customer examples, including Workday reducing agent deployment time from five months to under a day; these are company-reported claims.

### Source excerpt

LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.

## Own Your Intelligence: The Key to Lasting AI Advantage

DevFeed: [Own Your Intelligence: The Key to Lasting AI Advantage](<https://devfeed.tech/articles/own-your-intelligence-the-key-to-lasting-ai-advantage-131301.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/own-your-intelligence>)

Author: LangChain Accounts

Published: 2026-11-12T17:19:15Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [act](<https://devfeed.tech/tags/act.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [ai-stack](<https://devfeed.tech/tags/ai-stack.md>), [ai-startup](<https://devfeed.tech/tags/ai-startup.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [business](<https://devfeed.tech/tags/business.md>), [context](<https://devfeed.tech/tags/context.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [generic](<https://devfeed.tech/tags/generic.md>), [governance](<https://devfeed.tech/tags/governance.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [key](<https://devfeed.tech/tags/key.md>), [learn](<https://devfeed.tech/tags/learn.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

Lasting AI advantage comes from adapting intelligence to a business and improving it with use. The text argues companies can buy generic models and infrastructure while retaining control of the agent system: model choices, orchestration, tools, workflows, context and memory. It also calls for managing operating cost, measuring quality with evaluations, setting data and action boundaries, and keeping traces that show what agents saw and did. Traces and feedback can guide changes to prompts, tools and workflows, with evaluations to catch regressions. The stated aim is a portable learning loop that makes later interactions more useful; the text presents this as a strategic framework, not evidence that every system will improve automatically.

### Source excerpt

Learn why companies must own their agent systems, governance, context, and feedback loops to turn generic AI into lasting business advantage.

## How our GTM Agent builds consistent, high-quality sales artifacts

DevFeed: [How our GTM Agent builds consistent, high-quality sales artifacts](<https://devfeed.tech/articles/how-our-gtm-agent-builds-consistent-high-quality-sales-artifacts-130247.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/gtm-agent-high-quality-sales-artifacts>)

Author: LangChain Accounts

Published: 2026-11-12T03:34:55Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [added](<https://devfeed.tech/tags/added.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [build](<https://devfeed.tech/tags/build.md>), [builds](<https://devfeed.tech/tags/builds.md>), [business](<https://devfeed.tech/tags/business.md>), [business-context](<https://devfeed.tech/tags/business-context.md>), [context](<https://devfeed.tech/tags/context.md>), [deep](<https://devfeed.tech/tags/deep.md>), [gtm](<https://devfeed.tech/tags/gtm.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [learn](<https://devfeed.tech/tags/learn.md>), [quality](<https://devfeed.tech/tags/quality.md>), [sales](<https://devfeed.tech/tags/sales.md>)

### AI overview

LangChain's GTM Agent generates branded sales documents using deal stage rules, Salesforce and Drive data, call transcripts, templates, and brand guidance; the article attributes most of its quality to this business context rather than prompt tuning. Reps request artifacts in Slack or receive suggestions in pre-meeting briefs. The agent checks for missing inputs, fills templates in a sandbox, renders and reviews them, then files the result for human handoff. Skills, a sandbox with Office tools, Slack, scheduled runs, memory, and LangSmith tracing support the workflow; Managed Deep Agents includes these building blocks. A stopping rule for self-review cut a one-pager run from 18 minutes to 7. In the reported period, 47% of deals with a sent artifact advanced to a later stage, versus 16% of matched deals without one; this comparison does not establish causation.

### Source excerpt

Learn how LangChain built GTM Agent on Deep Agents to build high-quality, custom sales artifacts trained on business context.

## How Workday Built an Enterprise-Scale AI Agent Platform with LangGraph and LangSmith

DevFeed: [How Workday Built an Enterprise-Scale AI Agent Platform with LangGraph and LangSmith](<https://devfeed.tech/articles/how-workday-built-an-enterprise-scale-ai-agent-platform-with-langgraph-and-langsmith-126674.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/how-workday-built-an-enterprise-scale-ai-agent-platform-with-langgraph-and-langsmith>)

Author: LangChain Accounts

Published: 2026-11-10T17:18:08Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Langgraph](<https://devfeed.tech/topics/langgraph.md>), [internal developer platform](<https://devfeed.tech/topics/internal-developer-platform.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [internal developer platform automation](<https://devfeed.tech/topics/internal-developer-platform-automation.md>)

Tags: [a2a](<https://devfeed.tech/tags/a2a.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [agent-teams](<https://devfeed.tech/tags/agent-teams.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-platform](<https://devfeed.tech/tags/agentic-platform.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-scale](<https://devfeed.tech/tags/enterprise-scale.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [platform](<https://devfeed.tech/tags/platform.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [workday](<https://devfeed.tech/tags/workday.md>)

### AI overview

Workday built an internal platform for developing and running AI agents on its infrastructure, with LangGraph providing graph-based orchestration and LangSmith supporting tracing, observability, and evaluations. A Python SDK routes LangChain primitives through Workday services, while an Agent System of Record governs which APIs agents may access. The platform was designed to let engineers choose agent workflows while standardizing underlying authentication, security, compliance, and infrastructure. Workday says prototypes that previously took four to five months can now run in staging in under a day with authentication and security requirements in place. The excerpt also reports that LangChain's agent server support meant the platform's agent servers already supported A2A and MCP. These are Workday's reported results and implementation details.

### Source excerpt

See how Workday used LangGraph and LangSmith to build an internal AI agent platform that cut prototype time from months to less than a day and compliance needs.

## How Stripe Built Kai on Deep Agents in 1 Week

DevFeed: [How Stripe Built Kai on Deep Agents in 1 Week](<https://devfeed.tech/articles/how-stripe-built-kai-on-deep-agents-in-1-week-124910.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/how-stripe-built-their-knowledge-ai-platform-on-deep-agents>)

Author: LangChain Accounts

Published: 2026-11-09T22:07:04Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [accelerate](<https://devfeed.tech/tags/accelerate.md>), [accelerated](<https://devfeed.tech/tags/accelerated.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [company](<https://devfeed.tech/tags/company.md>), [deep](<https://devfeed.tech/tags/deep.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [stripe](<https://devfeed.tech/tags/stripe.md>), [users](<https://devfeed.tech/tags/users.md>), [wide](<https://devfeed.tech/tags/wide.md>)

### AI overview

Stripe built Kai, a company-wide assistant for non-engineers, with one engineer in one week using Deep Agents as its agent foundation. Deep Agents supplies the tool-calling loop, middleware, streaming, and state management; Stripe adds its security and internal services, configurable agent setups, and UI. Kai connects to internal data, Slack, and Google Suite, and produces artifacts alongside session chats. A virtual filesystem backed by S3 persists files across turns through sandbox sync-in and sync-out; a separate sandbox runs analytics code and processes files, while summarization manages long sessions and context costs. Skills owned by teams load tools dynamically, but selection is becoming difficult across 500+ MCP tools and 1,000+ skills; the excerpt reports quality degradation beyond 150 skills with the system prompt and describes hybrid prefiltering as planned work. After open preview, users grew from 296 to over 5,000 in roughly four weeks; the excerpt also reports 83% weekly use. Governance, behavioral personalization, and collaboration across sessions remain areas of work.

### Source excerpt

Learn how Stripe built Kai, a company-wide AI agent on LangChain, LangGraph, and Deep Agents, reaching 5,000 users in roughly 4 weeks.

## Iterating Towards LLM Reliability with Evaluation Driven Development

DevFeed: [Iterating Towards LLM Reliability with Evaluation Driven Development](<https://devfeed.tech/articles/iterating-towards-llm-reliability-with-evaluation-driven-development-123893.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/iterating-towards-llm-reliability-with-evaluation-driven-development>)

Author: LangChain Accounts

Published: 2026-11-09T18:31:27Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [code](<https://devfeed.tech/tags/code.md>), [collection](<https://devfeed.tech/tags/collection.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [development](<https://devfeed.tech/tags/development.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [llm](<https://devfeed.tech/tags/llm.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [performance](<https://devfeed.tech/tags/performance.md>), [production](<https://devfeed.tech/tags/production.md>), [products](<https://devfeed.tech/tags/products.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [scale](<https://devfeed.tech/tags/scale.md>)

### AI overview

Dosu uses evaluation-driven development (EDD) to assess changes to its LLM logic, models, and prompts. The team creates initial evaluations, launches behavior, monitors production for failures, adds failure examples to offline evaluation datasets, iterates, and relaunches. As activity grew across thousands of repositories, manual log review became impractical. LangSmith's SDK let Dosu trace functions and LLM calls together, including inputs, rendered prompts, outputs, and metadata; its search helps surface failures through feedback, user sentiment, errors, and response delays. The team reports finding slow responses to very large logs or raw embedding values, among other issues, then adds examples to evaluations and iterates. Their stated requirements included keeping prompts in Git, code-level tracing, data export, and customization. Automatic dataset collection from production traffic is described as ongoing work.

### Source excerpt

Dosu uses evaluation driven development and LangSmith to build reliable LLM products at scale, monitor production performance, and iterate with confidence.

## Promptim: an experimental library for prompt optimization

DevFeed: [Promptim: an experimental library for prompt optimization](<https://devfeed.tech/articles/promptim-an-experimental-library-for-prompt-optimization-123895.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/promptim>)

Author: LangChain Accounts

Published: 2026-11-09T18:30:44Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [prompt](<https://devfeed.tech/topics/prompt.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-performance](<https://devfeed.tech/tags/ai-performance.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [automate](<https://devfeed.tech/tags/automate.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [faster](<https://devfeed.tech/tags/faster.md>), [library](<https://devfeed.tech/tags/library.md>), [models](<https://devfeed.tech/tags/models.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [prompt-engineering](<https://devfeed.tech/tags/prompt-engineering.md>), [prompt-optimization](<https://devfeed.tech/tags/prompt-optimization.md>), [save](<https://devfeed.tech/tags/save.md>), [switch](<https://devfeed.tech/tags/switch.md>), [time](<https://devfeed.tech/tags/time.md>)

### AI overview

Promptim automates optimization of a single prompt using a LangSmith dataset, locally defined evaluators, and an iterative metaprompt loop. It scores an initial prompt on a dev split, uses training examples and their scores to propose revisions, and keeps a revision only when dev metrics improve; train/dev/test splits are optional. Human feedback through LangSmith Annotation Queues is also optional, and the authors recommend human review of the final prompt. Compared with DSPy, Promptim focuses on rewriting one prompt and retaining human oversight, while DSPy targets whole compound AI systems and offers options such as fine-tuning and few-shot prompting. Promptim is described as experimental, and its optimization is not presented as a substitute for human sanity checks.

### Source excerpt

Automate prompt engineering with Promptim's optimization library. Save time, improve AI performance, and switch models faster.

## LangSmith BYOC on AWS is generally available

DevFeed: [LangSmith BYOC on AWS is generally available](<https://devfeed.tech/articles/langsmith-byoc-on-aws-is-generally-available-123894.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/langsmith-byoc-is-now-generally-available-on-aws>)

Author: LangChain Accounts

Published: 2026-11-09T18:30:23Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Amazon VPC](<https://devfeed.tech/topics/amazon-vpc.md>), [Amazon Elastic Kubernetes Service](<https://devfeed.tech/topics/amazon-elastic-kubernetes-service.md>), [Security, Identity, & Compliance](<https://devfeed.tech/topics/security-identity-compliance.md>), [observability](<https://devfeed.tech/topics/observability.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [Amazon CloudWatch Logs](<https://devfeed.tech/topics/amazon-cloudwatch-logs.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bring-your-own-cloud](<https://devfeed.tech/tags/bring-your-own-cloud.md>), [byoc](<https://devfeed.tech/tags/byoc.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [inside](<https://devfeed.tech/tags/inside.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [managed](<https://devfeed.tech/tags/managed.md>), [observability](<https://devfeed.tech/tags/observability.md>), [teams](<https://devfeed.tech/tags/teams.md>), [vpc](<https://devfeed.tech/tags/vpc.md>)

### AI overview

LangSmith BYOC is generally available to Enterprise customers on AWS, placing sensitive LangSmith data and agent workloads in the customer's AWS account and VPC while LangChain operates the deployment. Its data plane includes a private EKS cluster, databases, and storage; a control plane in LangChain's cloud handles authentication, organization settings, billing metadata, and provisioning. The planes communicate through AWS PrivateLink. LangChain manages upgrades, scaling, patching, backups, and monitoring. Customers retain ownership of the AWS environment and data, and the provisioning role is scoped to infrastructure management without specified trace or database read permissions. BYOC is offered across 15 AWS regions in the US, EU, and APAC. Most core observability, evaluation, deployment, sandbox, and gateway capabilities are available; it requires the Enterprise plan and contacting LangChain to get started.

### Source excerpt

LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.

## What Is Eval-Driven Development? How to Improve AI Agents

DevFeed: [What Is Eval-Driven Development? How to Improve AI Agents](<https://devfeed.tech/articles/what-is-eval-driven-development-how-to-improve-ai-agents-123896.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/what-is-eval-driven-development>)

Author: LangChain Accounts

Published: 2026-11-09T16:23:28Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [behaviors](<https://devfeed.tech/tags/behaviors.md>), [build](<https://devfeed.tech/tags/build.md>), [build-ai-agents](<https://devfeed.tech/tags/build-ai-agents.md>), [compare](<https://devfeed.tech/tags/compare.md>), [define](<https://devfeed.tech/tags/define.md>), [development](<https://devfeed.tech/tags/development.md>), [eval](<https://devfeed.tech/tags/eval.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [first](<https://devfeed.tech/tags/first.md>), [good](<https://devfeed.tech/tags/good.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [what-is](<https://devfeed.tech/tags/what-is.md>), [write](<https://devfeed.tech/tags/write.md>)

### AI overview

Eval-driven development (EDD) improves agents through a repeatable measure-and-compare loop: define pass/fail behavior, including what must not change; build an evaluation dataset and evaluator before implementing the feature; run a baseline; then compare each change across examples. Use code checks for deterministic criteria and an LLM judge when scoring is less deterministic. For agents that change an environment, evaluate the resulting state in a clean sandbox with task-specific tests; tool calls and final answers may not reveal enough. Review individual regressions and traces, since average scores can hide broken behavior. Keep held-out examples to check for overfitting. The text recommends running fast checks in CI and slower evaluations nightly or before release, then monitoring sampled production traces, human annotations, scores, cost, and latency to find new cases and add them to the dataset.

### Source excerpt

Eval-driven development helps you build AI agents against a consistent set of metrics. Define good behavior, write the eval first, then compare experiments.

## Agents Are Going Async

DevFeed: [Agents Are Going Async](<https://devfeed.tech/articles/agents-are-going-async-119838.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/agents-are-going-async>)

Author: LangChain Accounts

Published: 2026-11-05T20:03:27Z

Content type: tutorial

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [async](<https://devfeed.tech/topics/async.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [DeepSeek Harness](<https://devfeed.tech/topics/dsh.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>)

Tags: [added](<https://devfeed.tech/tags/added.md>), [addition](<https://devfeed.tech/tags/addition.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agents](<https://devfeed.tech/tags/agents.md>), [also](<https://devfeed.tech/tags/also.md>), [api](<https://devfeed.tech/tags/api.md>), [application](<https://devfeed.tech/tags/application.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [async](<https://devfeed.tech/tags/async.md>), [background](<https://devfeed.tech/tags/background.md>), [deep](<https://devfeed.tech/tags/deep.md>), [let](<https://devfeed.tech/tags/let.md>), [notifications](<https://devfeed.tech/tags/notifications.md>), [responsive](<https://devfeed.tech/tags/responsive.md>), [run](<https://devfeed.tech/tags/run.md>), [subagents](<https://devfeed.tech/tags/subagents.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [work](<https://devfeed.tech/tags/work.md>), [workers](<https://devfeed.tech/tags/workers.md>)

### AI overview

Async subagents let an orchestrator stay available while long-running work proceeds in the background. In Deep Agents, `start_async_task` returns immediately; the orchestrator can check, update, cancel, or list tasks, and workers report results when they finish. Follow-ups either interrupt and restart a task (the default) or enqueue instructions for after it finishes. Notifications behave differently depending on whether the orchestrator is busy, idle, or awaiting approval; approval requests remain on the subagent's thread, and Managed Deep Agents on Slack posts them to the original thread. Async subagents are available in Deep Agents for Python and JavaScript and Managed Deep Agents. Task notifications are in beta, so the API may change.

### Source excerpt

Async subagents let an agent stay responsive while background workers run long tasks. How the orchestrator, notifications and approvals work in Deep Agents.

## LangSmith BYOC is now available on AWS, Azure, and Google Cloud

DevFeed: [LangSmith BYOC is now available on AWS, Azure, and Google Cloud](<https://devfeed.tech/articles/langsmith-byoc-is-now-available-on-aws-azure-and-google-cloud-116379.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/langsmith-byoc-aws-gc-azure>)

Author: LangChain Accounts

Published: 2026-11-04T02:56:29Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Cloud](<https://devfeed.tech/topics/cloud.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Azure](<https://devfeed.tech/topics/azure.md>), [Google Cloud Platform (GCP)](<https://devfeed.tech/topics/google-cloud.md>), [Amazon VPC](<https://devfeed.tech/topics/amazon-vpc.md>), [Cloud Networking](<https://devfeed.tech/topics/cloud-networking.md>), [Redpanda BYOC](<https://devfeed.tech/topics/redpanda-byoc.md>), [Azure Kubernetes Service](<https://devfeed.tech/topics/azure-kubernetes-service.md>)

Tags: [aws](<https://devfeed.tech/tags/aws.md>), [azure](<https://devfeed.tech/tags/azure.md>), [byoc](<https://devfeed.tech/tags/byoc.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [google-cloud](<https://devfeed.tech/tags/google-cloud.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>)

### AI overview

LangSmith BYOC keeps sensitive data in customer-owned cloud accounts while LangChain operates the data plane; the control plane retains authentication, organization and workspace configuration, billing metadata, hashed API keys, and static UI assets. AWS is generally available, while Azure and Google Cloud are in beta. AWS deployments use an existing VPC and customer-selected database subnets; Azure uses a dedicated virtual network and private AKS API endpoint; Google Cloud supports any region, managed from LangSmith's US control plane. Across clouds, LangChain handles scaling and platform updates, and BYOC includes Managed Deep Agents endpoints. Migration provisions a data plane, then uses an open-source tool for workspace resources; LangChain separately migrates traces, runs, and feedback, with trace migration currently available on AWS. Self-hosting remains an option for teams requiring complete control.

### Source excerpt

LangSmith BYOC now runs on AWS (GA), Azure and Google Cloud (Beta). Your traces, evals, and agent deployments stay in your cloud account while LangChain runs it.

## How We Optimized Browser Use for Deep Agents

DevFeed: [How We Optimized Browser Use for Deep Agents](<https://devfeed.tech/articles/how-we-optimized-browser-use-for-deep-agents-116377.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/how-we-optimized-browser-use-for-deep-agents>)

Author: LangChain Accounts

Published: 2026-11-03T22:30:50Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [browser](<https://devfeed.tech/topics/browser.md>), [Selenium](<https://devfeed.tech/topics/selenium.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-agents](<https://devfeed.tech/tags/browser-agents.md>), [browser-tools](<https://devfeed.tech/tags/browser-tools.md>), [browserbase](<https://devfeed.tech/tags/browserbase.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [browsing](<https://devfeed.tech/tags/browsing.md>), [cdp](<https://devfeed.tech/tags/cdp.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [chrome-devtools](<https://devfeed.tech/tags/chrome-devtools.md>), [claude](<https://devfeed.tech/tags/claude.md>), [evals](<https://devfeed.tech/tags/evals.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

The team selected Browserbase's Stagehand after comparing seven browser toolsets, then used LangSmith traces and evals to refine it. In their benchmarks, Stagehand passed 90% of WebVoyager tasks for $1.98 total, while Playwright MCP passed 78% for $26.71 and took three times as long per task. Stagehand's code-based `run` batches browser actions, keeping intermediate page data out of the model context; its `snapshot` returns a compact accessibility tree with IDs for interactive elements; and running actions in the browser reduces round trips. A separate harness change made fixed waits end once the page had been quiet for 500 ms. On HardBench, combined with structured answers and a model-call timeout, this reduced median time from 182 to 124 seconds while accuracy stayed within noise. The reported results cover the stated benchmarks and setups; the suggested optimization process is to inspect traces, change tools or harness behavior, and check changes with evals.

### Source excerpt

We compared seven browser toolsets for Deep Agents, picked Stagehand from Browserbase, and tuned it with LangSmith traces and evals. Here's what we learned.

## Why human insight is a strategic advantage for building better agents

DevFeed: [Why human insight is a strategic advantage for building better agents](<https://devfeed.tech/articles/why-human-insight-is-a-strategic-advantage-for-building-better-agents-116378.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/human-insight-strategic-advantage-agents>)

Author: LangChain Accounts

Published: 2026-11-03T21:48:04Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [human review](<https://devfeed.tech/topics/human-review.md>), [human feedback](<https://devfeed.tech/topics/human-feedback.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [annotation](<https://devfeed.tech/tags/annotation.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [context](<https://devfeed.tech/tags/context.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [continuous-improvement](<https://devfeed.tech/tags/continuous-improvement.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [define](<https://devfeed.tech/tags/define.md>), [development](<https://devfeed.tech/tags/development.md>), [domain](<https://devfeed.tech/tags/domain.md>), [evals](<https://devfeed.tech/tags/evals.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [experts](<https://devfeed.tech/tags/experts.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [human-review](<https://devfeed.tech/tags/human-review.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The text argues that expert review helps teams define agent quality, judge behavior in context, and turn feedback into reusable evaluation data. In LangSmith annotation queues, reviewers score a run or full thread against a rubric and record why; reviewing the thread preserves earlier messages and tool calls that may explain a final answer. Teams can use these labels to calibrate LLM judges, update online evaluators, and create golden datasets for regression testing. Fetch Rewards reviewers assess individual assistant turns but inspect tool results, product images, and user-specific offers to verify answers; they document ambiguous cases so engineers can tune automated judges. The account presents human review as a way to expose gaps in both agent behavior and evaluation criteria.

### Source excerpt

Explore 3 principles for effective human-in-the-loop workflows and how human-review is a strategic imperative for production-ready agents.

## Managed Deep Agents: the fastest way to ship a production deep agent

DevFeed: [Managed Deep Agents: the fastest way to ship a production deep agent](<https://devfeed.tech/articles/managed-deep-agents-the-fastest-way-to-ship-a-production-deep-agent-113051.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/introducing-managed-deep-agents>)

Author: LangChain Accounts

Published: 2026-11-02T22:28:13Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [hosting](<https://devfeed.tech/topics/hosting.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [app](<https://devfeed.tech/tags/app.md>), [application](<https://devfeed.tech/tags/application.md>), [assets](<https://devfeed.tech/tags/assets.md>), [async](<https://devfeed.tech/tags/async.md>), [beta](<https://devfeed.tech/tags/beta.md>), [deep](<https://devfeed.tech/tags/deep.md>), [durable-execution](<https://devfeed.tech/tags/durable-execution.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [managed](<https://devfeed.tech/tags/managed.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production](<https://devfeed.tech/tags/production.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [ship](<https://devfeed.tech/tags/ship.md>), [tool](<https://devfeed.tech/tags/tool.md>)

### AI overview

Managed Deep Agents runs the open-source Deep Agents harness on LangSmith, handling production runtime tasks such as durable threads, streaming, deployment, and provisioning for capabilities declared in the project. A project needs only `agent.py`; use `mda dev` to test locally in LangSmith Studio and `mda deploy` to ship. Add files for cross-thread memory, cron schedules, Slack or webhook channels, isolated sandboxes, identity and connections, and other capabilities. Deployments expose an Agent Server API and an `/mcp` endpoint. LangSmith traces tool calls and intermediate steps, while Context Hub stores editable instructions, skills, and durable memory. The managed runtime compiles definitions from `define_deep_agent`; with `create_deep_agent`, developers compile and operate the backend and server themselves. The post says the service is in public beta on LangSmith Cloud.

### Source excerpt

Run deep agents in production with durable execution, sandboxes, tool access, and LangSmith observability, without building the runtime yourself. Now in private beta

[Next page](<https://devfeed.tech/sources/langchain-blog.md?cursor=WyIyMDI2LTExLTAyVDIyOjI4OjEzKzAwOjAwIiwgIjA1ODMyYjQ4LTUwNzEtNDhjNy1iNzdmLTIzOGNmZWI3ZTI0ZSJd>)