Feed

Building Production Agents with Jev and LangGraph

See how LangGraph orchestrates Jev, TypeSafe AI's decision model, to build faster, cheaper production agents.

LangSmith Custom Apps: Build custom interfaces around your agent data

LangSmith Custom Apps lets you build the interface you want with your LangSmith data, publish it into your workspace, and skip the hosting, auth, and permissions work. Learn more.

New in LangSmith: Engine v2, Managed Deep Agents, Fine-Tuning, and more

LangChain announced new updates to LangSmith. Updates include Engine v2 with red teaming and automatic testing, a new version of Managed Deep Agents, trajectories and more.

The ‘SaaSpocalypse’ is over. How Salesforce now plans to thrive in an AI world

New in LangSmith Engine: red teaming and automated testing

LangSmith Engine now includes Red Teaming to proactively detect agent issues and automated agent testing. Learn more about the Engine v2 release.

Introducing LangSmith Fine-Tuning

LangChain introduces LangSmith Fine-Tuning and SmithTune, a CLI built for post-training models. Train specialized models without building data pipelines by hand.

Five Big Ideas Coming Out of Dreamforce 2026

In the leadup to Dreamforce 2026, dozens of announcements outlined what enterprises look like when software meets AI, but the event itself filled in the picture. Organizations are being transformed. Ways of working within them are transforming just as quickly. To see how headless architecture, Slack Code, purpose-trained models, and more are going to shape […]

The 9 best AI tools for social media management in 2026

Click publish, exhale. Start again. Tomorrow's post doesn't write itself. What are people discussing right now? Dive into analytics, surface trends, reply to 15 DMs. And then you go viral, your sales dashboard goes through the roof—but no more free time for you in the next three weeks. Congratulations? The content hamster wheel isn't going away, but AI is here to help you run faster, with more…

The 6 best AI resume builders in 2026

Searching for a job is becoming a job of its own. With so many open positions, tests, and interview stages, joining the workforce or moving up is becoming harder. And with screening software automatically disqualifying candidates, the chances to get some 1-on-1 time with recruiters grow thin. But you have something powerful in your corner: AI-powered resume builders can help you generate a…

Jotform vs. Typeform: Which is the best form builder? [2026]

Back when I was scrolling through my first website in the mid-'90s—I'm almost certain it was SpaceJam.com—web forms were still in their nascent stage. Websites were treated more as one-way communication devices, like newspapers. Forms changed all that. At first, forms were clunky HTML elements that you had to pinch-and-zoom to interact with on small screens. Eventually, Jotform, Typeform, and…

What is Claude Code?

You've probably used software built with Claude Code, maybe even already today. Companies like HubSpot and Atlassian use it to fix bugs and ship new features, and Anthropic itself reports that 80% of Claude's code was generated with its AI coding tool. Originally built for engineers, Claude Code packs a wide range of capabilities to speed up the software development process. But it's so easy to…

Claude models: Fable vs. Opus vs. Sonnet vs. Haiku

Anthropic's Claude family has four primary models: Haiku, Sonnet, Opus, and Fable. The version numbers are inconsistent between them; as I write this, Opus 5.5 just dropped, Fable 5.1 came out on September 1, 2026, Sonnet 5 was released on June 30, 2026, and Haiku is still on 4.5 and launched in October 2025—though a new model is due out soon. There's also Mythos, but the general public doesn't…

How Higher Ed Is Putting AI Agents to Work

At Penn State and DePaul University, AI agents are doing more than automating administrative work. By using AI to connect fragmented data and handle routine tasks, colleges can rethink how they support students in their educational journeys.

Your agent, laid bare

For decades, enterprise software was a black box — hard for companies to understand, implement, adapt, and integrate, or even replace. With Sierra, nothing is hidden. It’s easy to build an agent, understand the actions it takes, integrate it with existing systems, and make changes directly.

Futures Issue 5: Agentic Enterprise Futures

Building the Agentic Enterprise: Secrets from Early Adopters

Salesforce customers are at the forefront of the agentic revolution, and they’re already seeing real-world value from it. Early adopters like Box and Engine are finding new efficiencies and improving the experiences of their own customers at scale. But these kinds of tech shifts don’t happen easily, and there are a lot of learning moments […]

Sierra achieves AIUC-1 certification

Sierra is now AIUC-1 certified, following an independent audit by Schellman and extensive testing by the Artificial Intelligence Underwriting Company (AIUC).

The personalization paradox in private markets distribution

Solve the personalization paradox in private markets. See how WRITER scales advisor outreach in your voice, with compliance built in. The post The personalization paradox in private markets distribution appeared first on WRITER .

The AI Marketing Canvas: Jim Lecinski on why 85% of marketers are stuck in AI transformation

Jim Lecinski explains why 85% of marketers are stuck in AI transformation. Learn the AI Marketing Canvas, a five-stage framework no marketer can skip. The post The AI Marketing Canvas: Jim Lecinski on why 85% of marketers are stuck in AI transformation appeared first on WRITER .

The three pillars of AI-native marketing: Why productivity is just the baseline

AI-native marketing rests on three pillars: visibility, differentiation, and always-on orchestration. Learn why productivity is just the baseline for CMOs. The post The three pillars of AI-native marketing: Why productivity is just the baseline appeared first on WRITER .

Next gen multimodal agents: an interface that morphs with the conversation

Sierra’s multimodal agents bring voice, text, and visuals into the same conversation, so customers get the best of each medium without having to pick just one.

WRITER Unveils Enterprise Brain, the First Universal Context Layer to Power the Agentic Customer Journey

Enterprise Brain launches with team-level Agent Memory, plus new WRITER Meet and WRITER for Slack and Microsoft Teams, bringing shared enterprise context to every conversation, agent workflow, and customer touchpoint The post WRITER Unveils Enterprise Brain, the First Universal Context Layer to Power the Agentic Customer Journey appeared first on WRITER .

Introducing Enterprise Brain: The shared GTM context layer, for an always-on customer journey that’s distinctly yours

Discover Enterprise Brain, WRITER's shared context layer for brand, teams, and compliance. Learn how Agent Memory and WRITER Meet keep GTM work on-brand. The post Introducing Enterprise Brain: The shared GTM context layer, for an always-on customer journey that’s distinctly yours appeared first on WRITER .

Hyper-𝜏-bench: Evaluating agents that build agents

Today we’re open-sourcing hyper-𝜏-bench, a new long horizon agent evaluation that measures how well models can not only act as an agent, but construct one.

AI for call centers: an operating and rollout guide

Use a lifecycle map and go/no-go checklist to plan routing, workforce, technology controls, failover, and expansion for AI in the call center.

Stop giving your agents database credentials

AI agents don’t fail in production because they lack autonomy. They fail because autonomy without structure is impossible to trust.

Executive Insights Series 01: What Happens When AI Eliminates the Easy Conversations

We’ve all been there. You’re deep in work when a colleague drops in—“Quick question, how do I export that report again?” Or your manager pings you about the latest PTO policy. These micro-interruptions—let’s call them what they are: time thieves —steal minutes that turn into hours, fragmenting focus and draining energy.

Executive Insights Series 02: When Thinking Becomes Free

A few years ago, a single cargo ship blocked the Suez Canal and froze nearly $10 billion in global trade each day. The shock, besides the world grinding to a halt, was how completely we’d misread our reality. For decades, we had optimized for demand: forecast it, stimulate it, capture it. But the real constraint wasn’t demand. It was supply. When that ship ran aground, it revealed that our global…

Re:imagine 2025 Dallas - Where AI Velocity Meets Control

The Dallas stop of re:imagine 2025 opened with proof instead of prediction. A customer dialogue with AMD’s Kari Ramseth, HR Service Center Leader, illustrated what disciplined scale looks like in practice.

The Hype Trap: Why Waiting for Certainty Guarantees You’ll Be Too Late

"Doubt is not a pleasant condition, but certainty is absurd." — Voltaire Voltaire nailed something every business leader knows instinctively: if you wait for certainty, you’re waiting for an illusion. In business, certainty is just another word for “too late”—the point where opportunity has been claimed by those who acted when things were still unclear.

How to build Agents Where Data Already Lives

CrewAI and Snowflake give enterprises a cleaner path to build governed, high-impact agents across the business.

How a Mid-Tier Enterprise SaaS Provider Automates Cloud Support Triage

Mid-tier SaaS automates cloud support triage with a 5-agent workflow, boosting ticket validation, routing, and SLA compliance in enterprise cloud support.

How a Leading Fintech Cuts Weekly Compliance Reporting from 2 Days to 2 Hours

Fintech compliance reporting automation cuts weekly reporting time from 2 days to 2 hours using agentic AI for multi-source data extraction and report synthesis.

How a Healthcare Provider Cuts Nurse Intake Work by 80% with Agentic AI

Discover how healthcare automates patient intake using agentic AI, cutting nurse intake time by up to 80% to improve efficiency and patient experience.