Blogsby Glyph65% of teams have misdiagnosed digital friction, shipping the wrong fix
Shipping a fix for the wrong root cause charges a compounding tax on engineering resources and customer trust.
120 of 800 posts
Wed Aug 2650 posts
Governed AI at the speed of Snowflake: How Collibra MCP powers Snowflake CoWork & Cortex CoCo
What Is Collibra MCP? MCP is an open standard that gives AI assistants and agents a live, structured connection to enterprise systems. It functions like an API layer purpose-built for AI applications.
You can't control what you can't see
What LaunchDarkly showed live on the Control Panel: how to see what's happening in production, act on it in real time, and test on data you already trust.
Fewer lockouts, less manual work: What's new for 1Password EPM admins
As a company grows, more employees join, but the size of the IT team overseeing critical systems often doesn’t grow at the same pace.
WebMCP Opens Your Website to Agents
Open your documentation site to ChatGPT, Codex and other browser agents with WebMCP and Context7.
+1more from Upstash Blog that day
Giving Agents Their Own Turso Accounts with AgentID
AgentID gives AI agents their own OIDC identity, so an agent can create and access its own Turso account with no borrowed credentials or human in the loop.
Aperture GA: Building a home(lab) for agentic AI
Adding model tokens, chat Projects, MCP controls, and more.
Why Your AI Application Is Exposed (Even When Your Scans Come Back Clean)
AI applications can pass security scans yet remain exploitable through chained attacks across models, tools, data, and business workflows. Learn how DAST, AI pentesting, and red teaming work together to expose end-to-end risk.
How to evaluate session replay software: a developer's guide
Compare session replay tools on recording methodology, privacy architecture, integration depth, overhead, AI-readability, and mobile support
Intelligent Model Routing on Replit
You want to bring an idea to life, not compare models. But the best model for the task can change week to week, project to project, task to task.
Pulumi Context API: query your infrastructure as a graph
Every platform team fields the same questions: What is running? What breaks if we change this? What can we safely delete? The answers exist, but they’re scattered across state files, cloud consoles, and the memories of whoever set things...
Prisma Is Building the Stack for the Next Million Products
Prisma is building a software factory: one environment where a builder describes what they want and an agent builds it, runs it, inspects it, fixes it, and keeps going.
Sharing Linear’s growth with the people building it
As Linear passes $100 million in ARR, we’re giving our team another opportunity to participate in the upside.
+1more from Linear Blog that day
Introducing Pytest and Vitest integrations for LangSmith Evaluations
Introducing a new way to run evals using LangSmith’s Pytest and Vitest/Jest integrations.
+53more from LangChain Blog that day
- Role Based Access Control (RBAC) for LangSmith
- LangServe Playground and Configurability
- Cube x LangChain: Building AI experiences with LLMs and the semantic layer
- Using LangSmith to Support Fine-tuning
- Benchmarking Question/Answering Over CSV Data
- Making Data Ingestion Production Ready: a LangChain-Powered Airbyte Destination
- Automating Web Research
- Plan-and-Execute Agents
- Announcing our $10M seed round led by Benchmark
- Retrieval
- Timescale Vector x LangChain: Making PostgreSQL A Better Vector Database for AI Applications
- Autonomous Agents & Agent Simulations
- Meet Connery: An Open-Source Plugin Infrastructure for OpenGPTs and LLM apps
- LangChain State of AI 2023
- OpenAI's Bet on a Cognitive Architecture
- How to design an Agent for Production
- Kay x Cybersyn x LangChain: Embedding SEC Filings for RAG
- Eden AI x LangChain: Harnessing LLMs, Embeddings, and AI
- Xata x LangChain: new vector store and memory store integrations
- Introducing Airbyte sources within LangChain
- Qdrant x LangChain: Endgame Performance
- Data-Driven Characters
- Auto-Evaluator Opportunities
- Applying OpenAI's RAG Strategies
- Agent observability needs feedback to power learning
- Building a company due diligence Agent with Deep Agents
- LangSmith Engine: How We Built an Agent for Improving Agents
- EU Macroeconomic Analysis with Deep Agents and You.com
- How Harmonic Rebuilt Scout on Deep Agents and 4x'd Retention
- Build an Auditable VC Research Agent with Perplexity
- How Candidly Built State-Aware Agent Harnesses in LangSmith
- Wiki Memory: File-Based Memory for AI Agents
- Proving Agentic AI ROI in Financial Services
- LangChain Announces Enterprise Agentic AI Platform Built with NVIDIA
- LangChain raises $125M to build the platform for agent engineering
- LangGraph Platform is now Generally Available: Deploy & manage long-running, stateful Agents
- AI Agent Latency 101: How do I speed up my AI agent?
- LangChain and NVIDIA Launch NemoClaw Deep Agents Blueprint
- Evaluating OpenWiki with WikiBench
- January 2026: LangChain Newsletter
- Why We Rebuilt LangChain’s Chatbot and What We Learned
- Reflections on Three Years of Building LangChain
- Introducing Interrupt: The AI Agent Conference by LangChain
- LangChain State of AI 2024 Report
- LangSmith: Redesigned product homepage and Resource Tags for better organization
- LangChain's Second Birthday
- Pushing LangSmith to new limits with Replit Agent's complex workflows
- How Podium optimized agent behavior and reduced engineering intervention by 90% with LangSmith
- Announcing LangGraph v0.1 & LangGraph Cloud: Running agents at scale, reliably
- Aligning LLM-as-a-Judge with Human Preferences
- How Factory used LangSmith to automate their feedback loop and improve iteration speed by 2x
- How LangSmith and LangChain OSS Help You Meet EU AI Act Requirements
- LangSmith LLM Gateway: Runtime Controls for Agents
Inside SWSH's automated mobile release pipeline with Expo
SWSH runs 300 builds a month and ships a native release every week. Here's how the team automated the whole pipeline with EAS Build, Submit, Update & Observe.
Why we rebuilt the engine behind Estuary
Estuary rebuilt its runtime for faster, more scalable data movement with transactional correctness, autonomous scaling, and simpler operations.
Workflow lab: Moving between design and code with agents
Coding agents are reshaping how developers build, but they’re only as good as the input they’re given. This workflow explores how context keeps code and canvas in sync.
Closing the AI agent trust gap with graduated autonomy
Most teams give AI agents either full access or read-only, leaving value unused or risk unmanaged. This post describes graduated autonomy, an architectural pattern in which agents earn expanded permissions through sustained reliability and...
+1more from AWS Architecture Blog that day
Building a data plane from scratch: Stripe’s own high-performance distributed proxy
To minimize failed payments for our users, Stripe targets 99.9995% reliability. As traffic grew beyond 1.6% of global GDP, this put intense strain on the service mesh.
How researchers adapted Dolma for better Thai language models
Thai researchers adapted Ai2’s open Dolma toolkit to build Mangosteen, a 47-billion-token Thai corpus that filters low-quality web data while maintaining or improving model performance and strengthening Thai cultural knowledge.
Confidence to Go Further: Workiva Amplify 2026
Workiva Amplify 2026 brings together finance, accounting, sustainability, and GRC professionals in Las Vegas, September 14–16. Explore 90+ sessions, earn up to 11 CPE credits, and confidently go further. Register at workiva.com/amplify.
Python projects now support routing rules
Python projects can now use routing rules to set response headers or rewrite requests to internal paths, including apps built with FastAPI, Django, and Flask.
How Hologryph built SAND: Raiders of Sophie for a sustainable live ops cadence
Learn how Hologryph engineered SAND: Raiders of Sophie in Unity to ship new content on a consistent live ops cadence.
The reliability paradox: you bought more automation tools, and your team is doing more manual work
See why fragmented automation and AI agents create new reliability risks, and how shared orchestration helps SRE teams preserve context, recover safely, and reduce operational toil.
Everything in its place: Making agents write correct Temporal applications
The tools and habits I've found that lead to stable, production-ready Temporal applications.
SentinelOne Cybersecurity Blog
Edge Infrastructure Under Siege: What Two Independent Datasets Reveal About Who's Exploiting Your Perimeter
A new joint study by Tenable and SentinelOne reveals how state and criminal groups converge on the same vulnerable edge infrastructure.
Celebrating excellence: Palo Alto Networks announces the 2026 North America Partner of the Year Awards
At the 2026 Executive Partner Summit, Palo Alto Networks President BJ Jenkins made one thing clear: the AI era is the platform era, and above all, the AI era is the …
Nutanix Kubernetes Platform Achieves CNCF Kubernetes AI Conformance
The Nutanix Kubernetes Platform (NKP) solution is now a CNCF Certified Kubernetes AI Conformant Platform. NKP 2.18 satisfies all twelve requirements of the Certified Kubernetes AI Conformance Program validated on production infrastructure...
+2more from Nutanix Blog that day
How to Build a Data Science Portfolio
Data science is among the fastest-growing fields. In fact, the US Bureau of Labor Statistics (BLS) projects it’ll grow 34% from now until 2034.
+2more from Intuit Blog that day
Streamline identity lifecycle management on HCP with SCIM provisioning
New HCP SCIM provisioning automates user and group lifecycle management from your identity provider to reduce admin overhead and improve secure, consistent access.
Everything New in groundcover Dashboards: August 2026
A roundup of everything new in groundcover Dashboards this quarter: thresholds, tree maps, gcQL, and more, all built for agents and humans alike.
Inside Fastly’s 2026 Internship Program: Projects, Impact & Culture
Go behind the scenes of Fastly’s 2026 Internship Program. See how our intern cohort tackled real-world engineering projects and made a lasting impact.
Introducing v5 Droplets: next-generation performance, sized to your workload
We’re excited to introduce v5 Droplets, a new generation of compute built on 5th Gen AMD EPYC™ processors. v5 Droplets are purpose built to deliver higher performance for demanding workloads such as compute-intensive agentic AI platforms...
Bring observability to SCADA systems in operational technology environments
Step outside your home. The water flowing from your tap, the tolls collected on the highway, the gas that heats your stove, and the power delivered to your city. None of it runs on a web app or a mobile dashboard.
The world runs on open source. We’re putting more than $10 million behind it
CodeRabbit is committing more than $10 million of its actual direct cost to open source over the next year through cash sponsorships, free Review and Security, and broader agentic support across the software development lifecycle.
Everything We Tried Failed Except for This One Weird Trick
We got rid of most of our marketing and are just focusing on the thing that actually works.
Not the Coyote, but the Road Runner: The Reality of Autonomous AI Attacks
Autonomous AI security threats aren't novel super-weapons. They're relentless, low-tech attacks that never stop. Learn why traditional defenses fail.
Taming PUNKs: How ES|QL queries Elasticsearch fields it was never told about
In Elasticsearch 9.5, ES|QL can query unmapped fields. It reads them from _source or returns nulls, so a query keeps working when a field drops out of the mapping and you avoid a reindex that takes hours.
DuckDB outgrows its nest
Today Duck Labs, the developers of DuckDB, announced they are being acquired by Amazon. This is big news in the duck-iverse, and many people are wondering what this will mean for everyone’s favorite duck-powered database, MotherDuck.
What's new in the ClickHouse.NET Driver: the road from 1.0 to 1.3
Discover how ClickHouse.NET Driver 1.1–1.3 adds type-safe POCO workflows, extensible serialization, broader type support, performance improvements, and official ecosystem integrations.
DuckLabs to Join AWS, Projects to Remain Open Source
DuckLabs will join Amazon Web Services (AWS), which is expected to be effective in early September. The projects will remain open-source under the MIT license.
Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It’s...
+2more from NVIDIA Technical Blog that day
Scaling Conditional Learned Retrieval for Pinterest Home Feed
Devin Kreuzer | Sr. Machine Learning Engineer; Yichi Wang | Machine Learning Engineer I; Sujan Reddy Ale | Machine Learning Engineer I; Zelun Wang | Sr. Machine Learning Engineer; Hongtao Lin | Sr.
Intelligent transcription with Gemini 3.5 Transcribe
Now you can get more intelligent speech-to-text transcription with Gemini 3.5 Transcribe.
How loveholidays is making everyone a builder with Codex
Discover how loveholidays uses OpenAI Codex to make software development accessible across the business, helping teams turn ideas into products faster.