Blogsby GlyphHow Pizza Hut turns behavioral data into AI-powered experimentation
How Pizza Hut moved from manual A/B testing to AI-built product affinities, using Fullstory behavioral data to see the "why" behind every experiment.
84 of 800 posts
Tue Aug 2542 posts
Verified, not invited: What Gmail’s political sender program actually says about deliverability
Gmail's new Verified Sender Program isn't the spam-filter bypass headlines are claiming; it just requires political senders to do what good deliverability already demands: authenticate their mail, keep volume predictable, and hold spam...
LaunchDarkly is now native on the Vercel Marketplace
You can now install LaunchDarkly from the Vercel Marketplace and evaluate your first flag in minutes. Start on our free Developer plan and upgrade when you need to, all managed from Vercel.
What makes a good AI coworker? With OpenAI’s Codex product lead
Zero-Shot Learning is a podcast about how AI is built, secured, and deployed. Hosted by Nancy Wang, 1Password CTO, and Dev Tagare, Senior Director of Engineering at Google Gemini, it offers a builder’s view of the architecture and complex...
Free GLM API: Which GLM Models Have Free Access in 2026?
Looking for a free GLM API? Compare z.ai's free Flash models, OpenRouter's rate-limited GLM-5.2, and paid GLM-4.5-Air pricing.
The Email Verification API
A new proposal aims to enable email verification directly within the browser.
How Render Workflows powers our internal data pipeline
Learn how Render’s data team uses Render Workflows to orchestrate a production dbt data pipeline with branching logic, durable retries, observability, and cost savings.
Push-button migration from Confluent to Redpanda with Shadowing
Migrate off Confluent without the “big cutover weekend.” Redpanda Shadowing carries topic data, schemas, offsets, and ACLs on a single link. Available on Self-Managed, BYOC, and Dedicated.
Learning by Doing: Reflections from a Summer Internship at Locus Robotics
Marketing Intern Shannon Bailat reflects on her summer internship at Locus Robotics, sharing lessons learned about collaboration, confidence, content marketing, and professional growth.
+1more from Locus Robotics Blog that day
Debugging Deep Agents with LangSmith
Debug deep agents with LangSmith's tracing and analysis. Analyze complex traces, optimize prompts with Polly, and improve performance.
+15more from LangChain Blog that day
- Using skills with Deep Agents
- The rise of "context engineering"
- How Klarna's AI assistant redefined customer support at scale for 85 million active users
- Workspaces in LangSmith for improved collaboration and organization
- Multi-Vector Retriever for RAG on tables, text, and images
- Structured Tools
- LLMs and SQL
- Multi-modal RAG on slide decks
- Agentic Engineering: How Swarms of AI Agents Are Redefining Software Engineering
- How Lyft Built a Self-Serve AI Agent Platform with LangGraph and LangSmith
- Introducing Rubrics: Build Agents that Evaluate and Correct Their Work
- The Art of Loop Engineering
- How We Build Agent Environments & Tasks
- Building Self-Correcting Memory in OpenWiki
- LangSmith Engine Improves Agent Issue Detection by 2x
Introducing Observe: Performance monitoring for Expo apps, now generally available
Observe is generally available. Startup and per-screen performance for React Native, measured on real devices, tied to every build and update.
Why you still need data people in the agentic era & what for
AI can automate data pipelines, but only humans can own business accountability.
The Cost of Reconciliation: Why Community and Regional Banks Lose Time Chasing Numbers
Reporting analysts spend hours every week chasing numbers across reports. Learn how the cost of manual reconciliation adds up and how to eliminate it.
Chat SDK now supports XChat
You can now build bots that hold end-to-end encrypted 1:1 and group conversations on XChat with the new XChat adapter for Chat SDK. The adapter handles all encryption, key management, and signature verification automatically.
+11more from Vercel News that day
- Bring your agent to Notion with Chat SDK
- Vercel Connect now supports Linq
- Chat SDK now supports Slack Enterprise Grid
- Vercel Connect is now generally available
- AI Gateway now supports asynchronous video generation
- Wan 3.0 now available on AI Gateway
- MiniMax M3 and M2.7 are free on AI Gateway
- The end of credential sprawl for agents
- Introducing Run SDK: secure eval for your agents
- Speed Insights now has a free tier
- Vercel applications are protected from Next.js August 2026 security vulnerabilities
Ground AI agents with live enterprise context using UiPath Data Fabric
Read how UiPath Data Fabric gives AI agents secure access to live enterprise data with structured queries, reusable entities, and built-in governance.
The Entertainment Industry’s Biggest Names Back Stability AI in Latest Funding Round
We've closed our Series B, bringing total funding to $232M under new leadership. This round welcomes entertainment titans Electronic Arts, Sony Music Group, Universal Music Group, Warner Music Group, and more.
SentinelOne Cybersecurity Blog
The Path to the Autonomous SOC: The Early Returns of AI & What It Means for Cybersecurity
Discover how early-stage AI yields rapid SOC returns, driving platform consolidation and reducing analyst burnout in this blog post.
What Is Workforce Planning? Definition, Types and Benefits
If it feels like a constant scramble to find the right people, you’re not alone. Workforce planning gives organizations a clearer, more proactive path forward.
OpenRouter Video Generation API: A Code-First Guide
Every video provider has its own endpoint, job statuses, polling logic, and output format. Our async video API puts Seedance, Veo, Wan, and more behind one submit, poll, and download loop. Here's the full lifecycle in Python and TypeScript.
+2more from OpenRouter Blog that day
Claude Desktop support with Ollama
Claude Desktop can now be configured to work with Ollama as a third-party gateway provider, making it possible to use open models in Claude.
How we made Lovable apps work with the rest of your stack
How Lovable went from no formal integrations to nearly 100 app connectors in six months, and what's next for OAuth, permissions, and app user connections.
groundcover's Partner Ecosystem Is Scaling Fast - Here's What's Behind the Momentum
Partner-sourced pipeline has grown eight-fold since launch and now represents more than 10 percent of groundcover's overall pipeline, a strong indication that partners are becoming an increasingly important source of new business rather...
Which brands does AI recommend in Mexico? We measured 14,000 answers
Read our Mexico Visibility Index - we analysed 14,000 AI answers to 700 questions Mexican consumers actually ask - in Spanish, across seven industries and 315 brands.
Level Up Your Security with Fastly API Enforcement
Take control of your API landscape with Fastly API Security. Discover, monitor, and enforce schema compliance at the edge to stop threats and secure your apps.
From Lab to Fab: Capturing the Uncatchable in CMP Filtration
From Lab to Fab: Capturing the Uncatchable in CMP Filtration
Private Preview: DigitalOcean Managed Agents Runtime Services
AI agents are helping developers, teams, and businesses do more: writing and executing code, conducting research, and running dynamic workflows across systems. But that ability is often bounded by where they run.
SRE best practices and platform engineering trends: How AI workloads raise demands on observability to meet reliability requirements
AI workloads are reshaping SRE and platform engineering. New Dynatrace research shows how AI is changing SRE and platform engineering in two ways: teams are using AI to streamline and scale IT and DevOps while taking on greater...
+1more from Dynatrace News that day
Introducing the CodeRabbit plugin for Cursor
Install the CodeRabbit plugin for Cursor and run focused code reviews from the same Agent session where you build.
Apple introduces M6 and M5 Ultra for a big leap in performance and AI compute
Apple debuted M6 in the new Mac mini and M5 Ultra in the new Mac Studio, providing an extraordinary leap in performance and AI capabilities.
+2more from Apple Newsroom that day
The New Face of Financial Fraud: AI-Powered Brand Abuse
AI-powered brand abuse is hitting banks hard. Read about the threats, the business impact, and how Akamai Brand Guardian helps financial institutions fight back.
Problems with large tables in Postgres
Postgres presents pretty predictable performance problems when dealing with large tables. Sharding solves this.
Three SLOs every search team needs: monitoring search latency, availability and quality with OpenTelemetry
Your OpenTelemetry search spans already carry the signals for SLOs, burn rate alerts, anomaly detection and incident response, and this post shows how to build all four in Elastic Observability.
The Grafana AI SDK for Go: a shared foundation for building AI applications
Starting an experiment with an LLM has never been easier. Keeping a growing collection of those experiments consistent is another matter.
MotherDuck Acquires Tower: Agents Can Answer. Now They Can Build
I’m excited to announce that MotherDuck has acquired Tower Computing Inc. Tower provides runtime infrastructure for data engineering tasks, and is ideally situated to help AI agents and vibe-coded pipelines run data engineering tasks.
ClickGap: Autonomous QA for ClickHouse
ClickGap reviews merged ClickHouse changes, executes reproducers, rejects false positives, and attributes regressions to specific commits.
+2more from ClickHouse Blog that day
Scaling AI is easy. Trusting it is hard
As AI scales, cracks in data trust and governance start to show. Here's what breaks first, and what it takes to fix it.
DuckDB Table Functions in Java
The DuckDB Java client can register table functions written in pure Java, exposing any Java-accessible data source as a SQL table.
+1more from DuckDB Blog that day
CUDA Python 1.0: Stable APIs, One Foundation, Full Platform Access
For years, a Python developer who needed a GPU had two realistic choices: Learn NVIDIA CUDA C++ well enough to write an extension, set up a build toolchain, and...
+1more from NVIDIA Technical Blog that day
Wire It, Run It, Deploy It: AI Workflows in Gradio
+2more from Hugging Face Blog that day
AgentHands: Generating interactive hand gestures for spatially grounded agent conversations in XR
Human-Computer Interaction and Visualization
Project Lighthouse, Part 3: Introducing project-lighthouse-anonymize
Project Lighthouse, Part 3: Introducing project-lighthouse-anonymize The data in Project Lighthouse is powered by privacy-preserving anonymization code.
Introducing the Admin plugin for ChatGPT Work and Codex
Use the Admin plugin for ChatGPT Work and Codex to analyze workspace usage, manage members and permissions, adjust limits, and act on admin requests.