Blogsby GlyphSeeds of Science, Visuals in Bloom: Introducing Whole-Graph Projections
Bloom, part of Neo4j’s suite of user tools, has offered analysts the ability to run a selection of Data Science algorithms for quite a while.
31 of 800 posts
Mon Jul 2024 posts
Why AI agents fail: they don't understand your business
A mounting problem across every enterprise Enterprise AI isn't failing because the models aren't good enough. It’s failing because the models don't understand the business they're operating in.
OpenAI Python SDK Guide: Install, Configure, and Use the OpenAI API in Python
Learn the OpenAI Python SDK, set up the OpenAI API in Python, and ship chat, streaming, tool calling, and compatible workflows faster.
+1more from Novita that day
Building AI Agent Databases: A Complete Guide to Database-per-Agent Architecture
Most database scaling advice breaks when you're dealing with AI agents. Here's why giving each agent its own database works, and four patterns for building it on Turso.
MongoDB Query Tracing in.NET with Sentry + OTLP
Trace MongoDB queries in.NET using OpenTelemetry and Sentry's OTLP ingestion. See spans, query data, and error correlation in Sentry.
Incident Response as Code: Managing PagerDuty with Pulumi
You usually find out in the postmortem: the alarm fired, but it paged a schedule nobody was on anymore. Or the service had been running in production for three months before anyone created the matching PagerDuty service, so the first...
Extending Prisma 8 with Typed Postgres ltree
Use PostgreSQL ltree in Prisma 8 with prisma-ltree: typed path columns plus ancestor and descendant queries.
How we picked LibreChat, and ended up with a Slack agent
How Metabase's Cloud team consolidated AI tooling behind self-hosted LibreChat, contributed upstream MCP fixes, and built LibreBot, a Slack agent for internal tools.
Introducing Loops
Loop engineering has quickly emerged as an important practice in software development. In tools like Claude Code and Codex, developers define recurring or trigger-based behavior for their agents, usually through a /loop command, and hand...
How Anything Is Building a Vibe-Coding Empire with 1M+ Users
How Anything uses E2B to give every AI agent a real computer, powering app generation for more than one million users.
OSWorld on Daytona Windows Sandboxes
+1more from Daytona Blog that day
Purge your Remote Cache's build and CI artifacts
Team Owners can now clear the team's Remote Cache of all artifacts in one click. This is useful when you believe there are poisoned artifacts in your cache.
+1more from Vercel News that day
Meet the Unity CLI: manage Unity from your terminal
Install editors, automate CI, and drive a running Editor or dev build from the terminal. The Unity CLI and com.unity.pipeline package give scripts and AI agents a fast, structured way to operate Unity.
The new enterprise AI conversation leaders are having right now
Learn what enterprise leaders must solve to move AI from promising pilots to reliable business processes that are governed, measurable, and built to scale.
Introducing Agent Data Visualization: See Your AI Search Data Answered as Charts
Data visualization lives inside the Searchable Agent. Ask about your AI visibility, competitors, prompts, or citations and get the answer back as a live chart, table, or funnel in the conversation.
Go from product launch to insight to action in minutes
Learn how to launch, monitor, and act on product data faster using Amplitude's Global Agent
+2more from Amplitude Blog that day
Why Taste Matters: Building Real-Time Recommendation Systems with AI
+1more from Akamai Blog that day
Every UPDATE Leaves a Ghost: MVCC, Bloat, and VACUUM in PostgreSQL
What happens to old row versions after nobody needs them? They become dead tuples, and over time they bloat your tables. Go deeper into PostgreSQL MVCC with runnable psql examples.
AI shopping agents: Why context comes before the query
AI shopping agents that guess at your vocabulary make expensive mistakes. Pre-computed catalog context stops the guessing before the first tool call.
Your next level starts here: A preview of dbt Summit sessions, by role
Preview dbt Summit 2026 sessions by role: hands-on labs and breakouts for analytics engineers, data leaders, and execs.
How our universal content processing platform Riviera evolved for AI and beyond
Riviera is the Dropbox content processing platform that’s been iteratively improving content transformation in our products for roughly a decade.
Integrate NVIDIA Omniverse RTX Sensor Simulation Into Existing Apps
Developers building 3D, design, simulation, robotics, and industrial digital twin applications need ways to bring physical AI capabilities into the tools and...
+1more from NVIDIA Technical Blog that day
Together AI and Y Combinator partner to launch the first dedicated GPU cluster for the YC community
No more two-year compute contracts. Together AI and YC just gave YC startups a faster way to get GPUs.
Safety and alignment in an era of long-horizon models
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.