An Agent That Closes the Troubleshooting Loop

Automating the entire troubleshooting loop across Datadog logs and GitHub Actions. No tickets, no waiting.

April 15, 2025 · 1 min · 73 words · David Twizer

How xpander.ai Embraces the Model Context Protocol in Practice: An Engineering Deep-Dive

The architecture, the gritty engineering challenges (from SSE streaming to multi-tenant security), and how we wove MCP into a production agent platform.

March 31, 2025 · 25 min · 5324 words · David Twizer

The Year AI Will Start Building and Managing Other AI Agents

When you have a genie in a bottle granting you three wishes, clever thinkers will ask the genie for another genie.

January 2, 2025 · 5 min · 1050 words · David Twizer

Announcing Agent Graph System: 4x Better Multi-Step Tool Use

An agent built with Agentic Interfaces and Agent Graph System hit a 98% success rate on multi-step tasks, versus 24% for GPT-4o alone, and did it 38% faster with 31.5% fewer tokens.

November 20, 2024 · 8 min · 1665 words · David Twizer

From Manual to Autonomous: Revolutionize Business Tasks In-House

How enterprises can build and deploy AI agents in-house: autonomous digital workers that automate complex tasks while keeping full control over data, security, and cost.

November 18, 2024 · 9 min · 1777 words · David Twizer

xpander.ai + OpenAI Realtime API

Real-time function calls across any system: 1st-party APIs, 3rd-party services, or custom platforms.

October 3, 2024 · 1 min · 70 words · David Twizer

xpander.ai + NVIDIA NIM

A Text-to-Action runtime that turns text inputs into tangible results with graph-driven agents.

September 16, 2024 · 1 min · 87 words · David Twizer

Optimizing EC2 Workloads with Amazon CloudWatch

Many customers ask for our advice on choosing the ‘best’ or the ‘right’ storage and instance configuration, but there is no one solution that fits all circumstances. This blog post covers the critical techniques to right-size your workloads. We focus on right-sizing a SQL Server as our example workload, but the techniques we will demonstrate apply equally to any Amazon EC2 instance running any operating system or workload. We create and use an Amazon CloudWatch dashboard to highlight any limits and bottlenecks within our example instance. Using our dashboard, we can ensure that we are using the right instance type and size, and the right storage volume configuration. The dimensions we look into are EC2 Network throughput, Amazon EBS throughput and IOPS, and the relationship between instance size and Amazon EBS performance. ...

June 9, 2021 · 1 min · 182 words · David Twizer

Running SQL Server with Amazon FSx as a shared storage

With Amazon FSx, you get fully managed shared file storage that automatically replicates the storage synchronously across two Availability Zones. Moreover, Amazon FSx provides high availability with automatic failure detection, failover, and failback. The service also fully supports the SMB Continuous Availability (CA) feature required to support SQL Server Always On FCI deployments. For those of you who chose to deploy SQL AG with Enterprise Edition licenses, to avoid the complexity and cost of using FCI with shared storage, now you can use Standard Edition licenses. This will save you 50–60% in license costs. It will also simplify the overall complexity of your SQL deployment and ongoing management (like not needing to replicate system database objects across all replicas, which you must do in AG deployments). ...

March 6, 2020 · 1 min · 135 words · David Twizer