News and engineering notes from the team building AI agents for enterprise implementations.
Yes, if the AI reconciles its own work. superglue reads the QuickBooks Desktop company from a .QBM file without QuickBooks, loads a NetSuite sandbox and checks the trial balance, open items and applied payments against QuickBooks.
Install the free QuickBooks Desktop Enterprise trial, save the company as a portable company file (.QBM), and superglue reads the whole company from it.
Yes. superglue reads a QuickBooks Desktop portable company file (.QBM) without QuickBooks installed and returns the company data as records.
superglue joins the Information Technology Alliance (ITA) as a Silver Technology Partner. The partnership brings AI-agent-driven ERP implementations to ITA's community.
superglue reads a QuickBooks Desktop portable company file (.QBM) without QuickBooks, maps it to NetSuite, Sage Intacct or Business Central, and reconciles the load against QuickBooks.
superglue's implementation agents set up and migrate each client's systems. Artifact's agents then run the recurring accounting work from the first month.
NetSuite users can now read and write NetSuite records from their AI agent.
Why superglue’s MCP server now returns complete tool results with no size limit, and what happened when we sent 12 MB of JSON to Claude, ChatGPT and other MCP clients.
A practical look at Jev’s structured decisions, probability calibration, and performance in superglue’s documentation pipeline.
Sage Intacct users can now create and update records straight from Claude.
Pine Services Group's firms run ERP implementations for more than 10,000 customers. We've signed a group-wide agreement that opens superglue to all 18 of them, starting with a NetSuite implementation at The Vested Group.
superglue's AI agents are available to Sage implementation partners around the world, automating data migration and configuration in Sage Intacct implementations.
Why prompt caching matters and how superglue agents maximize prompt cache hits.
A custom MCP server connects your AI agents to internal APIs, legacy ERPs, and proprietary databases through a standard interface. Learn when to build one and how superglue lets you do it in minutes.
As the number of agentic AI applications grows, enterprises must address data access enforcement, auditability, integration reusability, and tool portability — or face compounding risk and technical debt.
We went through three architectural iterations to figure out how our AI agent should apply edits to JSON tool configurations. Here's what we learned about structured output, search & replace, and JSON Patch.
In building integrations using AI, one of the toughest engineering tasks is turning third-party documentation into reliable context for agents. Learn about our approach at superglue.
Why developer tools don't need UIs anymore. With MCP and agents like Cursor, the age of clicking through dashboards is ending. The future is capability-based interfaces that work directly in your editor.
The fundamental difference between agentic tools and API endpoints. Why MCP exists as an abstraction layer that provides capabilities rather than forcing agents to navigate endpoint orchestration.
The reality behind MCP adoption: who builds and maintains MCP servers for legacy enterprise systems? Exploring the challenges of bridging modern AI interfaces with decades-old software.