Pondhouse Data Blog

How Kuken made 70 years of engineering drawings searchable with AI, and how to build the same pattern with a vision model, Postgres and image search.

How NVIDIA Auto Ontology grounds text-to-SQL in an automatically generated semantic layer, what worked in our test and where it still falls short.

How we moved 310 Confluence pages into a Git-based company wiki that an LLM agent updates, cross-links and checks, with a human reviewing every change.

Copilot Studio loads SharePoint lists whole. Two agent flow tools fix that: one reads internal column names, one fetches only matching items via OData.

Run GLM-4.7-Flash, a 30B MoE coding model, on a 16GB GPU: build llama.cpp for NVIDIA or AMD, serve the Q4 GGUF and connect it to OpenCode.

Build graph-based Microsoft Agent Framework Workflows in Python: a four-step IT ticket pipeline, the DevUI, and conditional edges for urgent tickets.

Microsoft Agent Framework explained: tools, workflows, state and checkpointing, then a Python IT helpdesk agent with Dev UI, FastAPI and Docker.

Connect AI agents to BigQuery via MCP: Google's managed remote server vs. MCP Toolbox 1.16, with setup, guardrails, costs and a 7-question agent test.

RAGFlow 1.0 installed with Docker and tested on a 147-page PDF: setup, OpenAI models, DeepDoc vs. a vision LLM parser, RAM usage and answer accuracy.

How MCP sampling lets a FastMCP server hand its LLM calls to the client: ctx.sample on the server, a sampling handler on the client, with code.