MCP and skills: measure and reduce tokens without losing context

A reproducible MCP lab measures local token counts, tests filters and projections, and checks that shorter results preserve the evidence needed.
24 articles for “ai”, page 2 of 2

A reproducible MCP lab measures local token counts, tests filters and projections, and checks that shorter results preserve the evidence needed.

A Docker lab shows how an agent harness controls permissions, retries, budgets and evidence, and when to choose an existing runtime.

A small pull request can pass its tests and still be wrong. A Docker example shows how to expose the defect, fix it and explain the acceptance decision.

A Docker lab with LangGraph shows what runs again after a crash and how checkpoints and idempotency keys prevent duplicate tickets.

Decide when a project map is enough and when to pin revisions. A complete submodule setup with manifests, agent instructions and a runnable Git example.

Verify AI coding agents from requirements to release: source checks, regression tests, review and deployment evidence, with a runnable example and reusable skill.

Evaluate AI coding agents in a team: quality, complete-task cost, ownership and criteria for adopting, limiting or stopping a pilot.

Organise context, sources and handoffs for AI agents. A real Notion knowledge path, from METR findings to reuse and ongoing maintenance.

Compare LangChain, LangGraph, OpenRouter and Langfuse by role and use case: practical criteria for business AI projects, with technical details.

Research in progress on the cost of Claude and Codex tasks: usage, time and human review, with commands and settings for the workflow variants to compare.

Build a code review skill for Claude and Codex. A lab compares two descriptions across four Codex sessions, with observed results and limits.

What MCP does and when to adopt it: business processes, costs, permissions and decision criteria, with a complete server example.