Articles, guides and field reports on AI agents
Company AI policy: write it, then check real usage
An unchecked AI policy stays an intention. What it changes in how your teams use AI, and how to check each rule against what really happens.
GitHub Copilot pricing: what usage changes on the bill
GitHub Copilot's price stays per seat, but every request is paid at the model's rate. The settings to check, and how to reopen where usage pays off.
Copilot usage report: active does not mean used
One prompt in a month makes a Copilot licence count as active. What the usage report leaves out, and three checks to run before you renew.
AI automation: from no-code to autonomous agents, a practical guide
Where no-code ends and the autonomous AI agent begins: the criteria for switching, concrete use cases, implementation steps and guardrails.
Workflow automation: a 5-step method and the shift to AI agents
How to scope workflow automation: a 5-step method, rules-based tools compared with autonomous AI agents, and use cases by business function.
Claude Code and agentic coding: how it works, MCP and best practices
Understand agentic coding with Claude Code: the execution loop, the CLAUDE.md file, MCP and best practices for rolling it out in the enterprise.
Jev vs LLM-as-a-judge: we measured 4,500 judgements
Can Jev, TypeSafe's decision model, replace an LLM to evaluate your AI agents? We measured it on RM-Bench: accuracy, bias, calibration, cost.
Dust AI: what reviews miss about how it is actually used
Dust AI explained: features, use cases by team, pricing model and the one usage signal that published reviews almost always ignore.
Claude Cowork: capabilities, limits and how to manage it in the enterprise
Where Claude Cowork fits in your AI estate: what it can do, where it falls short and what to measure before you roll it out across a team.