Building a PowerShell agent harness: model routing by prompt with explicit tool permissions
dfinke · x · 2026-09-24
Developer dfinke is building a PowerShell agent harness around a simple idea: let the AI choose its model, then check available tools before acting. Built on his PSAISuite (15 providers and their models) plus Jev for PowerShell, it routes models by prompt and enforces explicit permissions — what can run, where files get saved, read-only or not. More details promised soon.
More from coding & agent
- Malicious AI agents steal 600K credit cards, hit 100+ sites with skimmers — ChuckDBrooks · 2026-09-25
- Self-organizing agent teams hit 66.7% across five benchmarks, beating their strongest member — Aneesh Pappu · 2026-09-25
- Antigravity SDK offers plug-and-play support for Ollama, LM Studio, and vLLM backends — rseroter · 2026-09-25
- TinyFish launches Data Partners Alliance with Crunchbase, Similarweb and 13 more for AI agents — ayushtweetshere · 2026-09-25
- Anthropic staffer's startup tip: build things that save agents tokens — jeff_weinstein · 2026-09-25
- Enterprise agent security whitepaper maps 8 vulnerability classes, claims 8.3% injection rate — Kyrannio · 2026-09-25