Copilot CLI issue proposes inline custom-agent calls and chaining
DenDrobiazko-Apryse · ghdev · 2026-07-21
A GitHub Copilot CLI issue proposes explicit inline custom-agent invocation and chaining inside prompts.
- Today, users can pick a custom agent before starting a task or rely on automatic delegation, but cannot clearly switch agents mid-prompt.
- The proposal adds syntax like $agent: architecture-review so a workflow can pass findings from one specialized agent to another while preserving context.
- The author argues this would make multi-agent workflows more deterministic, easier to document, and less dependent on the model guessing which agent to use.
More from coding & agent
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- Investment Analyst Asks How to Build a Claude-Based Diligence Agent Stack — Careless_Tie2286 · 2026-09-11