Practitioner take: cross-product MCP workflows are missing; agents could run 60-80% of company ops
pritisinghhhh · x · 2026-08-28
A practitioner argues there's a clear market need for cross-product workflows exposed to agents via MCP — multi-step execution spanning different product surfaces, running somewhat deterministically, available to AI apps and coding agents.
Key points: - MCP is good (though multi-step tool chaining got closed in the new spec) and Skills are heavily used, but the current dichotomy is weak: agents orchestrating tools randomly across MCP servers vs. skills that are "workflows disguised as long prompts and shell scripts"; - We're early on long-horizon, cross-product orchestration; state and idempotency get far too little attention; - He envisions 60-80% of company operations running via such workflows, executed and managed by humans through their agents, with Temporal, Zapier, and n8n as strong players.
More from coding & agent
- Google DeepMind uses Teamwork multi-agent framework for math breakthroughs — algo_diver · 2026-08-28
- Oxlint Config v2 Released to Keep AI Agents on Track — cnakazawa · 2026-08-28
- Overengineering pitfalls: Misusing Docker and excessive constraints — burny_tech · 2026-08-28
- Photographer tests ChatGPT Desktop for photo editing: achieves perfect results, saves $1k/month — Ice2jc · 2026-08-28
- Video: Why teams are taking back control of their AI coding stack — labeveryday · 2026-08-28
- Relay Harness Unifies 204 Models into a Single Coding Agent with Prepaid Billing — realmeetjames · 2026-08-28