Loops vs. graphs: a new way to structure agent workflows around company memory
femke_plantinga · x · 2026-07-23
The post lays out two ways to run an agent on the same support task: loops and graphs.
- Loops: you define the goal and quality bar, and the agent owns the path, drafting, checking, and retrying until it passes.
- Graphs: you define the workflow up front — read → triage → draft → QA → send — and the agent fills each node.
Both rely on a shared company brain: past tickets, policies, and product docs that each step can pull from as the work moves through the process. The takeaway is simple: use loops for one-off, exploratory work; use graphs when the work is repeatable and the path is already known.
More from coding & agent
- Hermes merges 114 PRs, adding multi-window desktop support and tighter MCP handling — Teknium · 2026-07-23
- Genspark gives its AI agents persistent memory with SecondBrain — rohanpaul_ai · 2026-07-23
- Cognition’s SWE-1.7 Lightning is being used for rapid design iteration and live production fixes — silasalberti · 2026-07-23
- ToolFunnel wraps old MCP servers so they still work after the July 28 spec change — WorldlyAd7946 · 2026-07-23
- Developers compare multi-agent terminal setups, from Ghostty split panes to Claude agents — majidmanzarpour · 2026-07-23
- Poolside ships Laguna S 2.1, a compact open-weight coding model that outperforms bigger rivals — The Decoder · 2026-07-23