Agent orchestration tips: a manager or simple sequence beats complex topologies
PawelHuryn · x · 2026-09-09
Pawel Huryn shares practical agent design steps. Step 4, provide memory: agents must track progress and learn; most platforms support short-term memory (variables, last interactions), long-term memory (files, vector, SQL, graph), and a scratchpad ("think tool"). His tip: often an agent using .md files is all you need. Step 5, orchestrate the logic: map/code repeatable logic that doesn't belong to specific agents, and orchestrate communication between agents (static or dynamic). In most cases, adding a manager or sequencing agents—sometimes with a loop—is enough; no need to study topologies.
Related event: Practical Guide to Building AI Agents: Orchestration, Memory and Tools(3 posts)→
More from coding & agent
- xbrlkit: open-source XBRL layer over Arelle with built-in MCP server support — jfrench009 · 2026-09-09
- Herdr lead agent orchestrates sub-agents with worktree and PR skills, dev ditches the GUI — iannuttall · 2026-09-09
- Session acting weird? Open a new one: practitioners' fix for momentum prior and context rot — gerardsans · 2026-09-09
- Dev Adds a Complete Tech Tree With GPT-6 Astra in 2h21m — Dimillian · 2026-09-09
- Cheap models via OpenRouter fall apart in agentic harnesses: GLM and DeepSeek can't match Claude — scottyLogJobs · 2026-09-09
- Multi-agent coding's hardest problem: deciding who is allowed to change what — apghere · 2026-09-09