Engineer Wraps MCP Calls in LangGraph to Fix Slow, Non-Deterministic Agent
colinmcnamara · x · 2026-11-10
Joseph Fluckiger's fraud agent originally ran on a single 2,000-line prompt with some 30 tools. It was slow — a single run could take four minutes — and non-deterministic.
His fix: a LangGraph flow where plain code turns raw MCP calls into just the signal the agent needs, making runs much faster and more deterministic.
Related event: Engineer Rebuilds 2,000-Line Prompt Fraud Agent with LangGraph for Speed(2 posts)→
More from coding & agent
- NODES 2026: 100+ sessions, but devs should filter for Text2Cypher, entity resolution and quantization — JeremyCMorgan · 2026-11-10
- A One-Person AI Company in Hong Kong Staffed by a Team of Grok Bots — AIFlow_ML · 2026-11-10
- Astral open-sources serc under new astral-experiments org for agent-authored projects — charliermarsh · 2026-11-10
- Astral's serc: Codex-built Rust CPython bytecode compiler, byte-identical and 2-4x faster — charliermarsh · 2026-11-10
- Sentry CEO shares hands-free AI game dev progress: auto-added wildlife shaders at 82fps — zeeg · 2026-11-10
- Anthropic's official guide: when to use Fable 5.2, Opus 5.5, Sonnet or Haiku — ClaudeDevs · 2026-11-10