--- title: Graph engineering agents description: Exploring how graph-based agent architectures are replacing manual prompting for autonomous work source: ManticsCore kind: intent_session url: https://manticscore.com/clip/s-24a62a24fbfc3bf2 --- # Graph engineering agents Exploring how graph-based agent architectures are replacing manual prompting for autonomous work # Graph engineering agents 8 sources, one thread Exploring how graph-based agent architectures are replacing manual prompting for autonomous work # Sam Altman on Prompting OpenAI CEO Sam Altman explains how to use ChatGPT better than most people do. A recording of a lecture given to Stanford students reveals new ways to interact with ChatGPT, suggesting current user methods may only be utilizing a fraction of the tool's potential. # Vercel's Internal AI Agent Guillermo Rauch introduces @v, an agent powering internal operations at Vercel. Vercel has built an internal agent called @v that is now involved in every day-to-day job at the company, seeing exponential growth in daily interactions and token usage. # Personal AI Preferences Robert Scoble explores which personal AI tools users are sticking with. A discussion on personal AI tools, noting that TownAI and Poke are currently leading the preference for some users. **Current Mentions** - TownAI - Poke # Grok Bot Is Running 6 Employees For Me "HOLY F**K, ELON GROK BOT IS RUNNING 6 EMPLOYEES FOR ME AND I HAVEN'T TYPED A PROMPT IN 11 DAYS" — @SpikeCalls claims to have built a company running inside Grok instead of using it as a simple search bar. **The 6 Agents** - Research - Writing - Outreach - Ops - Finance HOLY F**K, ELON GROK BOT IS RUNNING 6 EMPLOYEES FOR ME AND I HAVEN'T TYPED A PROMPT IN 11 DAYS 6 agents: research, writing, outreach, ops, finance, ## Related reading - [OpenAI (@OpenAI) on X](https://x.com/OpenAI/status/2061845950705140121) — x.com - [Ed Zitron (@edzitron) on X](https://x.com/edzitron/status/2085066310338421174) — x.com sharing a recent breakthrough in harness architecture i achieved with @pidotdev this is not a common problem but it happens when your agent starts to handle loops that would fire events from the background. e.g. the agent is babysitting a PR, and it checks every 5 minutes # Andrew Ng: Building Agentic Knowledge Graphs from Scratch A tweet from Anatoli Kopadze highlighting what he calls the best 2 hours on graph engineering ever recorded — Andrew Ng breaking down how to build agentic knowledge graphs from scratch. **Video Timestamps** 1. 9:14 - your first working agent 2. 33:11 - how loops actually work 3. 1:02:46 - turning loops into working graphs 4. 1:30:15 - agents that improve Shared on X by Anatoli Kopadze, this post points to a long-form video/session where Andrew Ng walks through constructing agentic knowledge graphs step by step, from a first working agent through to loops, graph construction, and self-improving agents. Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Full interactive version: https://manticscore.com/clip/s-24a62a24fbfc3bf2