> Markdown version of [/videos/2159-using-agents-to-curate-the-content-you-see-online-dan-gish?t=0](https://www.wearedevelopers.com/videos/2159-using-agents-to-curate-the-content-you-see-online-dan-gish?t=0). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Using Agents to Curate the Content You See Online - Dan Gish

Dan Gish shows how to completely bypass centralized algorithms. Deploy EvoGent, an open-source AI agent, to filter out AI slop and ruthlessly curate your custom social feed.

- **Speakers:** Dan Gish
- **Event:** Coffee With Developers
- **Published:** August 31, 2026
- **Duration:** 12:47
- **URL:** https://www.wearedevelopers.com/videos/2159-using-agents-to-curate-the-content-you-see-online-dan-gish

## Summary

Dan Gish introduces EvoGent, an open-source personal AI agent designed to reclaim control over social media feeds by filtering out platform-driven algorithms, "AI slop," and propaganda. Instead of relying on centralized curation from networks like X, Facebook, or Instagram, EvoGent empowers users to run their own custom algorithms. The system acts as a personalized content filter that can explicitly follow whitelist and blacklist rules, or autonomously evolve by observing a user's interactions and preferences to deliver a tailored timeline.

Under the hood, EvoGent employs a flexible, multi-stage pipeline of agents to avoid deterministic brittleness. It utilizes cheaper, faster agents for initial browsing and relies on cutting-edge models (like Opus 4.7) for intelligent curation. A dedicated enrichment agent specifically filters out toxic or irrelevant replies in comment sections, addressing a major pain point in modern social media consumption. Because these agents browse websites like normal users, they dynamically adapt to UI and layout changes, mitigating the traditional "Whac-A-Mole" maintenance problem associated with web scraping and API restrictions.

To lower the barrier to entry, EvoGent pioneers a novel installation method: rather than following complex manual documentation, users feed a provided instruction blob directly into their preferred coding agent (such as Claude Code), which then automates the entire setup on a local machine or a cloud VM like Hetzner. Ultimately, Gish envisions a collaborative ecosystem where users can easily share and deploy these custom curation configurations—reminiscent of sharing RSS OPML files—fostering a community-driven defense against the rising tide of algorithmic noise.

**Keywords:** evogent, personal ai agents, social media content curation, filtering ai slop, algorithmic timeline control, automated agent pipeline, autonomous web browsing agents, comment section enrichment, bypassing platform algorithms, agent-driven installation, hetzner VM deployment, claude code, opus 4.7, open source react app, sharing curation algorithms

## Chapters

1. **Introduction to EvoGent and personal curation** (00:00) — EvoGent empowers users to regain control over their social media feeds using customizable AI filtering.
1. **Setting preferences and adapting to platform changes** (01:36) — The agent learns from user interactions to filter feeds and dynamically adjusts to social platform layout updates.
1. **Open source customization and community curation** (03:47) — Users can modify the React front end and collaborate on shared filtering algorithms to combat unwanted content.
1. **Agent pipeline architecture and content enrichment** (06:42) — A multi-agent backend pipeline browses sources, curates feeds using advanced models, and filters comments.
1. **Simplifying installation and flexible hosting options** (08:37) — AI coding agents streamline the setup process, enabling users to deploy the application locally or on cloud virtual machines.

## Related Moments

- [Social networks for agents and AI slop aggregation](https://www.wearedevelopers.com/videos/1830-wearedevelopers-live-speculaitions) (from "WeAreDevelopers LIVE - SpeculAItions")
- [Exploring agentic browsers and artificial intelligence generation](https://www.wearedevelopers.com/videos/1723-wearedevelopers-live-graalvm-in-action-static-analysis-insights-and-more) (from "WeAreDevelopers LIVE - GraalVM in action, Static Analysis insights and more")
- [Evolving from generative AI to autonomous agentic AI](https://www.wearedevelopers.com/videos/1604-supercharge-agentic-ai-apps-a-devex-driven-approach-to-cloud-native-scaffolding) (from "Supercharge Agentic AI Apps: A DevEx-Driven Approach to Cloud-Native Scaffolding")
- [Publishing on the web amidst AI generated content](https://www.wearedevelopers.com/videos/1743-wearedevelopers-live-ai-vs-the-web-ai-in-browsers) (from "WeAreDevelopers LIVE – AI vs the Web & AI in Browsers")
- [Building agentic artificial intelligence applications using Node.js](https://www.wearedevelopers.com/videos/1512-building-ai-applications-with-langchain-and-node-js) (from "Building AI Applications with LangChain and Node.js")
- [Establishing an optimistic AI viewpoint for software agencies](https://www.wearedevelopers.com/videos/1316-fighting-fraud-with-an-ai-grandma-ben-hopkins-and-morten-legarth-from-faith-vccp) (from "Fighting Fraud with an AI Grandma - Ben Hopkins and Morten Legarth from faith @ VCCP")

## Related Articles

- [The Web We Broke (And Why AI Agents Are Paying the Price) - AgentCon Berlin](https://www.wearedevelopers.com/magazine/735-the-web-we-broke-and-why-ai-agents-are-paying-the-price-agentcon-berlin)
- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)
- [WebMCP: Empowering Agents as First-Class Citizens of the Web](https://www.wearedevelopers.com/magazine/696-webmcp-empowering-agents-as-first-class-citizens-of-the-web)
- [Dev Digest 207: Spring Cleaning, AI Agent Manipulation and Stopping Bad Bots](https://www.wearedevelopers.com/magazine/695-dev-digest-207-spring-cleaning-ai-agent-manipulation-and-stopping-bad-bots)

## Related Jobs

- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**
- [Staff Software Engineer, Agentic Platform](https://www.wearedevelopers.com/jobs/48464-staff-software-engineer-agentic-platform) at **Docker, Inc.**
- [Junior Engineer (AI)](https://www.wearedevelopers.com/jobs/ext/2458261-junior-engineer-ai) at **Almedia**
- [Staff Software Engineer, GitHub Intelligence (Copilot Agents)](https://www.wearedevelopers.com/jobs/ext/2650582-staff-software-engineer-github-intelligence-copilot-agents) at **GitHub**
- [Senior Software Engineer, CoPilot Agent Platform](https://www.wearedevelopers.com/jobs/ext/2211591-senior-software-engineer-copilot-agent-platform) at **GitHub**
- [Full Stack Entwickler Python und TypeScript für Agentic Workflows mit GenAI](https://www.wearedevelopers.com/jobs/ext/2389239-full-stack-entwickler-python-und-typescript-fur-agentic-workflows-mit-genai) at **Aok Systems Gmbh**