{
  "id": 10118345,
  "title": "It Looked Finished on Day One",
  "url": "https://urgent.news/2026/09/27/it-looked-finished-on-day-one",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-09-27T02:36:30.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/henry_dan_81513dd35a2f540/it-looked-finished-on-day-one-4k0j"
  },
  "original_language": "en",
  "account": "The FORGE app, a dashboard for AI agents, was initially a simulation with no real agents. This early version featured a workflow canvas, live event stream, timeline, replay scrubber, agent counters, and cost monitors. Behind the scenes, a simulator produced fake events to display on all screens. One crucial design decision was that each screen was computed from a log of events, not an updating record.\n\nWhen real agents replaced the simulator, the screens remained unchanged, as they all displayed the same events. The app began with three agents: a researcher, a writer, and a reviewer. The researcher used the GLM-5.3 Flash model from OpenRouter, costing $0.15 per million input tokens. The writer and reviewer used free tools like DuckDuckGo and Claude.\n\nDuring initial testing, calls to the models frequently timed out due to Node.js's default 250-millisecond attempt limit. The fix involved preferring IPv4 addresses and extending the attempt time to three seconds. Some model replies were empty because the model had exhausted its output budget. The researcher continuously researched until it hit the step limit, resulting in incomplete notes. Each tool result also displayed the remaining rounds, forcing the researcher to write up its findings once the limit was reached.\n\nReal agent implementation revealed additional issues. The run history contained sample runs, not actual data, creating confusion. Simulated data needed clear labeling to differentiate it from real data. The server now maintains a single SQLite database, eliminating per-browser local storage conflicts, and issues unique run IDs to prevent data overwriting. The reviewer proved to be the most expensive component, with Claude Sonnet offering the best balance of accuracy and cost.",
  "summary": "I wanted a team of AI agents that could answer a research question the way a small team of people would. One plans the work, one searches the web and reads the sources, one writes it up, and one checks the write-up before I see it. I also wanted to watch them do it: which agent is working, what it's reading, what it handed to whom, and what it cost. The app is called FORGE, and it runs on a small…",
  "key_points": [
    "FORGE app initially simulated AI agents with fake events",
    "Three real agents: researcher, writer, reviewer",
    "IPv4 and extended attempt time fixed model timeouts"
  ],
  "editors_take": "The FORGE app's design decision to compute screens from a log of events, not updating records, allowed a seamless transition from simulated to real agents, revealing key issues to address.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}