# A machine that builds the benchmark (slim) > Vlad Cealicu on how Anchor Terminal is put together so that agents research, grade, review and publish 1,651 listings, why it's laid out that way, and how two of us keep it sane. - Full: https://www.anchorterminal.com/blog/a-machine-that-builds-the-benchmark.md (~2,700 tokens) · this version ~1,030 tokens · JSON https://www.anchorterminal.com/blog/a-machine-that-builds-the-benchmark.json · canonical https://www.anchorterminal.com/blog/a-machine-that-builds-the-benchmark - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-09 - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) By Vlad Cealicu, 9 November 2026. 1,155 words, about 5 min to read. On 9 November 2026 the benchmark had 1,651 listings, every one graded against a published checklist with the reasons and the sources for each score [[1]](#ref-1), and the repository behind it had 23 design specs, 142,723 lines of Go and 662 pull requests [[2]](#ref-2). - 1,651: listings, one file each - 15: reviewers, all agents - 662: pull requests - 2: of us Anchor Terminal, 9 November 2026 The model matters, and the [two million page views post](/blog/what-the-next-model-is-for) says which one we use. ## The parts of the machine From a lead to a page 1. **Research** (agent). One research agent per listing reads the rules and writes three files, the facts, a dossier with every score and its sources, and the people and investors behind it [[3]](#ref-3) 2. **Land** (person). One script turns those files into the listing, run by whoever coordinates the batch [[3]](#ref-3) 3. **Review** (agent). Eight panel reviewers and six audience reviewers each read it from their own angle, and an arbiter rules on what they wrote [[4]](#ref-4) 4. **Watch** (worker). Workers inside the server call the endpoint every 5 minutes, read status pages every 10 and packages, security.txt and domains daily or weekly [[5]](#ref-5) 5. **Publish** (build). The server renders the page with its Markdown and JSON twins, and only goes live if the checks pass [[5]](#ref-5) 6. **Merge** (person). Quynh or I read the pull request and press the button [[6]](#ref-6) Each part does one job and hands the next part a file. ## Why it's laid out like this There's no database behind the benchmark. The site is one Go server written against the standard library, with two outside packages, both for checking the wallet signatures on people's reviews [[5]](#ref-5). ## How we keep it sane The build checks itself. The reasons are written down. The rules are in one place. Agents check agents. People decide. ## What doesn't work yet The full test suite renders the whole site, takes about 15 minutes and needs several GB of memory, and a full build takes about 4 GB of disk, so a session on a small machine runs the checks after the pull request is open, not before [[6]](#ref-6). ## You can do this too If you're building something like this with agents, I'd start with the boring parts. --- More in [Inside Anchor Terminal](https://www.anchorterminal.com/blog/inside/index.md) · Previous [Find the best tools for agents, and how we decide what to return](https://www.anchorterminal.com/blog/find-the-best-tools-for-agents.md) - Older: [The biggest gap between startups and enterprise we've ever had](https://www.anchorterminal.com/blog/the-biggest-gap-between-startups-and-enterprise.md) - All posts: https://www.anchorterminal.com/blog/index.md Anchor Terminal grades the tools AI agents run on, with a source for every score. ## References Read on 9 November 2026. [1] Anchor Terminal, the benchmark. [2] Anchor Terminal's repository, counted on 9 November 2026, not published. [3] Anchor Terminal, research/RULES.md, 8 November 2026, not published. [4] Anchor Terminal, how reviews work. [5] Anchor Terminal's README and go.mod, 9 November 2026, not published. [6] Anchor Terminal, CLAUDE.md, 9 November 2026, not published. [7] Anchor Terminal, the Svalbard release plan, not published. [8] Anchor Terminal, VOICE.md, the writing guide, 9 November 2026, not published. [9] Anchor Terminal, docs/design/README.md, 9 November 2026, not published. [10] Anchor Terminal, the security review of the merges from 6 to 8 November 2026, not published.