How to use Unknown to draft a novel with gollem
A gollem author-bot generated The Year Unedited through chained planning, continuity checking, and iterative drafting; the author treated it as an orchestration test.
news.ycombinator.comPrompt to try
Editorial adaptation, not the source author’s exact prompt. Replace bracketed inputs and review tool permissions first.
Using gollem, build an author-bot pipeline for [novel premise]. Chain chapter planning, continuity checking, and iterative drafting, passing each stage into the next. Generate [chapter target] and provide the manuscript for human assessment of character voices and plot continuity.
Reach people exploring AI agents
See placements →What happened
The author reported about 40,000 words across 11 chapters in about ten minutes and judged the novel surprisingly coherent as an orchestration stress test.
Reported by helsinki on Hacker NewsHow the agent did it
- Point the author-bot at generating an entire novel.
- Plan chapters using chained agent stages.
- Check continuity and iteratively draft through the pipeline.
Where a person stepped in
The author assessed coherence and published the novel; the post does not describe manuscript editing or formal review.
A person set the goal and reviewed the result.
The author built gollem, a Go agent framework, and used novel generation to stress-test its orchestration. The framework supports structured output, multiple providers, MCP integration, and multi-agent team swarms. For this experiment, an author-bot generated a complete novel rather than tackling a production software task.
The bot used chained agents for chapter planning, continuity checking, and iterative drafting. Its orchestration.ChainRun pipeline passed each stage's output into the next. The author reported approximately 40,000 words across 11 chapters in about ten minutes. The resulting novel, The Year Unedited, used a dystopian memory-editing premise.
The author's assessment was that the text was surprisingly coherent: characters retained distinct voices across chapters, plot threads mostly held together, and the ending did not neatly resolve everything. They explicitly stopped short of calling it good literature and framed the output as a stress test for long-running orchestration. They placed the novel on Amazon as an experiment. The post does not identify the specific provider used for this run or describe editing the manuscript.
Who it's for: Agent-framework developers testing whether a staged pipeline can maintain continuity across a long creative output.
Prompt
Suggested prompt (written by Agents In Use, not the author's)
Source: Hacker News · helsinki
Frequently asked questions
Which model provider generated the novel?
The excerpt lists supported providers for gollem but does not identify which provider powered this novel run.
How did the author assess the result?
They reported distinct character voices and mostly coherent plot threads, while explicitly declining to call it good literature.
More details
Remaining steps
- Publish the resulting novel on Amazon as an experiment.
About this account
The author-bot used chained planning, continuity checking, and iterative drafting to generate a full novel.
Platform: Hacker News. Attribution: https://news.ycombinator.com/item?id=47284403. Prompt: Suggested (written by Agents In Use, not the author's). Sourced by the Agents In Use pipeline.
Credit: helsinki on Hacker News
Source published 7 Mar 2026
Source checked 14 Oct 2026
Tools and topics
gollem · Go · orchestration.ChainRun
Agent workflows
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.