---
title: 'In the News: September 16, 2026'
description: "Swan's own account of its autonomous bug-fix pipeline: agent consensus voting, a human gate on agent memory, and skills built from accumulated evidence."
canonical_url: 'https://darkfactory.dev/news/2026-09-16-evening'
markdown_url: 'https://darkfactory.dev/news/2026-09-16-evening.md'
collection: news
date_published: '2026-09-16T19:20:00-04:00'
date_modified: '2026-09-16T19:20:00-04:00'
---

# In the News: September 16, 2026


Swan says agents now produce the vast majority of its code. Its Cygnet pipeline uses parallel investigators for bug triage, requires human approval before writing to shared agent memory, and promotes lessons into reusable skills only after evidence accumulates from multiple sources.

## 1. Swan says agents now produce the vast majority of its code

**[Swan's Agentic Software Factory: Cygnet Evolved](https://x.com/skwp/status/2100300329883664782)** · Yan Pritzker, co-founder and CTO, Swan · X, September 16, 2026

Pritzker walks through a single incident from July 9, when a partner's webhook sent a burst of events that broke a database job. A Cygnet job queried Datadog on its own, found the burst, and opened a ticket with its query, the time window, and a guess at the cause. Three investigator agents then reran that evidence in parallel. Two reached the same root cause and the third dissented, and all three write-ups went onto the ticket. A separate group of agents proposed a fix, and a human approved the resulting spec by adding a label. The pipeline opened a pull request that afternoon and tried to prove the fix worked by driving the change through a real browser in an offline environment. That proof run failed, so a human took over, reproduced the bug locally, confirmed the fix, and merged it.

The system puts two controls on agent memory. Memory writes triggered by a "remember this" Slack reaction require a human reply before anything is stored because, Pritzker writes, "memory poisoning can lead to security issues or worse outcomes." A lesson only gets promoted from an internal note into a shared, agent-loadable skill after evidence accumulates from multiple sources, though a single correction is enough to flag a problem: "when someone says 'no, not like that,' we don't need to wait for it to happen again." Swan reports going from zero agent-authored commits two years ago to what it calls the vast majority of its code today, and says ten people with no prior engineering background are now shipping code through a paired onboarding program called Wingspan.

**Why it matters:** Swan separates immediate corrections from durable agent memory. A human approves every shared-memory write, and repeated evidence is required before a lesson becomes a standing skill. Those controls address the risk that one interaction could alter future agent behavior. The commit and headcount figures are Swan's own account, with no outside audit.