the key infrastructure for us to spawn a sandboxed container that would run an agent
MonzoPublished by the organization itself (post), no named author
Post: Building Agent Chip: Monzo's in-house agentic tool, Monzo blog, August 13, 2026.
Topics / Running AI in an organization
The environments agents work in: sandboxes, cloud machines, background jobs, chat tools.
6 passages from 5 organizations; 6 checked against the source. The page states no conclusion: these are the organizations' own words.
the key infrastructure for us to spawn a sandboxed container that would run an agent
MonzoPublished by the organization itself (post), no named author
Post: Building Agent Chip: Monzo's in-house agentic tool, Monzo blog, August 13, 2026.
Early data shows that 70% of all our in house background agents, tasks which is Minions are toil.
Abhishek TibrewalSenior Data Scientist, Platform Engineering · Practitioner,
Uber
Social post: Engineering Enablement podcast by DX (DX sells developer-productivity measurement software); recording of Uber's talk at DX Annual, Engineering Enablement podcast by DX (DX sells developer-productivity measurement software); recording of Uber's talk at DX Annual, June 22, 2026.
Builderbot is an orchestration layer that coordinates multiple AI agents across our entire codebase. It works inside Slack: anyone can tag @builderbot with a short description of what they need, and it gets to work right there in the thread, whether it’s a bug fix, a migration across services, or a new feature.
BlockPublished by the organization itself (post), no named author
Post: Block rolls out BuilderBot, a new suite of AI-native tools that changes the way we ship, Block (own site), June 17, 2026, at How it works.
Well-defined, measurable tasks run with simple Droid agents or skills. Automations coordinate recurring workflows with a shared objective and memory. Remote and persistent execution leverages Droid Computers for long running or local agents. Multi-agent autonomous execution called Missions solve complex tasks over hours or days by decomposing work into parallel tracks to handle.
FactoryPublished by the organization itself (post), no named author
Post: Factory 2.0: From coding agents to software factories, Factory (own site), June 15, 2026.
And today at Uber, one in nine of our PRs is fully production ready with zero human authoring from our background agents.
Ty SmithPrincipal Engineer, AI & Developer Productivity · Practitioner,
Uber
Social post: Engineering Enablement podcast by DX (DX sells developer-productivity measurement software); recording of Uber's talk at DX Annual, Engineering Enablement podcast by DX (DX sells developer-productivity measurement software); recording of Uber's talk at DX Annual, June 22, 2026.
simply asking Ona or the bot on my research failed, can you my analysis failed, can you tell me why? And it will just go through the entire troubleshooting process.
Xiucheng QuekSoftware engineer · Practitioner,
Genentech
Talk: Background Agents for Genomics and Cloud Ops, YouTube video of a talk or interview (speaker in notes), May 7, 2026.