Background Agents
Focusasynchronous, cloud-delegated agents; managing fleets of parallel agents; issue-to-PR pipelines and triggers from Slack, Linear, and GitHub.
You buildAn issue-to-PR flow with isolation, budgets, checkpoints, and retries
Core material≈ 3 h 30 min
- 1The productsCodex cloudOpenAI
; Anthropic, Claude Code on the web; Cursor, Cloud Agents; GitHub, Managing issues and pull requests with the Copilot coding agent (≈ 20 min each; compare their trigger, isolation, and approval models).
- 2Orchestration case studyOpen-sourcing SymphonyOpenAI
And the Symphony specification (≈ 60 min) — issue-to-PR orchestration as a specification.
- 3Video37 minCloudflare's AI Engineering Stack: Assisted to DelegatedRajesh Bhatia of Cloudflare
How Cloudflare moved from assisted coding to delegated agents on its own platform.
- 4Durable execution15 minScaling AI Agents Without Breaking ReliabilityPreeti Somal of Temporal
Persistent state, orchestration, visibility, automatic recovery, human interaction, and parallel work.
- 5Fleet operations9 minI Run a Fleet of AI Agents Across Three Machines: Here's What BrokeKyle Jaejun Lee
Attention limits, durable context, blocking approvals, routing, conflicting work, and multi-machine recovery.
Tools and references
- LinkCode Mode: give agents an entire API in 1,000 tokensCloudflare
A tool-efficiency technique for fleets.
Additional video track
- Build your own harness1 h 52 minClaude Agent SDK: Full WorkshopThariq Shihipar of Anthropic
The SDK that Claude Code itself runs on, for building a custom background agent.
- Infrastructure economics1 h 23 min; the relevant chapters are long-running agents at `05:32`, the inference stack at `15:12`, throughput versus latency at `20:03`, and transformer hardware at `33:19`Why AI Is About to Get 1000x CheaperNeil Movva
. Treat “1000x” as an ambition, not a demonstrated forecast.
Build
Build an issue-to-pull-request background flow. Each job gets an isolated worktree or container, a strict budget, a checkpoint, deterministic validation, and a resumable state. Add retries with bounded backoff and prevent two agents from editing the same work item simultaneously.
Run three jobs in parallel: a small feature, a bug fix, and a documentation task. Interrupt one midway and demonstrate that it can resume or fail cleanly. Agents may open pull requests; only a human may merge.