From PM to AI Builder: Treat Your Agent Like Your Engineering Team
brandon_galang · x · 2026-10-15
A PM-turned-AI-builder shares how managing a remote engineering team in China—deep async communication via Jira comments, Slack, and PRDs, pre-empting missing context to avoid 12-24h round trips—shaped how he works with agents.
His framework for agent communication:
- Treat your agent like your eng team
- Explain the problem; give relevant context and constraints upfront
- Make room for questions, like a good tech lead clarifying details
- Confirm you're solving the same thing before going too far
Core thesis: working well with agents is a transfer of async remote collaboration and requirement-communication skills.
More from coding & agent
- DuoDiscover Tackles the Evaluation Bottleneck, Claims 2.68x TPU Kernel Gains — stanfordnlp · 2026-10-15
- Claude autonomously coded for 16 hours straight and shipped a perfect implementation — Atlan_ · 2026-10-15
- Gemini 4 Argon runs overnight on Google's 205k-line ADK repo, cuts session overhead 40% — leslysandra · 2026-10-15
- Every publishes 'How Codex Happened': inside OpenAI's coding comeback with Codex — every · 2026-10-15
- PMs should build more themselves: how agents collapsed weeks of design into hours — thechrisperry · 2026-10-15
- Dev uses Claude and Codex to decompile, modify and recompile old Windows apps — mobileraj · 2026-10-15