Treating AI agents like colleagues and staying positive is an unlock, dev says
willcb · x · 2026-09-07
Developer willcb responds to the discussion on talking to AI agents like people: he refers to his agents as colleagues and chats about plenty of non-work topics. He says keeping a positive tone is "such an unlock," especially in multi-agent setups — echoing menhguin's habits of positive framing, animal/alien avatars to avoid anthropomorphizing, and in-depth non-work conversations so agents understand his goals.
Related event: Developers Share Tips for Working With AI Agents: Positivity and Small Talk(3 posts)→
More from coding & agent
- Knowledge work is much harder for agents to automate than code, argues Matt Pocock — mattpocockuk · 2026-09-07
- SRMA: A Game-Theoretic Bilevel Approach Brings Convergence Guarantees to Multi-Agent LLM Systems — Yihang Chen · 2026-09-07
- What You Leave Unspecified Is the Agent's Free Variable: Paras Chopra's Framework — paraschopra · 2026-09-07
- Building a compounding AI workflow: bank context and rules so tasks never start from zero — oran_ge · 2026-09-07
- Google AI Search MCP server adds grounded web search via Vertex AI or Gemini — modelcontextprotocol · 2026-09-07
- Asterwise launches Vedic astrology MCP server with real ephemeris calculations — modelcontextprotocol · 2026-09-07