Non-tech colleagues commit AI features with unrealistic timelines
kmeanskaran · x · 2026-09-25
kmeanskaran describes a common pain: product and sales people commit features with two-day timelines assuming AI works like generating an image in ChatGPT.
- AI speeds up development, but shipping new functionality fast remains unhealthy — especially for agents
- Multi-agent orchestration, prompting, and retrieval require extensive testing across varied queries before system behavior is known
- Real-world experience: retrieval fetches the right resources, yet contradictory answers and mismatched figures still surface, demanding back-and-forth iteration
- Fixes for one query type must not break others; even using Astra and Fable together demands heavy experimentation
- Constraints around sessions, tokens, cloud auth, and repeated verification are invisible to business stakeholders
The author asks how others manage this expectation gap.
Related event: Engineers suffer as non-technical colleagues promise AI-speed delivery(2 posts)→
More from coding & agent
- Devin launches a redesigned home page for its AI coding agent — DevinAI · 2026-09-25
- Blender agent skill turns concept art into rigged game assets — one user shipped a Mario 64-style game in 8 hours — majidmanzarpour · 2026-09-25
- Open Manager for ComfyUI adds desktop mode for Vast.ai and other cloud GPU services — WASasquatch · 2026-09-25
- Block joins x402 Foundation, contributes Lightning payments for agentic commerce — kleffew94 · 2026-09-25
- Stripe engineer answers 'what's it like at Stripe' with demos over memos culture — schwentker · 2026-09-25
- Wasmer runs a real PostgreSQL 18.4 server on iOS and in the browser via WebAssembly — jedisct1 · 2026-09-25