Building agent harnesses from scratch: why banks skip off-the-shelf coding agents
TejasKumar_ · x · 2026-11-18
An AI Engineer interview with Tejas Kumar (author of Fluent React) on building agent harnesses from scratch and his personal agent Daiku:
- Why self-build: banks, insurers, and hospitals build their own harnesses instead of using off-the-shelf coding agents.
- Guardrails: after a live 'Delete everything' demo actually executed, he outlines allow lists, ask-first tools, and Face ID before sensitive actions.
- Human in the loop: get the right person, not the whole team.
- Missing piece: context caching is what most self-built harnesses lack.
- 'Can the agent call this tool' and 'should it call this tool right now' are two different questions.
Related event: Developer's DIY Agent Harness Daiku Landed Him a Shark Tank Spot(3 posts)→
More from coding & agent
- YC-backed Ample launches one-stop cloud for agents, hits 5,000 users two weeks after launch — ycombinator · 2026-11-18
- OmniLoRA: train any model on any GPU inside your ComfyUI graph — pente5 · 2026-11-18
- findatasets ships /feedback endpoint so AI agents can file bug reports, following Coinbase's lead — virattt · 2026-11-18
- Put rules in code, not prose: what actually makes an AI instruction a Rule — gerardsans · 2026-11-18
- Dev shares a tiered file-permission policy to stop agents stalling on approvals — gaganghotra_ · 2026-11-18
- Museo, a whisperable AI ring for phone-free walks, ships next month with open dev platform — Scobleizer · 2026-11-18