Stitch embeds AI agents in banking: the safety story is harnesses, not hack-proofing
alex_verem · x · 2026-11-17
StitchHQ announced native AI capabilities for banking: a copilot that does real work, a banking-grade harness to embed your own agents, and ready-made agents that drop into existing workflows, all within bank-set limits.
alexverem adds a security angle: none of those 178 breached sites were actually broken into — a trusted vendor's script was already loaded on every page and could do whatever it liked. The lesson for banks plugging AI agents into ledgers: the point isn't preventing hacks, but ensuring agents can't run loose once inside.
More from coding & agent
- Grok Bot testing live phone call handling: type replies in chat, bot relays to caller — XFreeze · 2026-11-17
- Foaster partners with consultancy Kéa to bring agentic AI into consulting — RaphaelDabadie · 2026-11-17
- Agent Identity 101: one sequence diagram explains delegated, agent, and MCP auth patterns — adnan_hashmi · 2026-11-17
- Running Voice Agents in Production: Dev Shares 1,200 Calls/Day and 5,000 Calls/Month Setups — FullStackFrenzy · 2026-11-17
- How Comet improved a financial incident remediation agent's score from 0.34 to 0.57 with Opik — dl_weekly · 2026-11-17
- Meta's Self-Improving Memory: agents discover their own memory skills and distill them into weights — jaseweston · 2026-11-17