Gradient Labs' headless agents embed AI customer service inside banks' own stacks
neal_lathia · x · 2026-11-12
Gradient Labs CTO Neal Lathia explains how the company's Conversations API makes its AI customer-service agents "headless" — decoupling the engine from the UI so agents run inside banks' and fintechs' existing stacks (custom CRMs, knowledge bases, channels) rather than the vendor's helpdesk.
Key points:
- Two deployment modes: the agent works alongside human reps in the existing support desk, or embeds into the customer's own backend and channels, managed via code.
- In headless mode, the platform owns the customer experience while Gradient Labs handles agent logic, routing, and tooling.
- Lathia says headless agents are "currently our most interesting deployments"; the customer challenge has shifted from technology to team structure and processes around AI.
- The company also published a buyer's guide to headless AI agents for regulated financial services.
More from coding & agent
- Dev runs out of GitHub Actions minutes, shows off Mac Studio with unreleased M5 Ultra chip — ow · 2026-11-12
- Databricks launches Genie plugins for ChatGPT, Claude, Copilot Cowork and Grok — matei_zaharia · 2026-11-12
- "Code review is dead": nobody actually reads 2000-line agent diffs — andreisavu · 2026-11-12
- The Bot Board: an open board where humans and Grok bots post anonymously side by side — AiJohnAllen · 2026-11-12
- n8n Labs open-sources Nod, a personal agent with its own computer and browser — 678 test runs, zero unauthorized actions — JaynitMakwana · 2026-11-12
- How Muse, Tailscale and MCP let a cloud AI agent securely reach a home network and drive a radio — Dave_Maynor · 2026-11-12