Signal SentrySearchUpdated Nov 20, 05:30 UTCAM Drop
Agents · industry

Agents in Financial services

Agent deployments and launches in Financial services, from the Drops.

From the Drops

AgentsFinancial servicesLiveHuman in loop: unclear

Duco cut agent context from 200,000 to about 20,000 tokens by loading tools on demand

AWS says Duco, which serves 200+ financial clients, exposed 300–400 tools per tenant, filling context before work began. Three meta-tools now find, load and call tools only when needed; AWS reports better answer quality.

Why it matters: Large MCP tool catalogs can quietly degrade agents. Measure tool-description tokens per session and, as Duco did, run evals before deciding an agent has gotten worse.

On the Frontier watch →From Drop #091 · Tue, Nov 17, 2026 · Morning
AgentsFinancial servicesLiveHuman in loop: yes

TCS says its agentic test orchestrator cut test effort 88% on about 100 scenarios

In a controlled internal benchmark, TCS says about 100 BFSI test scenarios took roughly 24 hours with its AgentCore-based agents versus about 200 hours by hand. A deterministic supervisor routes work, and fixes get bounded retries.

Why it matters: A pattern worth copying: split testing into narrow agents, cap retries and reject oversized fixes. The numbers come from TCS's own benchmark on one workload.

From Drop #079 · Wed, Nov 11, 2026 · Morning
AgentsFinancial servicesLiveHuman in loop: unclear

Stripe says 83% of staff use its Kai agent weekly, built on Deep Agents in one week

In a LangChain post, Stripe says one engineer built Kai's first version in a week, and users grew from 296 to over 5,000 in roughly 4 weeks. The team saw frontier models degrade past 150 skills with its system prompt.

Why it matters: Skill count is a limit to plan for: Stripe lets the skills an agent picks decide which of its 500+ tools load, and says it will need a prefilter as the catalog grows.

From Drop #077 · Tue, Nov 10, 2026 · Morning
AgentsFinancial servicesLiveHuman in loop: yes

Greenlight says its SOC agents resolve over 90% of up to 4,000 monthly cases on their own

Greenlight Financial says in an AWS post that Luna runs more than 30 specialized agents under two supervisor tiers; a feedback loop on past case outcomes lifted autonomous resolution from 83 percent.

Why it matters: A pattern for regulated teams: Luna triages and recommends, while a person or an approved policy carries out any fix. Start with one bounded case type and escalate hard cases with evidence.

From Drop #071 · Sat, Nov 7, 2026 · Morning
AgentsFinancial servicesLiveHuman in loop: unclear

Banks and retailers are blocking personal agents like Muse, CNBC reports

CNBC reports JPMorgan, Schwab, Amazon, Neiman Marcus and Kohl's block personal agents like Meta Muse. An audit of 51 big U.S. retailers by Billions Network found 37 block shopping agents mostly by accident, via old bot rules.

Why it matters: If your product sends agents to shop or bank for users, check target sites' bot rules first: many block agents by default, and none in the audit lets a verified agent check out.

From Drop #060 · Sun, Nov 1, 2026 · Evening
AgentsFinancial servicesLiveHuman in loop: unclear

Zafin reports 38% less effort from governed agent workflows in its own codebases

In a preprint case study on two production codebases, Zafin's authors say its AIOS control plane cut effort 38% on a pricing platform and reporting work 76% on a deal platform, keeping privacy, access and audit guardrails.

Why it matters: Real numbers from regulated finance, but the vendor is measuring its own platform, and the authors call the results descriptive.

From Drop #049 · Tue, Oct 27, 2026 · Morning
AgentsFinancial servicesLiveHuman in loop: yes

Two Sigma, Anthropic and Bloomberg share how they put controls around finance agents

Latent Space reports from AI Engineer New York: Two Sigma uses classifiers that send people only key requests, Anthropic showed an agent that proposes order fixes for approval, and Bloomberg urged audit trails and kill switches.

Why it matters: Practical patterns for agents near money: put deterministic checks outside the model and save human sign-off for consequential actions.

From Drop #025 · Thu, Oct 15, 2026 · Morning
AgentsFinancial servicesLiveHuman in loop: unclear

Apate runs about 350,000 AI bots that keep scammers talking, Wired says

Apate's CEO tells Wired its bots, used by banks, answer scam calls, texts and chats, and have gathered more than 250,000 pieces of fraudster data. An ETH Zurich researcher says LLM honeypots hold AI attackers longer.

Why it matters: Defenders can turn agent tech on attackers, wasting their time and collecting intelligence for banks and telecoms.

From Drop #016 · Sat, Oct 10, 2026 · Evening