Technology / WORLD

Tamnoon uses Bedrock to address cloud security findings

Tami examines findings from CNAPP and cloud security tools and coordinates fixes assessed as safe. AWS cites company data showing critical cloud exposure fell by up to 90% over 90 days.

The source does not state the event date; the period shown is the source review period.

Reading sizeSources ↓Share story ↗
Conceptual illustration of technology, processors and connected information.Illustration
Symbolic illustration

Tamnoon built Tami, an orchestrator on Amazon Bedrock, to normalize security alerts and rank them using asset context. Specialized agents investigate findings and plan fixes; each finding receives a SAFE, RISKY or AWAITING DATA label.

AWS’s October 14 case study says Tami analyzed more than 14 million alerts across customer environments and reports a reduction of up to 90% in critical exposure for a typical customer within 90 days. This is a company-reported result; AWS does not present an independent audit.

Data

Timeline

AWS technical post published

AWS described Tamnoon’s Tami cloud security remediation system on October 14.

  1. · Occurred

    AWS technical post published

    AWS described Tamnoon’s Tami cloud security remediation system on October 14.

Methodology

The date is the publication date shown by the AWS primary source; no launch or deployment date beyond the source is inferred.

Updated:

Structured coverage

Subjects and places

Subject proposals

Taxonomy version: IPTC Media Topics 2026-Q2

Continue reading

Technology

Postman details Bedrock architecture behind Agent Mode

An AWS technical post dated October 9 describes how Postman’s Agent Mode scopes tools by task, uses schema-based reads and shapes context. Postman describes its developer community as 40 million.

AWS Machine Learning Blog1 min read Data included
Technology

AWS evaluates Grok 4.7 agents on long-horizon tasks

An October 13 AWS technical post tested a tool-using agent with Grok 4.7 on Bedrock across three synthetic search tasks. Each task had one answer verified by brute force; six runs at each of four reasoning levels made 72 runs in total.

AWS1 min read Data included