---
type: "post"
id: "natural-language-security-queries-at-orca-security-using-e6d046"
slug: "natural-language-security-queries-at-orca-security-using-e6d046"
title: "Natural language security queries at Orca Security using Amazon Bedrock"
description: "From language to a bounded query interface Thesis Orca’s case illustrates how a model interface becomes operationally useful when it emits a structured domain query rather than a free-form answer. The system translates natural-language questions into Sonar filters making the"
retrieval_nugget: "From language to a bounded query interface Thesis Orca’s case illustrates how a model interface becomes operationally useful when it emits a structured domain query rather than a free-form answer. The system translates natural-language questions into Sonar filters making the"
published_at: "2026-10-14"
updated_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "published_at"
topics: []
source_urls: ["https://aws.amazon.com/blogs/machine-learning/natural-language-security-queries-at-orca-security-using-amazon-bedrock"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:natural-language-security-queries-at-orca-security-using-e6d046"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:dfd871aa8dc27a9286f678f8c428c5bb570b2ad25f0d6ac569ba198c52bf8b94","reviewed_at":"2026-10-14T04:04:34.571Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Orca’s case illustrates how a model interface becomes operationally useful when it emits a structured domain query rather than a free-form answer.","observed_facts":[{"text":"Sonar covers more than 900 cloud infrastructure and application resource models and supports 18 operators.","source_urls":["https://aws.amazon.com/blogs/machine-learning/natural-language-security-queries-at-orca-security-using-amazon-bedrock"]},{"text":"The initial proof of concept used roughly 2 million input tokens per workload and took about 60 seconds; AWS says the production pipeline handles thousands of queries daily at about 15 seconds.","source_urls":["https://aws.amazon.com/blogs/machine-learning/natural-language-security-queries-at-orca-security-using-amazon-bedrock"]}],"mechanism":"Orca combines retrieval-augmented generation with schema-aware query construction in a multi-stage pipeline, matching stages to different Bedrock models. This narrows the output contract from an open-ended response to a query that can be applied to Sonar.","why_now":"The case addresses a practical interface bottleneck: analysts need to explore a complex cloud graph without learning its schema and query operators first.","implications":["The useful design move is to treat the generated query as a task interface whose validity can be evaluated against the receiving system, rather than treating fluency as success.","AWS reports 90% lower query cost, 93% fewer input tokens, and 75% lower latency versus Orca’s initial baseline."],"evidence_boundary":"These are figures in an AWS customer case study, comparing the deployed approach with the initial proof of concept; they are not independently audited results, and the supplied account does not establish production accuracy rates.","watch_conditions":["Look for published query-validity and correction rates, plus evaluation across complex multi-model questions, to determine whether the efficiency gains preserve reliable results."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied for this specific customer implementation; this opens a distinct record on natural-language-to-security-query interfaces."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/natural-language-security-queries-at-orca-security-using-e6d046/","markdown":"https://newruntime.com/posts/natural-language-security-queries-at-orca-security-using-e6d046.md","json":"https://newruntime.com/posts/natural-language-security-queries-at-orca-security-using-e6d046.json"}
---

# Natural language security queries at Orca Security using Amazon Bedrock

## Retrieval answer

From language to a bounded query interface Thesis Orca’s case illustrates how a model interface becomes operationally useful when it emits a structured domain query rather than a free-form answer. The system translates natural-language questions into Sonar filters making the

## From language to a bounded query interface

**Thesis:** Orca’s case illustrates how a model interface becomes operationally useful when it emits a structured domain query rather than a free-form answer. The system translates natural-language questions into Sonar filters, making the model output an input to an existing security data interface.

**Observed facts:** Sonar covers more than 900 cloud infrastructure and application resource models and supports 18 operators. The initial proof of concept loaded the full schema into one prompt, using roughly 2 million input tokens per workload and taking about 60 seconds; AWS says the production pipeline handles thousands of queries daily at about 15 seconds. **Mechanism:** Orca combines retrieval-augmented generation with schema-aware query construction in a multi-stage pipeline, matching stages to different Bedrock models. This narrows the output contract from an open-ended response to a query that can be applied to Sonar.

**Why now:** The case addresses a practical interface bottleneck: analysts need to explore a complex cloud graph without learning its schema and query operators first. **Implication:** The useful design move is to treat the generated query as a task interface whose validity can be evaluated against the receiving system, rather than treating fluency as success. AWS reports 90% lower query cost, 93% fewer input tokens, and 75% lower latency versus Orca’s initial baseline. **Evidence boundary:** These are figures in an AWS customer case study, comparing the deployed approach with the initial proof of concept; they are not independently audited results, and the supplied account does not establish production accuracy rates. **Watch condition:** Look for published query-validity and correction rates, plus evaluation across complex multi-model questions, to determine whether the efficiency gains preserve reliable results.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)