Parallax Advanced Research Independent Research and Development (IR&D)


PHOENIX (An AI-Enabled Analytic Engineering and Requirements Management Platform) is a Parallax Independent Research and Development (IR&D) capability that transforms Priority Intelligence Requirements (PIRs) into structured, verifiable, and auditable analytic workflows. It operationalizes Structured Analytic Techniques (SATs) by decomposing Commander questions into Essential Elements of Information (EEIs), measurable Indicators, and Specific Information Requirements (SIRs)—creating transparent traceability between evidence and assessment.

PHOENIX —an AI-enabled analytic platform that integrates Large Language Models (LLMs) into the intelligence requirements workflow to improve how organizations define, structure, and answer operational questions.


Who It Serves

PHOENIX supports intelligence analysts, requirements managers, and Intelligence, Surveillance, and Reconnaissance (ISR) operators responsible for developing, decomposing, and managing PIRs across operational, strategic, and tactical levels. It also serves Air Operations Center (AOC) leadership, planners, and Commanders who require timely, defensible assessments and the ability to inspect how conclusions were derived.


Why It’s IR&D and Why It Matters

PHOENIX addresses a persistent operational gap: many current tools store requirements and products, but few enforce disciplined decomposition from Commander intent to collectible, measurable requirements—creating risk from bias, incomplete indicator identification, inconsistency across rotations, limited traceability, and difficulty identifying intelligence gaps. As IR&D, PHOENIX matures a digitally enforced reasoning process that improves analytic rigor, transparency, and repeatability for high-consequence decisions in Joint All-Domain Command and Control (JADC2) contexts.


How It’s Being Researched and Delivered

PHOENIX functions as a software-based analytic augmentation layer for AOC and requirements environments, structuring work through the hierarchy PIR → EEI → Indicator → SIR and linking intelligence products directly to the EEIs and Indicators they satisfy. The platform incorporates Large Language Model (LLM) support in a Human-on-the-Loop configuration to improve requirement decomposition, identify gaps, and provide active red-teaming feedback for bias, ambiguity, and logical breaks. It also supports confidence modeling and a feedback loop between intelligence producers and requirement originators.

Our Impact

  • PHOENIX strengthens analytic rigor by enforcing a transparent decomposition chain from Commander questions to measurable, collectible requirements—making analytic logic inspectable and repeatable.
  • It reduces operational risk by mitigating bias and mirror imaging, improving indicator completeness, and increasing analytic consistency across analyst rotations.
  • It improves decision advantage by providing auditable traceability from assessments to evidence, quantifiable confidence based on indicator coverage, and earlier identification of intelligence gaps and flawed reasoning.

Core Capabilities

  • Analytic engineering and requirements management: turns PIRs into structured, inspectable workflows with auditable evidence chains.
  • SAT digitization: embeds SAT methodology directly into the analytic process to enforce disciplined decomposition before assessment.
  • AI-assisted requirement decomposition: LLM-enabled support to identify missing EEIs and Indicators and improve question quality.
  • Active analytic red teaming: real-time detection of bias, ambiguity, and logical gaps in requirement formulation.
  • Confidence modeling and traceability: evidence-weighted aggregation from Indicators to PIR-level assessments; direct linkage between products, EEIs, and Indicators.
  • Intelligence-cycle feedback closure: structured feedback to validate whether products satisfy the originating PIR and diagnose gaps when they do not.


Key Contributors