Idea Summary

Don't just generate an answer. Generate the proof.

Standard AI offers a "black box" probability. The Double-Sided Context Graph delivers Auditability by Design, validating the source behind every decision and driving toward a Pink Team decision.

Problem Statement:
Data Rich, Context Poor

1. The Manual Scramble

The moment a new RFP is released, we need to identify win themes and compliance obligations immediately. In practice, the first days are spent simply hunting across Salesforce, SharePoint, and tribal memory just to assemble context.

2. The "Blind" AI Trap

Standard RAG automation fails because it lacks discernment. To a vector database, a 10-year-old resume is treated with the same weight as a signed contract. It cannot distinguish a "Claim" from "Evidence."

Standard RAG Pipeline
Legacy Mode

Vector Database

Ingests all documents equally. No concept of time or truth.

Old RFP (2020)Resume (Unverified)

Semantic Search

Retrieves chunks with high keyword similarity.

Match: "Senior Architect" found in Old RFP

LLM Output

Synthesizes answer based on retrieved chunks.

MATCH FOUNDConfidence: 98%

"Candidate is a perfect match based on the requirements."

The Context Graph
Context-Aware

Temporal Check

Req 1.0: Generic CertReq 1.2: AWS Pro (Amendment 02)

Ontology Normalization

Mapping terms to Concept ID: 101

RFP: "AWS Pro"
Resume: "Solutions Architect (Pro)"

Provenance Check

Source: ResumeClaim: Pro (Matches Concept 101)
Source: Cert DBEvidence: Associate Only

Compliance Decision

REJECTED

Evidence (Associate) contradicts Claim (Pro).

The Solution:
The Context Graph

We reject the concept of static truth. By separating Data from Context, we validate the two variables that actually matter in procurement: Time and Provenance.

Time (The "When")

Amendments supersede original requirements. We track the active state of every rule.

Ontology (The "What")

AI-assisted normalization bridges the gap between different terms (e.g., "AWS Pro" ≈ "Solutions Architect") to prevent false negatives.

Provenance (The "Who")

Claims are weighed by their evidentiary context. We prioritize corroborated records over unverified assertions by analyzing the full chain of custody.

Proposed Solution & Architecture

Step 1: Temporal Context

The Demand Plane: Time-Aware Requirements

Government procurements are chaotic. Requirements change via Amendments, and ambiguities are resolved via Q&A. We reify "Time" to treat the RFP not as a static file, but as a stream of evolving atoms.

Day 1RFP Released
RFP-2026-C4

Requirement C.4

"Senior Architect with Generic Cloud Certification"

Day 8Clarification
Q&A-Log-102

Vendor Question

"Does 'Generic' accept Azure?"

"No, must be AWS."

Day 15Amendment 02
AMD-02-C4
ACTIVE

Superseding Text

"Senior Architect with AWS Professional Certification"

Current Truth
Day 1 / 30
Paused
Step 2: Semantic Bridge

The Ontology Bridge: Pollution Control

Different documents use different words for the same concept. We use AI-assisted normalization to map messy language to a controlled concept graph, preventing "near-miss" hallucinations.

Unstructured Token Stream
NORMALIZING...
Senior Cloud Architect
Concept ID: 101
Senior Cloud Architect
Satisfies Requirement
Related Concept ID: 202
Related Concept
Does Not Satisfy

One Concept, Many Names

The RFP asks for a "Senior Cloud Architect." Your best candidate, Sarah, lists "Principal AWS Lead" on her resume. Different words, same job. A keyword search misses her entirely.

Our Semantic Bridge separates exact matches, directional implications, and related-but-not-sufficient concepts. "Principal AWS Lead" implies the capability of a "Senior Cloud Architect" in this domain, but the reverse is not true.

RFP
Requirement
"Senior Cloud Architect"
RES
Candidate
"Principal AWS Lead"
...both ID as... Unified Concept 101
Match ✅
VS. NEAR MISS
REL
"Cloud Infrastructure Lead" Adjacent role
Concept 202 No ✗
Step 3: Provenance Context

The Supply Plane: Evidence Over Claims

Resumes are claims, not facts. The context graph attaches provenance so verified sources carry greater evidentiary weight than unverified assertions, classifying claims into explicit trust tiers.

RESUME
Source: Upload
Claim: AWS Pro
Candidate: Sarah
Entity ID: 8842
AWS Associate
RECENT SOW
Source: Statement of Work

Silver Tier — The Claim

Resume: “AWS Professional”

The system ingests the resume as a distinct source node. It records the text "AWS Professional" but tags it as unverified claim data.

Gold Tier — The Evidence

Recent SOW: “AWS Associate”

A recent statement of work is treated as verified evidence. When higher-trust evidence conflicts with lower-trust claims, the evaluation logic weights the evidence based on provenance.

Step 4: Auditability

Auditability by Design: The Chain of Evidence

In regulated industries like GovCon, the "why" is more important than the "what". A standard AI tells you "Sarah is a match." Our Context Graph provides the Traceability, Version Control, and Risk Mitigation required to defend that decision— driving directly toward a Pink Team decision.

STEP 1
Context Engine
Analyzing evidence...
STEP 2
Policy Gate
DISCREPANCY FLAGGED
STEP 3
Human Auditor
Final Decision

Compliance Alert: Candidate #8842

Resume claims AWS Pro but verified source indicates AWS Associate.

Approve Hazard
Reject Candidate

Traceability

"We rejected this candidate because verified certification (Source: Database) does not meet criteria." Every decision is linked to an immutable source record.

Version Control

"We evaluated against Amendment 02, not the original RFP." The system never validates compliance against dead requirements.

Risk Mitigation

Contradictions are surfaced, not suppressed. The system explicitly flags discrepancies to the Human Auditor before a risk can become a liability.

Conclusion

Value & Impact: Meeting the Challenge

The challenge asked for an AI capability to assess bid viability, staffing, and win probability—The "Pink Team" MVP. The Double-Sided Context Graph is not just an abstract architecture; it maps 1-to-1 with the project deliverables.

Automated Bid Indicators & Win Guesstimate

Instead of a "vibe-based" prediction, the Graph calculates PWin (Probability of Win) by normalizing historical data—past submissions, wins, and project performances.

  • The Mechanism: Overlays current requirements on the Supply Graph while benchmarking against this normalized historical dataset.
  • Early Warning Radar: Flags missing mandatory requirements (e.g., "Top Secret Facility Clearance") as Critical Risks for immediate review.

Personnel Assignment & Risk

The "Sarah" scenario scaled up. We calculate a Confidence Score for each candidate based on evidentiary weight.

  • Probabilistic Staffing: Gold (Verified SOWs), Silver (Resumes), Bronze (Inferred).
  • Risk-Aware Gap Analysis: Empowers the Proposal Manager to weigh internal candidates vs. subcontracting costs based on verification level.

SWOT & Win Themes

Comparative analysis against the Demand Plane.

  • Strengths: Areas where verified past performance exceeds customer thresholds.
  • Weaknesses: Areas relying on unverified claims or identified gaps.
  • Competitor Analysis: Ingests public competitor data into the Reference Ontology for direct SWOT comparison.

The Pink Team Deliverable

Because the Context Graph is structured data, the final output is a document, not a chat message.

  • The system exports the Compliance Matrix, Staffing Plan, and Gap Analysis directly into the "Pink Team" template.
  • This automates the first 48 hours, moving the team immediately from "Reading" to "Strategy."

Turning Vision Into a Buildable Path

The Double-Sided Context Graph is more than a narrative—it is an architectural blueprint for safe, scalable AI. We have moved beyond simple prompt engineering to define the structures, responsibilities, and risk controls required to turn a conceptual idea into a deployable solution.

Data Sovereignty

By decoupling the Context Graph reasoning engine from underlying data sources, the solution can be seamlessly ported between different organizational tenants. This ensures strict data residency within local cloud environments (Azure or AWS), without sensitive proposal data ever leaving the tenant boundary.

Global Scale, Local Governance

Because Maximus operates globally, this portability is non-negotiable. Unlike opaque SaaS AI wrappers, this architecture allows us to lift-and-shift the entire reasoning capability to where the data lives—respecting local governance while leveraging global intelligence.