Skip to content

AI Intake and Justification Agent

Source: Gemini Agent Response (Internal)

To combat the “novelty effect” and ensure AI spend is a calculated investment, an Intake & Justification Agent (built on Google’s ADK - Agent Development Kit) acts as an automated “Lead Auditor.”

1. Agentic vs. Traditional Decision Matrix

Section titled “1. Agentic vs. Traditional Decision Matrix”
DimensionTraditional (RPA/Code)AI Agent (LLM)
LogicDeterministic (If X, then Y)Probabilistic (Interpretation)
DataStructured (CSV, SQL, API)Unstructured (PDF, Image, Slang)
ErrorsZero-tolerance (Financials)Context-dependent (Creative)
CostFixed, low infra costVariable, high token cost

The agent uses specific skills to conduct “anti-AI” due diligence:

  • Skill A (Context Miner): Consultative interview to identify the specific human task replaced and check if simple scripts (regex/Python) suffice.
  • Skill B (Efficiency Calculator): Uses the formula $S = (H \times R) - (T \times C)$ to estimate savings.
  • Skill C (Legacy Re-addresser): Checks Jira/GitHub to see if a solution already exists, suggesting a refactor over a new build.
  1. The Overkill Check: Would an API or better UI solve this without an agent?
  2. The Latency Tolerance: Can the process handle a 15–30 second “thinking” delay?
  3. The Longevity Test: Is this a permanent need or a 24-month critical process?
  4. The Human-in-the-Loop: Who is the “Pilot” responsible for verifying the output?

The agent outputs a recommendation (Traditional | Agentic | Refactor) with a projected burn vs. savings analysis, providing an auditable paper trail for the CIO.