POX AI STACK

Simulate. Score. Inspect the evidence. The stack behind every Ready call.

Why simulation

From interview answers to interaction evidence.

A good simulation should reveal behavior that a normal interview hides. In sales, customer success, recruiting, support, and operational roles, performance depends on how a person responds to incomplete information, conflicting incentives, and live feedback.

Traditional interviews tend to compress those conditions into hypothetical questions. The candidate explains what they would do, the interviewer interprets the answer, and the organization later discovers whether the answer predicted work.

PoX AI changes the unit of assessment from an answer to an interaction. The candidate is asked to perform inside a simulated business situation: qualify a buyer, handle objections, protect trust, explain tradeoffs, prioritize next steps, or coordinate a decision among multiple stakeholders.

Each exchange becomes a trace. The transcript shows what was said. The agent state shows what pressure was introduced and how the candidate held up when the scenario became more difficult.

Architecture

Separate the simulation from the score.

Layered responsibilities.

The upper layer produces the simulated world and buyer committee. The middle layer performs model reasoning under controlled prompts and state constraints. The lower layer captures the transcript, maps observed behavior to a rubric, and keeps the evidence behind every score.

Inspectable scoring.

Every scored claim points back to a transcript segment or scenario event. When a reviewer disagrees with a score, they can inspect the evidence rather than seeing only a final number.

Inside the stack

Four layers. One scored conversation.

Each layer has a single job. Together they turn a live exchange into structured evidence your hiring manager can defend.

The PoX AI stack

Scenario Graph Engine

A branching state machine builds the scenario and decides how it unfolds. It ramps difficulty, opens objection paths, and remembers what was committed earlier, so the situation reacts to how the candidate performs instead of following a fixed script.

State machineBranchingDifficulty rampObjection pathsScenario memory

Reasoning Models

Frontier language models provide the adaptive reasoning layer. They operate as controlled personas with scenario constraints, rubric boundaries, and conversation-state memory.

GPTClaudeRubric judgeScenario controller

Agent Simulation

A multi-persona buyer committee creates pressure, ambiguity, interruptions, and conflicting priorities. The candidate is evaluated against how they discover information, manage stakeholder tension, and turn a simulated conversation into an evidence-bearing interaction.

CFOVP SalesProcurementIT DirectorEnd User

Embedding top-seller calls

Every call and meeting is embedded with Gemini Embedding 2 and indexed for semantic retrieval. Top-performing conversations become a searchable corpus that surfaces the patterns behind best-seller outcomes.

CallsMeetingsBest sellersSearchableVector index

Scoring

Every score points back to behavior.

The scorecard surfaces concrete behavior in reviewer language. A useful AI assessment makes it easier for humans to compare what happened, not harder by hiding the judgment behind a generic number.

Discovery discipline

What it catches

Question sequencing, explicit hypothesis testing, and the ratio of follow-up questions to generic prompts.

What it means

High scores indicate that the candidate forms a useful model of the buyer instead of performing a scripted checklist.

Stakeholder navigation

What it catches

Treatment of conflicting incentives across finance, technology, procurement, and end-user personas.

What it means

High scores indicate that the candidate can hold multiple constraints in the same conversation without flattening them into one answer.

Evidence quality

What it catches

Specificity of claims, requested proof, acknowledgment of uncertainty, and correction after challenge.

What it means

High scores indicate that the candidate anchors the interaction in observable facts rather than confident but unsupported statements.

Searchable corpus

Embed every call. Search the best ones.

Every call and meeting in the platform is embedded with Gemini Embedding 2 the moment it ends. Transcripts and scoring evidence become vectors in a shared index, not isolated recordings.

Top-seller conversations are tagged at the source, so a query like "how the best reps handle a procurement objection" returns the actual moments behind the outcome instead of a summary.

Employers search prospects across the full PrompX database and hire the best, comparing candidate simulations against the closest reference calls from real winners. Scoring stops being abstract and starts pointing at the patterns that produced revenue.

PoX AI embedding system: video, image, sound, score, and text flowing into a vector store with insights as the output.

See how they sell before you hire.

Tell us the role, the buyer, and the skills that matter. We'll build a sales simulation that shows who can ask, explain, handle objections, and move the conversation forward.