MoreProofCase Study: Agentic RAG

Transition Readiness Agent

A state-managed, multi-source RAG pipeline synthesizing signals from 8+ enterprise systems to prepare CSMs for seamless, auditable customer transitions.

System: multi-source synthesis

Input fragmentation

The handoff existed across systems, not in one usable view

When Professional Services finished onboarding, CSMs had to reconstruct objectives, commitments, sentiment, and risk before they could take responsible ownership of the account.

That reconstruction duplicated work, produced inconsistent transition messaging, and allowed hidden risks to surface only after the moment for proactive intervention had passed. The problem was not missing data. It was evidence without a governed sequence.

Fragmented evidence

Signals lived across Salesforce, Gong, Zendesk, Totango, Jira, and linked documents rather than in one dependable handoff.

Governed access

Customer data required role-aware access and PII controls; a useful brief could not expose raw source material indiscriminately.

Workflow latency

A briefing had to complete in under 15 seconds to remain viable in a live customer-success workflow.

Operational scale

The system had to serve 1,200+ accounts without trading away grounding quality.

Governed state machine

Every transition has a named state and an exit condition

The architecture moved away from one opaque synthesis prompt and toward explicit retrieval, extraction, synthesis, and validation states.

Ingest account context

Parallel retrieval gathers opportunity data, conversation signals, support history, and open delivery risks under the user's existing access.

Extract the contract

Given an Opportunity ID, a dedicated step locates the linked SOW and Order Form, parses contractual details, and returns a strict JSON payload.

Synthesize the brief

The orchestrator resolves the inputs into confirmed objectives, current health, known risks, and alignment gaps — a brief a CSM can inspect rather than a raw transcript dump.

Gate the outcome

Faithfulness is scored against a golden dataset before delivery or CRM write-back. Failed checks route to human review instead of passing uncertain output downstream.

Design decision

Reliability was worth 200 milliseconds

The initial monolithic prompt hit context limits, hallucinated edge cases, and returned inconsistent structures. Moving to strict state transitions and JSON contracts cost roughly 200ms per briefing; in exchange, grounding accuracy measured against the golden dataset improved 40%, and hallucinations fell to near-zero in the production workflow.

Inspectable brief

The output shows its shape before asking for trust

The CSM receives a structured account view with objectives, health, risks, gaps, and the control state that determined whether the brief could be delivered.

Each briefing separates confirmed objectives from inferred risk, carries forward the source context needed for review, and exposes whether the faithfulness gate passed. The receiving CSM starts with a usable transition package instead of reconstructing the account from raw records.

Measured result

Earlier warning with stronger grounding

The production workflow improved the timing, adoption, and reliability of account handoffs.

14 Days

Earlier warning window for renewal-risk accounts

40%+

Adoption growth before the workflow became the standard handoff path

<2%

Hallucination rate across 1,200+ generated briefs

Evidence summary

Transition Readiness Agent

The role, constraints, design judgment, and operating evidence behind the result.

Role: Defined the evaluation harness and retrieval strategy, integrated output into daily CS tools, and established prompt/quality monitoring frameworks.
Constraints: Joined disconnected sources, respected governance and PII controls, operated under a sub-15-second briefing target, and served 1,200+ accounts.
Judgment: Replaced a monolithic prompt with a state-managed, multi-step agent chain and explicit validation gates.
Evidence: The existing state-managed orchestration diagram depicts ingestion, contract extraction, synthesis, and a quality gate.

My role

Sole architect and builder

I defined the evaluation harness, designed the RAG retrieval strategy, and integrated the final output into the CS team's daily operational tools. I also established the prompt libraries and quality-monitoring framework behind that adoption growth.

Connected systems: Salesforce / Gong / Totango / Zendesk / Jira / Google Drive / Confluence
Control patterns: State-managed orchestration / SOQL retrieval / Strict JSON contracts / Role-aware access / Faithfulness scoring / Human review

Optional walkthrough

Explore the operating model

A scripted simulation shows how the retrieval, readiness, and briefing stages coordinate without standing in for the historical production result.

Interactive model

Transition briefing route

See how retrieval, readiness checks, and structured briefing stages coordinate across connected systems.

Open the transition workflow simulation

Systems modeled

Salesforce / Totango / Zendesk / Gong / Provisio / Google Drive / Slack

Scripted with illustrative data. The walkthrough explains the operating sequence and does not display customer records or live system activity.

Back to All Work

Technical Deep Dives

Requirements & Acceptance Criteria