Maslow AI
LET’S TALKLET’S TALK
Case Studies / Enterprise AI Hub
CASE STUDYHEALTHCARE ENTERPRISEAGENTHUB

An enterprise prompt library with a contract-review system.

Built for a global healthcare company's internal innovation program under the Maslow AI brand: a department-organized prompt library backed by a Statement-of-Work review system with graph retrieval, field-level citations, and structured answers.

7
generative-UI widgets available for structured responses
DEPLOYED CLIENT IMPLEMENTATION
93%
expected first-tool routing on a 28-case live test suite
DEPLOYED IMPLEMENTATION TEST RESULT
50
SOW corpus, chunked by document structure
DEPLOYED CLIENT IMPLEMENTATION
11
departments in the curated prompt library
DEPLOYED CLIENT IMPLEMENTATION
EXECUTIVE SUMMARY

The case in four decisions

Waiting work
Knowledge workers lacked a shared prompt library and a fast way to review dense Statements of Work with traceable source fields.
What changed
A department prompt library and SOW reviewer now combine vector and graph retrieval, structured response tools, and field-level citations.
Human decision
Procurement and legal reviewers inspect cited source fields and decide whether drafted answers or documents can move forward.
Evidence state
The deployed implementation and 26-of-28 first-tool routing result are documented implementation evidence. Adoption and business-impact measurement are still in progress.

CLIENT DELIVERY JOURNEY

How a shared prompt library became a deployed review system

This progression covers the deployed client implementation and keeps the first-tool routing test separate from answer accuracy and business outcomes.

Skip the guided view
0101 · PROBLEM

Reviewed prompts and contract knowledge had no shared home

Knowledge workers needed one place to find working prompts and a faster way to review dense Statements of Work with traceable source fields.

Responsible owners
Innovation, procurement, and legal reviewers
Waiting work
Contract questions, comparisons, and drafted sections
Required evidence
Source fields a reviewer can inspect

ResultThe engagement joined discovery and review in one experience.

CLIENT PROBLEM

0202 · BUILD

The team connected retrieval, routing, and structured responses

Maslow built an 11-department prompt library with a 50-SOW corpus, parallel vector and graph retrieval, field-level citations, and seven structured response widgets.

Knowledge
Structure-aware contract ingestion and retrieval
Workflow
Deterministic intent-to-tool routing
Review
Visible activity and source paths

ResultThe system was deployed for the client's internal innovation program.

DEPLOYED CLIENT IMPLEMENTATION

0303 · DELIVERED

The live pipeline selected the expected first tool in 26 of 28 cases

The 92.9% result, displayed as 93%, measures expected first-tool selection through the live streaming pipeline. It is one routing test for this implementation.

26 / 28
Cases with the expected first tool
7
Structured response widgets
50
SOWs in the current grounded corpus

ResultThe deployed implementation demonstrates routing and review controls against its current corpus.

DEPLOYED IMPLEMENTATION TEST RESULT

0404 · REMAINING

Accuracy, adoption, and business impact require separate evidence

The routing test does not establish answer correctness, citation accuracy, retrieval quality, unseen-query reliability, legal accuracy, organization-wide adoption, or business impact.

Answer quality
Outside the first-tool routing test
Adoption
Measurement remains in progress
Business impact
No outcome percentage is claimed

ResultThe next review should measure the decisions and work products the system supports.

MEASUREMENT IN PROGRESS

Map a document workflow
THE CHALLENGE

The product needed to support two jobs

Enterprise knowledge workers had no shared home for reviewed prompts, and no fast, trustworthy way to interrogate dense Statement-of-Work documents. "What are the termination terms?" meant an afternoon of reading. "Where's the duplicate-spend risk across these vendors?" meant nobody checked.

AgentHub combines a curated prompt library, organized by department, with an SOW review system grounded in the source documents.

THE EXPERIENCE

A prompt-library front door with a grounded review engine

THE FRONT DOOR
Department prompt library
Eleven color-coded departments, live search, likes and comments, public/private prompts, per-author categories. Every prompt opens straight into the AI chat; the library is how people discover what the review system can do.
MarketingLegalR&DFinanceSupply Chain+6 more
THE ENGINE
SOW review system
Ask a contract corpus questions in plain English (“compare the day rates across these SOWs”) and get grounded answers with citations to the exact field in the source document, via parallel dense-vector and knowledge-graph retrieval.
▸ VECTOR SEARCH · top-5 · 3072-dim embeddings▸ KNOWLEDGE GRAPH · entities + one-hop neighbors▸ CITATIONS · down to the exact jsonPath field
DEEP DIVE · HYBRID RAG

From 50 contracts to field-level answers

Parallel dense-vector and knowledge-graph retrieval, fused as grounded context. Drafted document sections can cite the exact source field. If the graph is unavailable, retrieval degrades gracefully to vector-only.

EXPLORE THE SIX-STEP RETRIEVAL PIPELINEHIDE THE SIX-STEP RETRIEVAL PIPELINE
01INGEST
Structure-aware chunking
Contracts follow their document structure during chunking, with breadcrumb metadata (section path and field names) preserved on every chunk.
02EMBED
3072-dim embeddings
Each chunk is embedded and stored behind a native vector index: cosine similarity over the full corpus.
03RETRIEVE ×2
Two legs in parallel
Dense vector search (top-5) runs alongside a knowledge-graph query for matching entities (vendors, clients, deliverables) plus their one-hop neighbors.
04FUSE
Grounded context fusion
Both result sets enter the prompt as labelled context sections, each vector hit carrying its similarity score and source path.
05GENERATE
Multi-step response loop
The model answers in a multi-round tool loop, streaming tokens, reasoning and widgets live over server-sent events.
06CITE
Field-level citations
Drafted documents cite per-section back to the exact field of the source SOW, auditable by a procurement or legal reviewer.
EXAMPLE TELEMETRYA data-source badge can show a vector result count and top score or a graph entity count. The Activity Panel displays retrieval searches, tool rounds, and source paths during a review.
DEEP DIVE · INTENT ENGINEERING & GENERATIVE UI

The review system selects what kind of response to give

Every message is routed through a deterministic intent layer: tool request, document drafting, data-heavy, narrative, off-topic or conversational. That classification gates which tools the model is offered. Conversational turns keep chart tools unavailable.

EXPLORE RESPONSE ROUTING AND TOOL EXAMPLESHIDE RESPONSE ROUTING AND TOOL EXAMPLES
SEVEN WAYS TO ANSWER
show_chartBar, line, area and pie charts in brand colors
show_data_tableSortable column/row comparisons
show_statsKPI grid with deltas and trend arrows
show_planVertical stepper with task states
show_optionsClickable choices that feed back into the chat
ask_questionsMulti-step clarifying wizard before drafting
generate_documentEditable sectioned docs with per-section citations
LIVE TEST RESULT
26 / 28
Cases routed to the expected first tool through the live streaming pipeline (92.9%).
“put the comparison in a table” → show_data_table
“draft a PRD” → ask_questions first, then the document
“what's the weather in Boston?” → text only, no tool
REVIEW CONTROLS

Traceable implementation controls for human review

REVIEW CONTROLS IN THIS IMPLEMENTATION
✓Visible retrieval record: the Activity Panel displays retrieval steps, tool calls, and source paths
✓Field-level citations: auditability that procurement and legal reviewers can check
✓Graceful degradation: if the graph is unavailable, the system records a vector-only fallback
✓Tool availability control: function-calling disabled for conversational turns
✓Routing regression coverage: the 28-case intent test suite plus browser test specs, run against the live pipeline
EXPLORE THE IMPLEMENTATION STACKHIDE THE IMPLEMENTATION STACK
UNDER THE HOOD
Frontend: React + TypeScript, Tailwind, assistant-ui with a custom streaming runtime, Recharts
Data: Convex reactive DB with native vector index · Neo4j knowledge graph · Clerk auth with post-sign-in intent replay
AI: Gemini 3 Flash (chat, thinking, tool-calling) · gemini-embedding-001 at 3072 dimensions · optional MCP tool discovery at runtime
Delivery: serverless; the whole chat/RAG/tool loop runs as one streaming action
The system provides field-level citations for graph-augmented SOW review and uses intent routing to select response tools. Dense and graph retrieval are combined into one context packet; the intent route uses deterministic orchestration.
HOW IT WAS BUILT · DEPLOYED IMPLEMENTATION

The demonstrated components in shared language

This map is scoped to components demonstrated in the deployed AgentHub implementation. Open the optional detail to compare the responsibilities.

VIEW THE DEPLOYED ARCHITECTURE MAPPINGHIDE THE DEPLOYED ARCHITECTURE MAPPING
Work arrives

Channels + triggers + schedules

A chat request enters the live streaming pipeline with its task intent.

Build the briefing

Context + session and durable memory

Vector and graph retrieval assemble cited contract context.

Apply the procedure

Skills + orchestration

Deterministic intent routing governs the multi-round tool loop.

Use approved capabilities

Tools + connectors + delegation

The classified request gates which response tools are available.

Return the result

State + trace + checkpoints

The Activity Panel exposes searches, tool rounds, and source paths.

EXPLORE THE SHARED INFRASTRUCTURE  >
SERVICES USED

This engagement, as catalog services

Knowledge foundation buildCustom workflow systemSkills authoringTeam enablement
MASLOW DELIVERY SUMMARY
The prompt library is the front door. The engineering story is a contract-review system that shows its sources, down to the exact field.
Deployed client implementation · 11-department library · 50-SOW corpus · adoption metrics in progress

Have documents your teams are afraid to ask questions of?

We build grounded, citable review systems within the agreed data and access boundary.

TALK THROUGH A WORKFLOW
← Infinite AI OSAll case studies