4.9/5 on Clutch — 13 verified reviews
Industry3PL Logistics & Warehousing
DeliveredText-to-SQL & Knowledge Retrieval AI
Data Scope4 Databases · 207 Tables
Query Accuracy90%+ on Plain-English Questions

Ask Your Database
In Plain English

Extensiv's warehouse platform runs on 207 tables across four databases: shipping, billing, inventory, operations. Reading it required SQL. Kodexo Labs built the AI layer that lets any operator just ask, and get a governed, accurate answer back.

EExtensiv AssistantLive · read-onlyInstant
Which fulfillment centers had the highest return rate last quarter?
reading 207 tables, live…
Two fulfillment centers stood out this quarter:
Fulfillment Center A6.8%
Fulfillment Center B6.1%
Illustrative example · 3-5s
Ask anything, in plain english
Top SKUs by returnsOpen orders this week
100%
Accuracy on Simple-to-Moderate Queries

The bar the agentic pipeline hits before expanding scope

207
Tables Across 4 Databases

Shipping, billing, inventory, and operations, now reachable in plain English

70%
Of Core Queries Covered

By the initial rollout, before wider schema expansion

About the client

The Operational Backbone Behind 1,500+ 3PL Providers

Extensiv (formerly 3PL Central) has built cloud-based warehouse management software since 2006. Its products, 3PL Warehouse Manager, Order Manager, and Integration Manager, cover the fulfillment lifecycle from shopping cart to doorstep, serving over 1,500 third-party logistics providers and processing more than one million orders every week.

The platform connects to Shopify, WooCommerce, Amazon, and Magento, plus leading ERPs, shipping carriers, and accounting systems, making it a central nervous system for modern logistics operations, and its underlying data one of the most valuable and complex assets in the business.

The challenge

Great Data, Locked Behind a Language Only Engineers Spoke

Extensiv's own engineers had started building text-to-SQL capability. It worked, until the questions got real. Four problems stood between an early experiment and something operators could trust.

01SQL Accuracy Broke Down on Complex Joins+

Simple queries ran fine, but questions needing three or four table joins produced SQL that was valid syntax but wrong logic, pulling in far more rows than intended.

02The Schema Was Too Big to Hand the AI+

With 207 tables, there was no way to show the model the whole database at once, and no way, yet, to automatically show it just the tables a given question needed.

03Two Kinds of Questions, One Pipeline+

Some questions need live numbers from the database; others need an answer from policy documents and help content. Nothing decided which was which.

04No Guardrails for What Comes Next+

Read-only queries were low-risk, but Extensiv's roadmap includes letting the AI take actions. Raw, AI-written SQL with write access was not a risk worth taking.

"The raw SQL generation from the LLM works well on simple elements, but sometimes we would get syntax errors or different issues as they got larger. We need the LLM to understand the concept of not wanting to bring in additional records. What's the right table to look at, not bringing in multiple different tables."

Brant Snow, Extensiv

The solution

A System That Decides How to Answer Before It Answers

Kodexo Labs built the AI layer around a LangGraph orchestration engine, a workflow coordinator that reads every question, decides what kind of question it is, and routes it down the right path before a single answer is generated.

Operator asks
Plain-English question
LangGraph node 1
Intent Classifier
Data question
SQL Expert Pipeline
Live database answer
Help question
Knowledge Expert Pipeline
Documentation answer

A single, lightweight AI call classifies each question the moment it arrives, keeping the extra step fast while making sure every question lands in the pipeline built to answer it correctly.

Data questions · SQL Expert Pipeline

Instead of Asking the AI to Write SQL Blind, It Plans First

Letting a model generate SQL end-to-end against 207 tables is how the fan-out and join errors happened in the first place. The pipeline instead breaks the job into four narrower stages, each one checked before the next begins.

STAGE 1

Plan & Extract Tables

The question is broken into logical parts, and a dedicated module identifies only the tables relevant to it, out of 207.

STAGE 2

Prune the Schema

Only the schema for those tables is retrieved, then trimmed further to the relevant columns: a focused context, not the whole database.

STAGE 3

Generate & Validate

The AI writes SQL against that narrow schema. If it fails validation, the error is fed straight back to it until the query is correct.

STAGE 4

Aggregate & Format

Once executed, raw database rows are turned into a plain-English answer shaped around the operator's original question.

Swipe →

A collaborative innovation

Extensiv had independently built a "canonical intent engine" that turns questions into structured JSON before writing SQL. Kodexo Labs ran it head-to-head against this agentic pipeline on identical query sets: the canonical approach won on governance and security, the agentic pipeline won on complex joins and dynamic schemas, pointing toward a hybrid of both.

Help questions · Knowledge Expert Pipeline

Answers Grounded Only in What's Actually Written Down

Questions about policies, business rules, or how the platform works don't need a database. They need Extensiv's own documentation, retrieved and checked for relevance before an answer is written.

01

Hybrid Search

Keyword (BM25) and semantic search run together via Pinecone, catching both exact terminology and conceptual questions.

02

Query Fan-Out

Multi-part questions are split into sub-questions, each retrieved in parallel, then merged into one complete answer.

03

CRAG Check & Rephrase

Retrieved documents below a 0.7 confidence score are discarded; a rephrasing agent retries the search until confidence holds.

04

Re-Rank & Order

A Cohere cross-encoder re-ranks results, placing the strongest documents first and last, where models pay the most attention.

Swipe →

The CRAG evaluator's discard-and-retry loop is what keeps the assistant from ever answering with a guess: if the documentation doesn't support an answer, the system keeps searching rather than filling the gap itself.

Data & security layer

Every Answer Passes Through Governance Before It Reaches Anyone

Read-only queries today; write access on the roadmap. The guardrails were built for both from day one.

Question inAnswer out
01

Input Sanitization

Every question is screened before processing to block prompt injection and protect system integrity.

02

Query Governor

An output filter validates generated SQL against governance rules, keeping every query read-only and unauthorized writes off the table.

03

Auth & RBAC

AWS Cognito handles authentication; role-based access control governs exactly which data and actions each user can reach.

04

Audit Logging

Every query, classification decision, and database interaction is logged for compliance and debugging.

Swipe →

Results & impact

From an Engineering Bottleneck to a Question Anyone Can Ask

90%+

Overall SQL query accuracy, up from ~75% baseline

85%+

RAG answer accuracy, up from 70%

3–5s

Average query latency, down from 5–8s

207

Tables across 4 databases now reachable in plain English

Accessibility

Warehouse operators, account managers, and analysts now reach operational data directly, removing the wait on engineering for ad-hoc requests.

Security Posture

The canonical intent layer and query governor give enterprise-grade governance, ready for write operations when the roadmap calls for them.

Trustworthy Answers

The CRAG evaluator grounds every knowledge answer in retrieved documents, virtually eliminating hallucinated responses.

Built to Scale

Separate pipelines for data and knowledge queries mean new capabilities can be added without re-architecting the core system.

The complete picture

One Question, Start to Finish

Every piece covered on this page, in the order it actually runs: from the moment someone types a question to the moment a checked, governed answer comes back.

1
Someone asks a question, in plain English
No SQL, no training. Just typed into the assistant like a chat message.
2
The Intent Classifier decides what kind of question it is
A quick check: does this need live numbers, or does it need documentation?
3
Data question
SQL Expert Pipeline
Plans, finds the right tables, writes and validates SQL, then reads the live database.
Help question
Knowledge Expert Pipeline
Searches documentation, checks confidence, and re-ranks the best matches.
4
Every answer passes through governance before it's shown
The query governor confirms it's read-only, access rules are checked, and the interaction is logged.
5
A clear, plain-English answer comes back
Formatted around the original question, in seconds. No engineer required.

Why Kodexo Labs

Production-Grade AI, Built With the Client Rather Than For Them

Deep AI/ML Engineering

Production experience with LangGraph, RAG systems, and text-to-SQL pipelines: systems that run reliably, not just prototypes.

Collaborative Problem-Solving

Rather than prescribing a solution, the team evaluated approaches and compared results with Extensiv's engineers to reach the architecture together.

Full-Stack System Design

From API gateway and authentication through orchestration and data security: a complete, production-ready architecture.

Evidence-Based Development

Every architectural decision was backed by comparative testing and real query results, tuned to Extensiv's own data.

Swipe →

Questions we get asked

What Teams Ask Before They Build This

Ready to Make Your Data Speak Your Language?

Whether you're in logistics, manufacturing, healthcare, or any data-intensive industry, Kodexo Labs can help you build intelligent, natural-language interfaces to your most critical systems.

Book a Discovery Call