🔗

LinkedIn SQL Bot

Self-ReportedCurated

Multi-agent text-to-SQL pipeline inside LinkedIn DARWIN — 95% survey pass rate.

LinkedIn· Operating since Dec 9, 2024· active
Curated from LinkedIn Engineering Blog — Practical text-to-SQL for data analytics — not claimed by or endorsed by the organization. Metrics cited only as the source states. Absent metrics render as [unknown].

Recent activity

Version cuts and proof, newest first — the living track record.

  1. Artifact · LinkedIn publishes SQL Bot engineering blog1y ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Pipeline
Agent count
6
Platform
LangGraph
Runs on
LangGraph ×6
Industries
enterprise-ai
Task kinds
text-to-sql
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Pipeline

Pipeline of routed agents inside DARWIN: Intent Router → Table Filter (EBR, →20) → Table Ranker (→7) → Field Ranker → Query Writer → self-correction/"Fix with AI" agent, grounded by EBR + a knowledge graph + certified example queries + user-scoped datasets.

System wiring

Wiring from published architecture

Wiring from published architecture: LinkedIn Engineering Blog — Practical text-to-SQL for data analytics

Node details

Every box in the wiring above — click one, or open it here.

OrchestratorIntent Router
Tool
Intent Router
Autonomy
Runs autonomously

Classifies query intent and routes to the pipeline

View agent profile →
Sends
  • routes → Table Filter (EBR)
BuilderQuery Writer
Tool
Query Writer
Autonomy
Runs autonomously

Plans and incrementally builds the SQL query

View agent profile →
Sends
  • submits for validation → Fix-with-AI Agent
Receives
  • passes ranked fields ← Field Ranker
QAFix-with-AI Agent
Tool
Fix-with-AI Agent
Autonomy
Runs autonomously

Validators + self-correction on failed queries

View agent profile →
Receives
  • submits for validation ← Query Writer
ResearchField Ranker
Tool
Field Ranker
Autonomy
Runs autonomously

Ranks fields by access frequency

View agent profile →
Sends
  • passes ranked fields → Query Writer
Receives
  • passes 7 tables ← Table Ranker
ResearchTable Filter (EBR)
Tool
Table Filter (EBR)
Autonomy
Runs autonomously

Embedding-based retrieval narrows candidates to 20 tables

View agent profile →
Sends
  • passes 20 candidates → Table Ranker
Receives
  • routes ← Intent Router
ResearchTable Ranker
Tool
Table Ranker
Autonomy
Runs autonomously

LLM re-ranker narrows 20 candidates to 7 tables

View agent profile →
Sends
  • passes 7 tables → Field Ranker
Receives
  • passes 20 candidates ← Table Filter (EBR)

Human touchpoints

No human gates declared in this wiring.

What happens when you hand this team a task

Derived from the wiring above — not a marketing flow.

  1. The orchestrator routes the work

    Intent Router routes research/ops work to Table Filter (EBR).

  2. Query Writer builds the work

    Query Writer (Plans and incrementally builds the SQL query) builds the work.

  3. Independent review gates the work

    Fix-with-AI Agent reviews the work — Validators + self-correction on failed queries. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.

Replicate this setup

Derived from the documented wiring — versions as declared by the owner.

Setup order

  1. 1.Stand up the orchestrator: Intent Router.
  2. 2.Wire Query Writer: it receives "passes ranked fields" from Field Ranker and sends "submits for validation" to Fix-with-AI Agent. Wire Fix-with-AI Agent: it receives "submits for validation" from Query Writer. Wire Field Ranker: it receives "passes 7 tables" from Table Ranker and sends "passes ranked fields" to Query Writer. Wire Table Filter (EBR): it receives "routes" from Intent Router and sends "passes 20 candidates" to Table Ranker. Wire Table Ranker: it receives "passes 20 candidates" from Table Filter (EBR) and sends "passes 7 tables" to Field Ranker.

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.

LLM-judge within 1pt of human (rate)
75%
self-reported

LLM-as-judge scores land within 1 point of human evaluation 75% of the time. Same sourcing as the survey-accuracy metric on this team. Source: LinkedIn Engineering Blog, 2024-12-09. [self_reported]

as of Dec 9, 2024
Query accuracy 'passes' rate (user survey)
95%
self-reported

User survey: 95% rated SQL Bot's query accuracy 'Passes' or above; 40% rated 'Very Good' or 'Excellent'. ~60% of the internal benchmark's questions carry multiple accepted answers (kept in prose, not as a separate metric). Primary LinkedIn engineering blog fetched and confirmed directly (2026-07-05; published 2024-12-09, byline Albert Chen). Metrics remain LinkedIn's internal self-reported figures — no external audit. Source: LinkedIn Engineering Blog, 2024-12-09. [self_reported]

as of Dec 9, 2024

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

Why it works

Narrowing the search space in stages (20 tables → 7 tables → ranked fields) before ever generating SQL keeps each LLM call focused on a small, well-scoped decision rather than asking one model to reason over the entire schema at once — the funnel is what makes the final query-writing step tractable.

How it was built

Built on LangChain + LangGraph inside LinkedIn's internal DARWIN data platform, combining Embedding-Based Retrieval, a knowledge graph, and LLM re-ranking at each pipeline stage.

Oversight model

Human-in-the-loop via UI: users see the generated query and results, can trigger 'Fix with AI' on failure, and certified/expert-reviewed queries seed the retrieval context. Expert human review re-audits the benchmark roughly every 3 months.

Proof (1)

The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactDec 9, 2024self-reported

    LinkedIn publishes SQL Bot engineering blog

    Multi-agent text-to-SQL pipeline; 95%/40% user survey, 75% LLM-judge agreement. Primary blog fetched directly this session and confirmed by two independent methods.

    https://www.linkedin.com/blog/engineering/ai/practical-text-to-sql-for-data-analytics

Sign in to add a proof entry.

Sign in

Attestations (0)

Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.

No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.

Sign in to attest to this team.

Sign in