🇮🇳 Made in India, for the world
🇮🇳 Made in India, for the world
Our SLM (Small Language Model)

A small language model built deep, not wide.

Not a general-purpose LLM with a compliance prompt bolted on. ReQL's Small Language Model starts deeply grounded in Indian BFSI regulation — with every answer traceable back to the circular, clause, and date it came from — and is built to extend the same approach across industries and geographies over time.

Regulatory
SLM
RBI
SEBI
MCA
IRDAI
FEMA
Ind-AS
CBDT
ICAI
0
Indian regulators & standard-setters covered
RBI · SEBI · MCA · IRDAI · FEMA · CBDT · CBIC · Ind-AS · ICAI
0+
RBI Master Directions ingested & indexed
RBI 2024
0
Corpus start year — continuously updated to present
ReQL bench · ReQL corpus
0%
Outputs required to carry a source citation
ReQL bench · Product invariant
Vision & mission

Why we're building this.

Vision

A world where no financial institution — however small, however remote — is one missed circular away from a compliance failure. Where regulatory knowledge isn't locked inside a handful of expensive consultants and legal teams, but available instantly, accurately, and in plain language to whoever needs it.

Mission

To build the regulatory intelligence layer for Indian BFSI — starting with a language model that actually understands how RBI, SEBI, MCA, and IRDAI regulation is written, cross-referenced, and amended, and that never answers a compliance question without showing its source.

Why an SLM, not an LLM

Narrow domain. Deep coverage. Every answer cited.

General-purpose LLMs know a little about everything. A domain SLM is built the opposite way — and for regulated work, that matters more than raw parameter count.

Dimension
General LLM
ReQL SLM
Training corpus
Broad web + books
Indian regulatory corpus, 2021 → present
Answers without source
Common
Blocked by design
Amendment tracking
Snapshot at training
Continuous — ingested as regulator publishes
Deployment
Vendor cloud
Self-hostable inside your perimeter
Optimised for
Everything, generally
Regulatory Q&A, gap analysis, clause diff
The corpus underneath

What the model actually reads.

Every clause is chunked, embedded, and stored with its citation metadata intact — regulator, circular number, section, and effective date.

0+
RBI Master Directions ingested
0
Sections of the Companies Act, 2013
0+
SEBI regulations (LODR, ICDR, PIT, MB, AIF …)
0
Corpus start year, updated continuously

RBI · MCA · SEBI 2024  Public statute and regulator counts.

How we're training it

Small, deep, and grounded — not big and general.

A general-purpose LLM knows a little about everything. Our SLM is built the opposite way: narrow domain, deep coverage, and a hard requirement that every claim traces to a source document.

1

Corpus ingestion

Circulars, master directions, and amendments from RBI, SEBI, MCA, ICAI, CBDT, CBIC, FEMA, Ind-AS, and IRDAI, structured from 2021 to present.

2

Structured indexing

Every clause is chunked and embedded with its citation metadata intact — regulator, circular number, section, and effective date.

3

Domain fine-tuning

The model is tuned specifically on regulatory Q&A, gap analysis, and clause comparison — the actual tasks compliance teams perform daily.

4

Citation-grounded evaluation

Every output is scored not just on correctness, but on whether it cites the right source — answers without a valid citation are treated as failures.

Grounded, not generative

Every answer either finds a source, or admits it can't.

A model tuned on a fixed corpus doesn't need to guess. On our internal regulatory-Q&A eval set, the SLM either returns a valid citation or explicitly declines.

General LLM — invents plausible rule
62%
General LLM — cites but wrong source
18%
ReQL SLM — cited, correct source
94%
ReQL SLM — explicit 'no source found'
6%

ReQL bench · Internal eval  Measured on ReQL's regulatory-Q&A eval set; representative, not audited.

How it learns

Training is the start. It keeps learning after that.

The corpus doesn't go stale and the model doesn't stay static — both update on a continuous loop, fed by new regulation and by how compliance teams actually use it.

1

New circular published

A new circular, amendment, or master direction is picked up as soon as the regulator releases it.

2

Ingested and cross-linked

It's chunked, cited, and cross-referenced against every existing clause it amends or supersedes.

3

Reviewed by compliance officers

Where an answer is corrected or flagged by a real user, that correction feeds back into evaluation.

4

Model re-evaluated

Accuracy and citation quality are re-scored against the updated corpus before anything ships to users.

What this makes possible

Why a narrow, grounded model beats a bigger one here.

01

No hallucinated compliance advice

A general LLM will confidently invent a plausible-sounding rule. A model grounded in a fixed corpus either finds the source or says it can't find one — there's no in-between.

02

Keeps up with amendments, not just headlines

Indian regulation moves in circulars and master direction updates, not press releases. A domain-specific model is built to track that granularity continuously.

03

Self-hostable, because compliance data is sensitive

A smaller model can run inside your own perimeter — no policy document or client contract needs to leave your infrastructure to get an answer.

04

Deep before wide

Every design decision — from corpus selection to evaluation criteria — starts from how RBI, SEBI, and IRDAI actually publish and structure regulation. Depth first is what makes expansion into new industries and geographies reliable later, not a rewrite.

Where this goes next

Deep in Indian BFSI today. Built to go wider from here.

The corpus, the citation engine, and the evaluation approach are all built to generalize — the roadmap is to extend the same grounded, cited approach to new industries and new geographies, not to rebuild it from scratch each time.

1

Now — Indian BFSI

RBI, SEBI, MCA, ICAI, CBDT, CBIC, FEMA, Ind-AS, and IRDAI, covering banks, NBFCs, fintechs, and insurers.

2

Next — more industries

Extending the same corpus-and-citation approach to sectors beyond BFSI as the model architecture generalizes.

3

Then — new geographies

Applying the same training methodology to other regulatory regimes, starting where demand is clearest.

4

Vision — cross-industry, cross-border

One grounded, citation-first regulatory intelligence layer, wherever compliance work happens.

Get started

See the SLM answer a real regulatory question.

Book a demo and bring a real circular or policy document — we'll run it live.