Three systems, in enough detail to check.
We would rather show one system properly than twenty logos. CourtNetra is ours and it is the deepest: hybrid retrieval over 18,863,754 judgments, a citator that says whether an authority is still good law, and an automated evaluation that fails the build when hallucination goes above 2%. Outbrew and Savidhi are also ours, and also live.
CourtNetra
Our own legal research platform, also shipped as NyayLens. Indian case law is the hardest retrieval problem we could have picked for ourselves: the corpus runs to 18,863,754 judgments, the same case is cited differently across the AIR, SCC and SCR reporter series, and a wrong answer lands on a professional who is inclined to trust it. It is the reason we can talk about grounding as a build gate rather than as an intention.
Figures from the production system, not a pilot and not a projection. Ask us for the CI report.
What is actually in there
- 18,863,754 judgments: 39,158 Supreme Court and 18,824,596 High Court, across all 25 High Courts, 1950 to the present.
- 687,289 chunks from the subset selected for vector retrieval, embedded with Qwen3-Embedding-4B at halfvec(2560), indexed under HNSW in PostgreSQL with pgvector, on a self-hosted CUDA GPU pipeline.
- Hybrid retrieval: dense pgvector similarity and tsvector BM25, reconciled by Reciprocal Rank Fusion, inside a hard 30-second budget.
- A Citator classifying every authority as good law, distinguished, doubted, partially overruled or overruled, across a 165,000-entry AIR-SCC-SCR crosswalk.
- 268 API endpoints, a 41-page Next.js 14 web app, and a 37-screen React Native app live on Google Play.
- Built and operated solo by our founder, Aniruddh Atrey.
Architecture, the trust layer, and the query planner bug that took the longest to find.
The products we built, and run
Every mark here is a product MetaMinds owns and operates, which is the opposite of a logo wall: these are not customers, and we do not claim any. Showing them is the cheapest honest way to answer the question a buyer actually has, which is whether this firm ships things that stay up. Where a product has a public address, it is linked and the link was checked. Where it does not, the card says so instead of implying one.
CourtNetra
Citation-grounded retrieval across 18,863,754 Indian judgments.
NyayLens
The same retrieval engine, shipped under a second name.
Savidhi
Temple puja, chadhava and prasad booking.
- Outbrew
Outbrew
AI cold email and outreach.
No public URL yet
Work our founder did somewhere else
This section is separated from the one above deliberately. Everything before this point is a system MetaMinds built, owns and operates. Everything here is work Aniruddh Atrey did at a prior employer, where MetaMinds was not the contracting party and no client relationship existed. Mixing the two is how a portfolio quietly becomes a claim about clients, so they do not get mixed.
SaveLIFE Foundation road safety systems
Prior employerThree production systems built by Aniruddh Atrey while employed at SaveLIFE Foundation, before MetaMinds existed: a multi-stage Haystack v2 retrieval pipeline that cut analyst lookup time approximately 70% across 100+ reports a week, a WhatsApp learning channel built for exactly-once delivery on a 12-state machine, and a computer vision pass over 500+ hours of dashcam footage at 95% precision. MetaMinds was not the contracting party on any of them.
Including the five things these numbers do not mean.
Two more products we built and run
Both are in production. Neither has a number on this page, because we publish figures we can evidence and these are not measured to that standard yet. When they are, they will appear here with their provenance attached.
Outbrew
Ours. Live.AI cold email and outreach
An AI cold-email and outreach platform. We built it, we run it, and it is in production today.
No metrics published. Ask on a call and we will open the system and show you.
Savidhi
Ours. Live.Booking and scheduling
A platform for booking temple services and consultations. We built it, we run it, and it is in production today.
No metrics published. Ask on a call and we will open the system and show you.
Client work sits under NDA.
Most of what we build for clients is covered by a non-disclosure agreement, so it is not on this page and it will not be. That is the correct outcome: a firm that publishes your architecture without asking will publish the next one too.
Available on request
On a call we can walk through the parts that matter to your decision, with anything identifying removed:
- The architecture, and why each component was chosen over the obvious alternative.
- Evaluation results, including the numbers that were bad before they were good.
- The failure modes we hit in production, and what the fix cost.
- References, where the client has given written permission for us to arrange one.
We do not name a client, publish a logo or quote a testimonial without written permission.
The portfolio, answered directly.
Every answer here is the same string this page puts in its structured data, so a person and an answer engine read the identical text. Open one to read it.
What has MetaMinds actually built and shipped?
Three systems that MetaMinds owns and runs: CourtNetra, a live legal AI platform doing citation-grounded retrieval across 18,863,754 Indian judgments; Outbrew, an AI cold-email and outreach platform; and Savidhi, a booking and scheduling platform for temple services and consultations. All three are in production today. CourtNetra carries published figures because they are measurable from a system MetaMinds operates; the other two carry none, and that absence is deliberate rather than an oversight.
Why do Outbrew and Savidhi have no published metrics?
Because there is no figure for either that MetaMinds would defend in front of a buyer, and publishing one that cannot be defended is the precise failure this site was rebuilt to remove. Both are described by what they do and by the fact that they are live, which is the whole of what can be substantiated today. The offer on both is a call rather than a case study.
What stands in for named clients and logos here?
Work this firm owns and can show you end to end, which is why the case studies on this page are MetaMinds' own systems rather than a grid of marks. Publishing a client name takes written permission on file, and a call with someone who has had the work done carries more than a logo would. Every figure on this site is attached to a named system and offered with its evidence.
Is CourtNetra a client project or MetaMinds' own product?
It is MetaMinds' own. It was built, is operated and is paid for by MetaMinds, which is exactly why its figures can be published at all: they are measured on a system MetaMinds controls rather than reported second-hand from a client engagement. It is the reason every retrieval number on this site is a measurement rather than a projection.
Can I speak to someone about work MetaMinds has done?
Yes, on a call, and that is currently a better offer than the logo grid it replaces. The route in is a 30-minute technical conversation with the engineer who did the work, where the system, the architecture decisions and what went wrong can all be discussed in specifics. What cannot happen is a named public reference, because no client has given written permission for that.
Whose work is the SaveLIFE Foundation case study?
Aniruddh Atrey's, built while employed at SaveLIFE Foundation and before MetaMinds existed. It is published as evidence of what the founder has built, with the employer named and the dates stated, because provenance is part of what makes a figure checkable. The retrieval, WhatsApp delivery and dashcam vision systems are all his work on that estate.
Tell us what breaks if the AI gets it wrong.
That single answer tells us more than a requirements document, and it is how every one of the systems above started. Thirty minutes, straight to the engineer who would build it.
Typical reply within one business day · Engagements start at $2,500