Agentic AI
The pilot graveyard is an evaluation problem
Most stalled AI projects never defined what "correct" looks like. A 300-example golden set, built with the people who do the job, is the cheapest investment in your AI programme.
Products we build and run
Four platforms, built and maintained by the same team that builds client systems.
Healthcare
AI EHR
An electronic health record where AI files lab reports, scans and wearable data into the patient record.
Explore →
Camera-AI safety
DRISHTI & AG Sentinel
Safety analytics on the cameras you already have, with edge processing and hash-sealed evidence.
Explore →
Workforce
WorkSync OS
Productivity analytics, attendance and work management with per-employee controls and retention limits.
Explore →Education
Study24by7
A voice-enabled AI Teacher for students and class intelligence for teachers.
Explore →What we build
Six capabilities, delivered as working systems rather than slide decks. Each one ships with evaluation sets, monitoring and a clear operating model.
Agentic workflows
Multi-step agents that plan, call tools, read your systems and complete tasks end-to-end — with approval gates where the risk warrants it.
Document intelligence
Turn forms, contracts, claims packs, lab reports and invoices into reviewed, structured data with field-level confidence and audit trails.
Enterprise knowledge & RAG
Grounded answers over policies, manuals and case history — hybrid retrieval, re-ranking and citations so every answer can be traced to a source.
LLMOps & evaluation
Offline eval sets, online monitoring, prompt and model versioning, drift and cost dashboards — the plumbing that keeps AI reliable after launch.
Small & private models
Fine-tuned small language models and on-premise deployments for teams that cannot send data out, or need predictable unit economics at scale.
AI governance & readiness
Model inventories, risk tiering, decision logs and board-level reporting aligned to MAS AI risk guidelines, PDPA, the India DPDP Act and the EU AI Act.
Selected work
Anonymised descriptions of systems we have built, with the delivery stage stated plainly.
LLM security gateway for prompts and responses
A gateway that screens prompts and model responses against configurable rules, with API keys, incident handling and audit logging.
Read the case study →
Hospital information system with pharmacy and ambulance
OPD and IPD workflows, prescriptions, pharmacy stock, blood bank, live ambulance tracking and video consultations.
Read the case study →
Insurance claims assessment with deterministic gates
An agentic pipeline that reconciles every figure in plain code and returns a structured review with an annotated PDF.
Read the case study →
Consent and rights management platform
Cryptographically signed consent records, a rights-request engine with deadline clocks and a hash-chained audit log.
Read the case study →
Medical lab report extraction and standardisation
Lab report PDFs and images become standardised results, with low-confidence items routed to human review.
Read the case study →
Multi-tenant real estate leasing and billing
Lease approvals, rent escalation, renewals and billing on a multi-tenant platform with audit trails.
Read the case study →How we work
A fixed-scope path from a real business problem to a system your operations team runs. No open-ended discovery phases.
1
Assess
We map the workflow, the data, the risk tier and the economics. You get a build/no-build decision with a business case.
2 weeks
2
Governed pilot
A working agent on your data with an evaluation set, approval gates and a measured baseline — not a chatbot demo.
4–6 weeks
3
Deploy
Integration with your systems, hardening, observability, runbooks and training for the team that will own it.
4–6 weeks
4
Operate & improve
Managed service or handover. Weekly eval review, drift and cost monitoring, model upgrades without regressions.
ongoing
What we're telling boards this year
Short positions from our current engagements.
Cost & sovereignty
Small models are winning the second wave
For narrow, high-volume tasks, a fine-tuned 7–14B model on your own infrastructure now beats frontier APIs on cost, latency and data-residency — if you have the evaluation discipline to prove it.
Governance
Regulators are asking for traces, not policies
MAS guidance, the EU AI Act and India's DPDP rules converge on one practical demand: show the decision, the data it used and who approved it. Build the log before you build the agent.
Start with a working session
Bring one workflow that costs you time or money. In 45 minutes we'll tell you whether an agent can take it on, what it would need, and what it would cost — honestly.