# AiGanak: full reference AiGanak is an AI workflow automation and systems studio in Pune, India. It builds multi-agent workflows on n8n and Make, prompt guardrails, private model deployments and custom small language model proofs of concept, and runs LLM cost and reliability audits for companies in the US, Europe and India. Last updated: 2026-10-23 ## Facts - Legal name: AiGanak Technologies OPC Pvt Ltd - Location: Pimple Saudagar, Pune, Maharashtra 411027, India - Founded: 2021 - Founder: Akshay Bankar, Founder & Director, Enterprise AI Architect - Markets: US, Europe and India - AiGanak-SLM-1B status: Phase 2 convergence, not released - AiGanak-SLM-1B size: About 1 billion parameters, decoder-only, 128k-token context - LLM Cost Audit pricing: Quick Check free; Standard $1,500; Deep $4,500; implementation from $5,000; monitoring from $500 a month - Audit turnaround: Five to seven working days - Live products: Prompt Lab, Model Lab, Hiboto ## AiGanak: private AI agents, LLM cost engineering and SLM research URL: https://aiganak.com/ AiGanak is a Pune-based AI systems studio. It builds multi-agent workflows, prompt guardrails and private model deployments, runs LLM cost and reliability audits, and researches small language models such as AiGanak-SLM-1B. ### What does AiGanak do? AiGanak builds production AI systems: multi-agent workflows on n8n and Make, prompt guardrails, private model deployments and custom small language models. It also runs LLM cost and reliability audits that show companies where their AI spend goes and how to cut it without losing quality. ### Where is AiGanak based and who does it work with? AiGanak is based in Pimple Saudagar, Pune, India. It works with companies in the US, Europe and India, mostly remotely. ### Is AiGanak-SLM-1B available? Not yet. AiGanak-SLM-1B is in Phase 2 convergence. Companies can join the Registry for early access, or commission a custom model proof of concept built on the same research. ### How do I start? Run the free Quick Check on the LLM Cost Audit page, or describe your project to AiGanak Agent on the contact page for a draft proposal that an engineer reviews with you. ## LLM Cost & Reliability Audit URL: https://aiganak.com/llm-cost-audit/ The LLM Cost & Reliability Audit measures your OpenAI, Anthropic, Azure, Bedrock or Gemini usage from your own logs, prices every saving (model routing, caching, prompt trimming, retrieval, batch) against your approved answers, and ranks reliability risks. A free Quick Check gives an instant estimate. ### What data do you need for an LLM cost audit? One calendar month of usage export from your provider's console or usage API, a sample of 500 to 5,000 logged requests and responses with personal data removed, and 20 to 50 approved example answers per feature. You run the export yourself, so we never need your API keys. ### Which providers are supported? OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Google Gemini and self-hosted open models. The importer reads the OpenAI and Anthropic usage APIs directly and a simple CSV for the rest. ### How do you make sure quality does not drop? Every model change is tested on your own approved answers in Model Lab. A cheaper setup is only recommended if it scores within one point of what you use today on a 0 to 100 scale. ### How much does an LLM cost audit cost? The Quick Check is free. The Standard Audit is $1,500 for up to 2 features. The Deep Audit is $4,500 for up to 5 features with model replay and prompt-injection testing. Implementation starts from $5,000. ### How long does an audit take? Five to seven working days from receiving your data, including an architect review and a 45-minute walkthrough call. ### Is my data safe? Work is done under NDA, on redacted samples only, in an isolated environment, and the data is deleted 30 days after delivery. ## Sample LLM cost audit report URL: https://aiganak.com/llm-cost-audit/sample-report/ A sample audit for Orvella, a fictional support-software company spending $14,001 a month on LLM APIs. It finds $5,851 to $7,377 a month in savings (42 to 53 percent) through 9 changes and lists 4 reliability issues. All data is simulated. ## AI engineering services URL: https://aiganak.com/services/ AiGanak builds production AI systems: multi-agent workflow automation on n8n and Make, prompt hardening and guardrails, private model deployment, and custom small or large language model development delivered as proof of concept, MVP and production. ### What kinds of AI projects does AiGanak take on? Workflow automation with AI agents, hardening LLM prompts and guardrails, deploying models privately, and building custom small or large language models. Most engagements start with an audit or a scoped proof of concept. ### Can you work with our existing n8n or Make setup? Yes. We extend existing n8n and Make scenarios with agents, stateful routing and guardrails rather than replacing them. ## Multi-agent workflow automation (n8n and Make) URL: https://aiganak.com/services/workflow-automation/ AiGanak builds n8n and Make multi-agent workflows that connect databases, CRMs, ERPs and messaging to language models with stateful routing, guardrails and cost tracking. ### What is a multi-agent workflow? A multi-agent workflow splits a business process into steps handled by separate AI agents, each with its own tools and instructions, coordinated by an orchestrator. In n8n or Make, each agent becomes a node that reads from and writes to your systems. ### Which systems can the agents connect to? Anything n8n or Make can reach: databases, CRMs, ERPs, email, WhatsApp and internal APIs, plus custom middleware where a connector does not exist. ## Prompt hardening and LLM guardrails URL: https://aiganak.com/services/prompt-guardrails/ AiGanak hardens LLM integrations against prompt injection, format failures and token waste using XML-structured prompts, negative constraints, input isolation and CI validation, backed by Prompt Lab diagnostics. ### What is prompt injection? Prompt injection is when text supplied by a user or a retrieved document contains instructions that override the system prompt, for example making a support bot reveal internal notes. Guardrails separate untrusted content from instructions and check outputs before they are shown. ### How do you test guardrails? Prompt Lab runs injection, format and boundary tests on each prompt, and the same tests run in CI on every prompt change. ## Private and on-premise LLM deployment URL: https://aiganak.com/services/private-model-deployment/ AiGanak deploys and optimises open-weight language models in a client's own cloud account or on-premise, including offline setups, so enterprise data never reaches public AI APIs. ### Can AI run without sending data to OpenAI or Anthropic? Yes. Open-weight models can run in your own cloud account or on your own servers, including fully offline. AiGanak benchmarks candidates on your tasks first so you know what quality to expect. ### When is self-hosting cheaper than an API? Only above a certain monthly volume. The LLM Cost Audit calculates your break-even point from your own usage before you buy hardware. ## Custom small language model development URL: https://aiganak.com/services/custom-slm-development/ AiGanak builds domain-specific small and large language models in stages: a proof of concept on sample data with an evaluation report, an MVP for a pilot team, then private production deployment. The work uses the training pipeline built for AiGanak-SLM-1B. ### What is a small language model? A small language model has roughly 0.5 to 7 billion parameters. It can run on a single server or edge device, so data stays in-house, and it handles focused tasks such as extraction, classification and document question answering well. ### How does a custom model project start? With a proof of concept on your sample data and an evaluation report, usually in two to four weeks. You decide on an MVP only after seeing results. ## Prompt Lab URL: https://aiganak.com/prompt-lab/ Prompt Lab audits a failing system prompt. You submit the prompt, the failed input and output, formatting rules and a target answer; it checks XML structure, negative boundaries and injection risks and emails a diagnostic report. ## Model Lab URL: https://aiganak.com/model-lab/ Model Lab benchmarks fine-tuned and candidate models against production baselines on your own examples, scoring accuracy, drift, hallucination and latency, and emails a performance report. ## AiGanak-SLM-1B URL: https://aiganak.com/slm-1b/ AiGanak-SLM-1B is AiGanak's in-house 1-billion-parameter decoder-only small language model with a 128k-token context window, built first for logistics and supply-chain documents. It is in Phase 2 convergence and has not been released. ### What is AiGanak-SLM-1B? An in-house 1-billion-parameter decoder-only transformer with a 128k-token context window, built first for structured logistics and supply-chain documents. ### Can I use AiGanak-SLM-1B today? No. It is in Phase 2 convergence and has not been released. Join the Registry for early access, or commission a custom model proof of concept. ### What hardware is it trained on? Training runs on AMD Instinct MI300X accelerators with ROCm and Flash Attention kernels. ## Hiboto URL: https://aiganak.com/hiboto/ Hiboto is AiGanak's no-code chatbot builder for creating bot profiles and chatbots. ## Model Registry URL: https://aiganak.com/registry/ The AiGanak Registry gives validated partners early access to sandbox model releases, local-weights documentation and 128k-context test suites once they are available. ## About AiGanak URL: https://aiganak.com/about/ AiGanak Technologies OPC Pvt Ltd is an AI systems engineering and research company in Pimple Saudagar, Pune, founded in 2021 by Akshay Bankar. ## Akshay Bankar, Founder and AI Architect URL: https://aiganak.com/akshay-bankar/ Akshay Bankar is the founder and director of AiGanak, an enterprise AI architect with more than 16 years in software architecture, specialising in small language models, secure on-premise AI and agentic systems. ### Who founded AiGanak? Akshay Bankar, an enterprise AI architect with more than 16 years in software architecture. He leads AiGanak's AI solutions and its small language model research. ### Does Akshay Bankar consult independently? Yes, through AiGanak: architecture reviews, SLM and RAG strategy, private AI design, agentic systems, AI cost optimisation and fractional AI architect roles. ## Contact and project scoping URL: https://aiganak.com/contact/ Contact AiGanak to scope a project. AiGanak Agent asks a few questions and drafts a proposal with an approach, timeline and estimate, which an engineer then reviews with you. ## AiGanak facts URL: https://aiganak.com/facts/ Verified facts about AiGanak, its services, products, model research status and pricing, kept current for people and AI assistants.