llms.txt
Compare with other sites' llms.txt files →# Nace.AI
> Execute your Workflows with Nace Small Models Powered by the Metamodel, our specialized models deliver exceptional precision at one-tenth the cost of large LLMs. Automate back office and front office operations end-to-end with execution layer.
## When to use Nace
- Put a decision model inside a browser agent: Drex Max reads the screenshot and scores the next click, with a probability for every option, in one pass.
- Make financial decisions on text and documents with Drex for Finance (model id drex-max-finance): filings, invoices, credit, fraud and AML, sentiment and monetary policy, each answer a calibrated probability.
- Make a decision from the facts of a case: send Drex a state and typed questions (pick one of several, yes or no, rate on a scale) and get a calibrated probability for every option in one forward pass, with no text to parse.
- Put a decision model inside a workflow: threshold the confident calls, route the uncertain ones to a person, and tune Drex on your own labelled outcomes.
- Read any file type with Nace Document Processing: parse, split, classify, extract and ground, with every value tied to the page and box, sheet and cells, or span it came from.
- Run the same models in our cloud, a dedicated cluster, your own cloud account or air-gapped, with your data training only your models.
- Automate receivables, payables, monitoring and continuous audit for a finance team, or put an AI Senior Accountant on an audit and accounting firm's clients.
## Get started for agents
- [Drex API guide](https://nace.ai/drex.md): the decision model: request shape, question types, benchmarks and deployment, as markdown
- [Decision endpoint](https://console.nace.ai/v1/systemone): POST with model "drex-latest", a state string and typed questions (choice, noul, score); https://console.nace.ai/v1/models lists checkpoints
- [Document endpoints](https://console.nace.ai/v1/documents/{parse|split|classify|extract|ground}): POST a source (a public URL, an uploaded workspace file or a finished parse job) and poll GET https://console.nace.ai/v1/documents/jobs/{id}; the same key and credit as decisions
- [Console](https://console.nace.ai): API keys, the playground, usage and billing; send `Authorization: Bearer $NACE_API_KEY` on every request
- [Console docs](https://console.nace.ai/docs): quickstart, question types, the document routes, errors, limits and pricing
- [Nace Document Processing](https://nace.ai/perception.md): the Perception series: parse, split, classify, extract and ground any file type with a location on every value
- [Drex for Search](https://nace.ai/drex/search.md): Drex for Search: decision-powered retrieval for agents, Drex finds the page, cited search through the CLI, SDKs, MCP and REST, and the public benchmark ranks
- [Industries](https://nace.ai/industries.md): Nace by industry: the files Document Processing reads and the decisions Drex makes for accounting, banking, mortgage, insurance, legal, healthcare, government, construction, logistics and professional services
- [Developers](https://nace.ai/developers.md): The execution layer for agents: Perception, Decision and Search behind one key, the Drex Max frontier, install steps, a scripted agent session and the four deployment boundaries
## How to read this site
- Any page as markdown: append `.md` to its URL or send `Accept: text/markdown`. Responses set `X-Markdown-Tokens` (an estimate) and link the HTML canonical.
- [Full site as one file](https://nace.ai/llms-full.txt): every listed page, serialized in order.
- [Sitemap](https://nace.ai/sitemap.xml)
## Industries
- [Industries](https://nace.ai/industries): Nace for your industry. Document Processing reads the files your industry runs on, and Drex makes the decisions that follow. For accounting, banking, mortgage, insurance, legal, healthcare, government, construction, logistics and professional services.
- [Accounting](https://nace.ai/industries/accounting): Document Processing extracts statements, ledgers and invoices and cites each value. Drex suggests codes, scores matches and flags exceptions for your team to review.
- [Banking](https://nace.ai/industries/banking): Drex scores fraud alerts, suggests dispute reason codes and routes requests inside your network, so analysts start with the riskiest cases. Document Processing extracts the onboarding and credit files behind them.
- [Mortgage lending](https://nace.ai/industries/mortgage-lending): Document Processing splits a 500-page loan package into its documents and extracts every figure with a citation, so processors and underwriters start from the facts.
- [Insurance](https://nace.ai/industries/insurance): Document Processing extracts submissions, claims packets and policies and cites each field. Drex suggests a triage queue, estimates coverage and scores fraud signals, for adjusters to confirm.
- [Legal](https://nace.ai/industries/legal): Document Processing extracts terms from contracts and filings, cited to the clause. Drex for Search finds the passage across the portfolio, and Drex scores what it permits, for a lawyer to confirm.
- [Healthcare](https://nace.ai/industries/healthcare): Document Processing reads faxed referrals, records and claims, low-quality scans included. Drex triages denials, prior auths and patient messages.
- [Government](https://nace.ai/industries/government): Document Processing extracts applicant data from benefits and permit forms. Drex checks each requirement and routes complete files to the right office. Both run on-premises and fully air-gapped.
- [Construction](https://nace.ai/industries/construction): Document Processing reads pay applications, lien waivers, subcontracts and submittals and cites every figure, so project accountants check facts instead of hunting for them.
- [Logistics and supply chain](https://nace.ai/industries/logistics-supply-chain): Document Processing reads bills of lading, customs forms and carrier invoices in any format, and points every value back to its page.
- [Professional services](https://nace.ai/industries/professional-services): Document Processing reads client tax documents, engagement letters and data rooms. Drex routes requests and reviews time, the decisions that quietly eat your margin.
## Developers
- [The execution layer for agents](https://nace.ai/developers): Nace is the execution layer for agents: Perception reads any file, Decision makes the call in under 200 ms, Search finds the page in your files. One API key, at small-model speed and cost.
- [Nace Document Processing](https://nace.ai/perception): Nace Document Processing parses, splits, classifies, extracts and grounds 36 file types with a location on every value. First on grounding and level with the frontier models on split and extract in Nace's Perception evaluation, managed, in your cloud or air-gapped.
- [Drex Max, the decision model that sees](https://nace.ai/drex): Drex Max v1.1 decides from screens, images and video, built for agents that use computers and browsers. It scores 70.8 on the public Decision Index 0.4.0, 10.1 points over Jev 1.14, decides in under 200 ms and accepts every screenshot size. Drex 2.0 ships open weights, and Drex 1.5 routes text at volume.
- [Drex for Search: supercharge your agentic search](https://nace.ai/drex/search): Decision-powered retrieval for your coding agent: 6% more answers right with 62% fewer steps and 56% fewer tokens across 6 work benchmarks.
- [Drex for browser use: every click is one decision](https://nace.ai/drex/browser-use): Drex Max reads the screenshot and picks the next click in one pass. 75.9 on the public Decision Index Vision against 63.9, 174 ms per screenshot decision, every screenshot size accepted.
- [Drex for Finance: fraud, credit and filing decisions for fintech](https://nace.ai/drex/finance): A decision model for fintech engineers: score fraud, credit, filings and support with answers limited to the options you define. 77.3 on the Drex Finance Index of 48 held-out finance test sets, against 63.6 for Jev 1.14, and ahead of it in all 9 categories.
## Research
- [Research](https://nace.ai/research): Research from Nace.AI on training trustworthy models capable of executing tasks reliably while continuously self-improving.
- [Towards Foundation Decision Models: Drex](https://nace.ai/research/towards-foundation-decision-models): Our technical report on Drex, four open decision models that return a calibrated probability for every option instead of generating text. Drex Max sets a new state of the art on Decision Index 0.4.1 and is competitive with frontier models on real-data decisions in under 200 ms. (2026-11-06)
- [Drex searches. Agents reason.](https://nace.ai/research/drex-searches-agents-reason): Agents spend many of their turns working out where to look. Drex for Search hands that job to Drex, our fast decision model. It finds the pages and tables that hold the answer, and the agent reads and reasons. (2026-11-01)
- [Scaling Laws for Hypernetwork-Based Knowledge Injection](https://nace.ai/research/scaling-law-for-hypernetwork): New scaling laws for train-time knowledge injection: hypernetworks beat LoRA and full fine-tuning on out-of-distribution generalization, and the gap grows with target model size. (2026-07-22)
- [Enterprise Policy Injection with Metamodels](https://nace.ai/research/enterprise-policy-injection-with-metamodels): Adapting model behavior at inference time without retraining, large context windows, or touching the primary model's weights. (2026-05-01)
- [Nace Meta Agent](https://nace.ai/research/nacemetaagent): NEMA: meta-learning architectures that generate specialized, task-specific agents automatically. (2026-01-27)
- [Memory Augmentation and Editing Techniques in LLMs](https://nace.ai/research/memory-augmentation-and-editing-techniques-in-large-language-models): Memory augmentation and model editing for handling outdated and domain-specific knowledge. (2025-03-18)
- [NAVI Console: Policy-driven Safeguards Comparison](https://nace.ai/research/policy-driven-safeguards): Benchmarking Nace's Safety Model against AWS Bedrock, Azure, NeMo Guardrails, and prompt-based approaches. (2025-01-19)
- [GeLoRA: Efficient Fine-Tuning of Large Language Models](https://nace.ai/research/gelora): A theoretical framework connecting the geometry of data representations to training dynamics. (2024-12-10)
- [Hypernetworks for Specialized Instructions](https://nace.ai/research/hypernetworks-for-specialized-instructions): Efficient fine-tuning of LLMs through task-specific parameter generation. (2024-12-07)
- [Meta-Learning through Hypernetworks](https://nace.ai/research/meta-learning-through-hypernetworks): Improving task adaptability in large language models. (2024-12-07)
- [Memory Augmentation for Document-heavy Enterprise Use Cases](https://nace.ai/research/memory-augmentation-for-document-heavy-enterprises): A modular RAG pipeline tailored to enterprise needs: over 90% F1 on verification. (2024-11-05)
- [Knowledge Graph Synergy with LLMs](https://nace.ai/research/knowledge-graph-utilization): How structured, verifiable knowledge complements LLMs where they fall short. No ML background required. (2024-11-01)
- [Progressing Towards Meta Models and What Lies Beyond](https://nace.ai/research/progressing-towards-meta-models-and-what-lies-beyond): Tailored, meta-learned Small Language Models for rapid, efficient adaptation. (2024-10-24)
- [Understand LLMs From the Perspective of Ranking](https://nace.ai/research/understand-llms-from-the-perspective-of-ranking): Most post-training performance gains are reranking: aligning the proposal distribution with the task. (2024-10-12)
## Blog
- [Blog](https://nace.ai/blog): Announcements, product launches and company updates from the Nace.AI team.
- [Introducing Drex for Finance](https://nace.ai/blog/introducing-drex-for-finance): A decision model for fraud, credit and filings that can't make things up. It scores 77.3 on the Drex Finance Index, against 63.6 for Jev 1.14. (2026-11-02)
- [Introducing Drex for Search: supercharge your agentic search](https://nace.ai/blog/introducing-drex-for-search): Drex for Search tells your agent where the answer is before it starts reading. Across 6 professional-work benchmarks, agents take 62% fewer steps, use 56% fewer tokens, get 6% more answers right and finish 2.3× faster. (2026-10-26)
- [Introducing Drex Max, a multimodal decision model for computer use](https://nace.ai/blog/introducing-drex-max): Drex Max is a decision model that sees the screen. It reads text, images and video, ranks first among decision models on the public Decision Index 0.3.2, and is generally available today. (2026-10-19)
- [Introducing Nace Document Intelligence: The Perception Layer for AI Agents](https://nace.ai/blog/document-intelligence-launch): Five tools that parse, split, classify, extract and ground any of 36 file types, and point every value back to the page it came from. Ranks first on grounding against frontier models. Available in the Console today. (2026-10-08)
- [Introducing Drex, a small model that decides instead of writing](https://nace.ai/blog/introducing-drex): Drex returns a calibrated probability for every option in one forward pass, and leads the public Decision Index with a model small enough to serve on one accelerator. (2026-09-24)
- [Nace.AI raises $21.5M to build AI-led enterprise workflows](https://nace.ai/blog/announcing-our-seed-investment): Nace.AI raises $21.5M to build specialized intelligence for complex enterprise workflows. (2026-05-05)
- [A Letter from the Founders of Nace.AI](https://nace.ai/blog/letter-from-founders): Nace.AI emerges from stealth with Metamodel 1: precision and adaptability for enterprises. (2025-02-08)
## Company
- [About Us](https://nace.ai/about): Nace.AI builds small models for professional work. Founded in 2024 by researchers and engineers from Google, Meta, Amazon and the University of Toronto, headquartered in Palo Alto.
- [Careers](https://nace.ai/careers): Join Nace.AI. We build small models for professional work in Palo Alto, CA. See our open positions.
- [Contact Sales](https://nace.ai/contact): Talk to the Nace.AI team. Tell us what you need, and we will follow up to arrange a demo or answer your questions.
- [Press](https://nace.ai/press): News coverage of Nace.AI, company announcements, media contact, and downloadable logos and team photos for editorial use.
- [Events](https://nace.ai/events): Meetups, parties and community events hosted by Nace.AI. See what's coming up, what we've hosted, and how to co-host an event with us.
- [Data Processing Addendum](https://nace.ai/policies/data-processing-addendum): How Nace.AI processes personal data in Customer Content on a customer's behalf.
- [Privacy Policy](https://nace.ai/policies/privacy-policy): How Nace.AI collects, uses, and discloses personal information when you use the developer console, APIs, and related services.
- [Terms of Service](https://nace.ai/policies/terms-of-service): The terms governing access to and use of the Nace.AI developer console, APIs, and related services.
## Community and trust
- [Trust center](https://trust.nace.ai): SOC 2 Type II report, penetration test report and subprocessors
- [Discord](https://discord.com/invite/nace-ai): community server: questions, product updates, early access
- [X](https://x.com/NaceAI): @NaceAI
- [LinkedIn](https://www.linkedin.com/company/nace-ai/): company page
- [GitHub](https://github.com/nace-ai): open models, agent skills and tools
## Optional
- [Full site](https://nace.ai/llms-full.txt): every listed page as one markdown file
- [Developers index](https://nace.ai/developers/llms.txt): the model series, the Drex and Perception pages and deployment
- [Products index](https://nace.ai/products/llms.txt): product pages only
- [Research index](https://nace.ai/research/llms.txt): publications, newest first