Search results for Reference Tracker

Groundnote is meeting intelligence software that turns discussions into actionable outcomes. It captures conversations via browser recording, media uploads, transcript pasting, or meeting connections, then processes them through a workflow separating AI inferences from human-confirmed decisions. AI outputs are treated as claims needing validation, not just transcriptions, with source-linked evidence like quotes, speaker IDs, timestamps, and confidence levels preserved for context. Participants can review, edit, or dispute commitments before finalizing agreements. Decision ownership is tracked, clarifying who committed to what and when. Unresolved commitments reappear in future briefs for visibility. The platform integrates with external systems, linking tasks to their meeting origins, and supports governance with audit records, retention controls, and local AI options.

naqilo is cloud-based transport management software (TMS) built for freight carriers, freight brokers and forwarders operating in Türkiye. It replaces ledgers, spreadsheets and disconnected tools with one system written in the language of freight, covering the whole operation from quote and order intake to trip planning, delivery paperwork, invoicing and collections. Three parties, one network. naqilo is more than back-office software: it connects the freight company (the hub) with its shippers and its owner-operator truckers on the same platform. naqilo Portal gives customers their own screen to open transport requests, follow shipment status, view statements and invoices, and message the carrier with files attached. naqilo Driver lets owner-operators see their trips, send a photo of the delivery note from WhatsApp and check their earnings. Built for Turkish compliance. e-Invoice and e-Archive documents are issued in one click through the integrator (Uyumsoft), incoming invoices are pulled in automatically, and U-ETDS freight movement declarations are generated from trip records and filed automatically, so no filing is missed and no penalty is paid. Withholding (tevkifat) rules for the transport sector are handled out of the box. Ledgers and money. Customer and carrier statements, receipts and payments, cash and bank, cheques and notes, receivables ageing and multi-currency support are all included. A Management Dashboard shows revenue, gross profit, margin, cash and receivables for any period, compared with the previous period and the same period last year, with alerts for overdue customers, trucks paid above the suggested price and customers who stopped ordering. Key features - Shipment and trip management from quote to delivery - e-Invoice / e-Archive integration and incoming invoice retrieval - Automatic U-ETDS freight declarations - Ledgers, cash, bank, cheques and notes, receivables ageing - WhatsApp Business, SMS and e-mail notifications - 50+ built-in reports with Excel/PDF export and a free-form analysis report - Fleet, licence and fuel consumption tracking (documents read from a photo) - Customer portal and driver app - Per-user permissions, remembered grid preferences, drag-and-drop dashboards - Isolated database per company, encrypted connections, scheduled backups In Turkish, naqilo is known as a "nakliye programı" (transport software) or "nakliye yazılımı" and serves nakliye firmaları, nakliye komisyoncuları and ambarlar. naqilo is the cloud successor to Şenkom Nakliye, a desktop transport application used by Turkish freight companies for over 25 years. Existing customers migrate their customers, vehicles, balances and transaction history with the built-in data transfer tool, and local support is one message away.

ARI is a private automation suite composed of two separate products: ARIflow, a workflow orchestration platform, and ARImodules, a set of pre-built vertical AI applications. ARIflow is a low-code workflow orchestration platform. Users design automation workflows in a visual, node-based editor, connecting nodes that perform a specific operation (LLM prompts, document processing, database queries, API calls, browser automation, conditional logic, and iteration). Workflows can be tested automatically against defined evaluation parameters, including comparison of different LLM models to balance output quality and models' cost. Each execution is tracked, and its LLM cost can be verified both per individual run and projected across an expected volume of executions, allowing teams to estimate costs before deploying a workflow to production. Different versions and variants of a workflow can be branched and compared through a built-in versioning system (Research Tree), which tracks how each workflow evolves across iterations. Once tested, workflows can be published as API endpoints with auto-generated documentation. ARIflow is aimed at technical users who build and maintain custom pipelines and solutions. It supports any LLM provider through an LLM-agnostic architecture, including self-hosted open-source models. ARIflow can be deployed as multi-tenant SaaS, as a single-tenant private cloud instance, or on-premise via Kubernetes on the customer's own infrastructure. ARImodules are ready-to-use applications built on top of the ARIflow engine, aimed at operational users who needs to use specific AI applications without building workflows from scratch. Each module is licensed and priced separately, on a usage basis (not per user seat), with LLM inference costs included in the price. ARIknow is a document question-answering module. Users upload documents into permission-scoped knowledge bases; queries are answered using hybrid retrieval (vector + BM25 keyword search), and every answer cites the source passage it was generated from. Knowledge bases are organized in parent-child hierarchies: granting access to a parent knowledge base automatically grants access to all of its child knowledge bases, without configuring permissions individually for each one. ARIdb lets users query relational, NoSQL, or legacy databases in natural language. The model reads only the database schema, not the underlying data, and generates inspectable SQL queries; access is controlled per table and role. Results can be returned as a data table or rendered as a dashboard, in the visual format the user requests as part of the query. ARIdoc extracts user-defined fields from documents (invoices, contracts, forms) regardless of layout. Each extracted field carries a confidence score; fields below a configurable threshold are routed to human review before being written to downstream systems (JSON, CSV, or direct API integration).

Neuronpedia is an open-source interpretability platform designed to enhance the understanding and analysis of artificial intelligence models. It offers a comprehensive suite of tools and resources that enable researchers and developers to explore, steer, and experiment with AI models, facilitating deeper insights into their internal mechanisms. By providing access to over four terabytes of activations, explanations, and metadata, Neuronpedia supports a wide range of interpretability research, including probes, latents/features, custom vectors, and concepts. Key Features and Functionality: - Exploration Tools: Browse extensive datasets comprising activations, explanations, and metadata to gain insights into model behavior. - Circuit Tracer: Visualize and trace the internal reasoning steps of models using custom prompts, inspired by Anthropic's circuit tracing research. - Steering Mechanism: Modify model behavior by adjusting activations with latents or custom vectors, supporting both instruct (chat) and reasoning models with customizable parameters. - Search Capabilities: Access a vast repository of over 50 million latents/vectors, searchable by semantic similarity or custom text inference to identify top matches. - API and Libraries: Utilize the world's first interpretability API, offering functionality through Python and TypeScript libraries, with comprehensive OpenAPI specifications and interactive documentation. - Inspection Dashboards: Delve into probes, latents, and features with detailed dashboards showcasing top activations, logits, activation density, and live inference testing, all shareable and embeddable. Primary Value and Problem Solved: Neuronpedia addresses the critical need for transparency and interpretability in AI models. By providing an open platform with extensive datasets and advanced tools, it empowers researchers and developers to dissect and understand the inner workings of neural networks. This capability is essential for ensuring the alignment, safety, and reliability of AI systems, particularly as they become increasingly complex and integral to various applications. Neuronpedia accelerates interpretability research by offering scalable infrastructure, collaborative tools, and a rich repository of data, thereby facilitating the development of more transparent and trustworthy AI technologies.