Wisedocs

Wiz is an AI cybersecurity platform for cloud and AI applications. It connects code, cloud, identities, network, and runtime in a unified security graph, using that context to scan attack surfaces, model lateral movement, privilege escalation, and data-access paths, detect exploitation, and generate code or infrastructure fixes. The videos describe its customer-side CVE scanning as producing security reports and discuss using agents to remediate vulnerabilities.

DocsBot is an AI-agent platform for businesses that turns company knowledge into customer-support, presales, internal-knowledge, research, and voice agents. Its agents answer questions from indexed documentation and other sources, can take actions through skills, APIs, webhooks, billing, booking, MCP, and app integrations, and can hand support conversations to humans when needed. Users create and configure a bot, import source data from websites, documents, cloud services, help centers, tickets, YouTube, and other supported sources, then test responses and deploy the agent through a chat interface, website or help-center embed, Zapier, Make, or the API. DocsBot supports custom instructions, privacy settings, multiple AI models, scheduled source updates, logs, analytics, live web search, and Code Interpreter for research workflows.

Deasy Labs is an enterprise platform for curating unstructured organizational data for AI applications. It connects to sources such as SharePoint and S3, OCRs, parses, and chunks files, then builds taxonomies, applies metadata, detects sensitive information, and evaluates file quality and relevance for a stated use case. Users can create data slices by topic, time, quality, relevance, or sensitivity and deliver them to RAG pipelines, search systems, and AI agents, while writing metadata back to source systems. Deasy continuously monitors connected sources, enriches new content, and refreshes datasets to reduce the effects of stale, duplicated, conflicting, irrelevant, or sensitive files. The platform provides APIs and a Python SDK, supports deployment in a customer's own environment, and allows use of customer-provided models and LLM endpoints. The company was acquired by Collibra, according to the video description.

DocuVault is a self-hosted team documentation and wiki application that stores Markdown files in a Git repository, with every browser save recorded as a Git commit. It provides a TipTap-based WYSIWYG editor, repository cloning for local editing, search, version history, role- and team-based permissions, fine-grained space access, and public share links with optional passwords and commenting. Its optional AI features include semantic search and question answering over documentation with source links, while its built-in MCP server lets authorized AI agents search, read, create, edit, share documents, manage tasks, and transfer files according to the user's permissions. It can synchronize spaces with GitLab or use a local Git repository; GitHub synchronization is listed as planned. The application is distributed for self-hosting with Docker images for amd64 and arm64, and uses PostgreSQL with pgvector, MinIO, Redis, and a reverse proxy in its documented deployment stack. DocuVault is in early access and is source-available under the Business Source License 1.1 rather than an OSI-approved open-source license. It is free to use and modify for self-hosting, while offering it as a competing hosted service requires a separate agreement; each version converts to Apache 2.0 after four years.

deident-wasm is a Rust privacy transformation engine for structured datasets. It applies declarative YAML policies to CSV, JSONL/NDJSON, Parquet, and DICOM data, supporting reversible pseudonymization and risk-assessed anonymization. Policies classify columns as direct identifiers, quasi-identifiers, sensitive data, or utility fields and can tokenize, remove, redact, bucket, truncate dates, or retain prefixes. The engine also detects identifiers embedded in content using built-in or custom regular expressions, with options to redact, tokenize, or replace matches with structurally valid fakes. It can process chained datasets with shared token scoping so foreign keys remain joinable after pseudonymization. Jobs may run in isolated WebAssembly sandboxes using Wasmtime and WASI, with a fresh store, one preopened directory, no network access, and memory, CPU, and time limits. An optional XChaCha20-Poly1305 mapping vault stores original-to-token mappings for authorized reversal. The tool produces risk reports containing row counts, identifier actions, pattern findings, and equivalence-class statistics; a minimum-k requirement can act as a CI post-condition. Its anonymization mode is described as reducing and measuring re-identification risk rather than certifying anonymity, while pseudonymized output remains personal data. The repository also documents DICOM metadata de-identification with consistent UID remapping.