The HelloDave.ai blog covers how to build AI workflows that keep humans in control: governed AI, human-in-the-loop review design, model-agnostic AI, and going from a blank canvas to a live workflow in under 20 minutes. Written by the voolama team from first-hand work building the platform.
Learn about Dave, a production-grade AI workflow orchestration platform with 305 API endpoints. Start optimizing your workflows today!
An approval gate pauses a DAVE workflow and routes it through a named human reviewer before execution continues. This guide walks through placing a Human Review node, wiring its…
Read →When a workflow task is assigned to a role rather than a named individual, any user holding that role can claim and complete it. This guide explains when to use role-based…
Read →The Routing node evaluates a field in the workflow payload and sends execution down a different path depending on what it finds. This guide walks through placing a Routing node,…
Read →A prompt library gives your team a single, governed source of truth for every AI instruction your workflows depend on. This guide covers creating, categorizing, and assigning…
Read →The API Call node lets you send an HTTP request to any external REST API during workflow execution, capture the response, and map values back into your workflow fields. This guide…
Read →DAVE supports Ollama as a first-class provider type, letting you point any agent at a locally hosted model without touching workflow logic or agent credentials. This guide walks…
Read →A step-by-step guide to adding Anthropic as an AI provider in DAVE, so your workflows can call Claude models with your own API key and zero platform markup.
Read →A step-by-step guide to adding Azure OpenAI as an AI provider in DAVE, so your workflows can call your Azure-deployed models with your own credentials and zero platform markup.
Read →A step-by-step guide to adding Google AI as an AI provider in DAVE, so your workflows can call Gemini models with your own API key and zero platform markup.
Read →A step-by-step guide to adding OpenAI as an AI provider in DAVE, so your workflows can call GPT models with your own API key and zero platform markup.
Read →An AI agent in DAVE is a named, versioned, reusable component that wraps an AI provider with a system prompt and behavior parameters. This guide walks through creating one from…
Read →A step-by-step guide to diagnosing and resolving a workflow instance that has stopped progressing: how to read the status, find the blocking task, inspect the context, and decide…
Read →A step-by-step guide to filtering, scoping, and exporting DAVE's audit log as a CSV file ready for external auditors, compliance teams, or incident investigators.
Read →Prompt locking pins a library prompt to an agent so that workflow designers cannot change it. This guide walks through the full process: creating the prompt in the Prompt Library,…
Read →A review loop runs a review node, routes failures back to an earlier generation step, and only advances when the review passes. This guide shows how to wire that pattern using…
Read →When a workflow runs multiple Agent Interaction nodes in sequence, each agent receives the instance context accumulated so far. This guide explains how that context is built, how…
Read →Retiring an agent version in DAVE marks it unavailable for new workflow assignments while leaving every running instance untouched. This guide covers when to retire, how to do it,…
Read →The Safety node runs content safety and compliance checks at a defined point in your workflow and propagates those guardrails to every downstream agent call. This guide shows how…
Read →Changing an agent's system prompt without a version record is how silent regressions happen. This guide covers the full safe-versioning workflow: creating a new version, testing…
Read →Learn Dave, at /learn-dave, is the walkthrough surface. It carries a nine-step run through your first workflow, from adding an AI provider to confirming a completed run, and every one of those steps links to a task-level quick reference guide. Ten of those guides exist, covering adding a provider, creating an agent, creating and activating a workflow, launching an instance, building a workflow in the editor, working a task from your inbox, reading a run's timeline, scheduling a recurring run, setting up a custom field, and connecting an AI assistant over MCP. The blog is where the thinking goes; Learn Dave is where the clicks go.
The voolama team, including founders Dean Brown and Adam Valine, writes from first-hand experience building the Dave platform.
Governed AI, human-in-the-loop design, model-agnostic AI, workflow building, and practical how-to guidance for AI workflow orchestration.
Yes. The posts explain how the platform actually works, node types, security, and deployment, so you can judge fit before starting a free trial.
Three kinds, in one feed: articles, guides and resources. Every card is tagged with its type, the feed can be filtered to one type at a time, and each post has its own page at /article, /guide or /resource.
In the product's own help centre rather than on this blog. Every Dave release ships plain-language release notes inside the app, alongside a guide for each area of the product.
On Learn Dave at /learn-dave: a nine-step walkthrough of your first workflow end to end, with every step linked to one of ten short task-level guides for the jobs people do most often.
