Riku.ai

Riku.ai provides a drag-and-drop interface that allows non-technical users to visually compose multi-step AI workflows by connecting nodes representing API calls, LLM prompts, conditional logic, and data transformations. The builder abstracts away JSON/API complexity by exposing input/output mapping through a graphical interface, enabling users to chain together complex sequences without writing code. Under the hood, workflows are likely compiled into a DAG (directed acyclic graph) structure that executes sequentially or in parallel based on node dependencies.

Riku.ai abstracts away provider-specific API differences (OpenAI, Anthropic, Cohere, etc.) by exposing a unified model selection interface where users can swap between providers without changing prompt structure or workflow logic. This is implemented through a provider adapter layer that normalizes request/response formats, parameter mappings (temperature, max_tokens, etc.), and error handling across different LLM APIs. Users can A/B test models or switch providers based on cost/performance without rebuilding workflows.

Riku.ai likely provides team collaboration features that allow multiple users to work on the same workflows, though the editorial summary suggests this may be underdeveloped. This would include shared access to workflows, role-based permissions (viewer, editor, admin), and possibly version control or audit logs. The implementation likely uses a centralized workspace model where teams can organize workflows into projects or folders and manage access at the team level.

Riku.ai allows workflows to include error handling nodes that catch failures from API calls or LLM requests and execute fallback logic. This might include retry logic, default values, or alternative workflow paths when steps fail. The implementation likely uses try-catch patterns at the workflow step level, allowing users to define what happens when an API call times out, an LLM request fails, or a webhook returns an error. This prevents entire workflows from failing due to a single step's error.

Riku.ai allows users to deploy workflows to production and manage multiple versions. This likely includes the ability to publish a workflow, create new versions, and potentially roll back to previous versions if issues arise. The platform probably maintains a version history and allows users to compare versions or promote versions from staging to production. Deployment is likely one-click or automatic, without requiring manual infrastructure setup.

Riku.ai enables workflows to be triggered by incoming webhooks and to call external APIs as workflow steps, with real-time request/response handling. The platform exposes webhook URLs that can receive POST requests from external systems, parse the payload, and execute workflows with that data as input. Workflows can also make HTTP calls to third-party APIs (Slack, Stripe, Salesforce, etc.) as intermediate steps, with response data flowing into subsequent nodes. This is implemented through a webhook listener service and HTTP client abstraction that handles authentication (API keys, OAuth), retries, and timeout management.

Riku.ai provides a prompt editor interface where users can write and test LLM prompts with variable substitution, system instructions, and example-based few-shot learning. The platform likely stores prompts as templates with named variables (e.g., {{customer_name}}, {{product_type}}) that are populated at runtime from workflow inputs or previous step outputs. Users can test prompts interactively before deploying them to production workflows, with version history and rollback capabilities (unclear if explicitly stated). This abstracts away raw API calls and enables non-technical users to iterate on prompt quality without understanding JSON request formatting.

Riku.ai allows workflows to include conditional branches based on LLM outputs, API responses, or user inputs. This is implemented through if/then/else nodes that evaluate conditions (e.g., 'if sentiment is negative, route to escalation workflow') and route execution to different workflow paths. The platform likely supports basic comparison operators (equals, contains, greater than) and boolean logic (AND, OR). Conditions can reference outputs from previous workflow steps, enabling data-driven branching without hardcoding logic.

Riku.ai provides a data mapping interface that allows users to transform and route data between workflow steps without writing code. This includes extracting fields from JSON responses, formatting text, and mapping outputs from one step to inputs of the next. The platform likely uses a visual JSON path selector or simple field mapping UI where users can click to select which data to pass forward. This abstracts away the need to write JavaScript or Python for data transformation, making workflows accessible to non-technical users.

Riku.ai provides execution logs and monitoring dashboards that show the status of workflow runs, including which steps succeeded/failed, execution time per step, and error messages. Users can inspect individual workflow executions to debug issues, view input/output data at each step, and understand where failures occurred. This is likely implemented through a centralized logging service that captures execution traces and exposes them via a dashboard UI. Logs may be retained for a limited time period (unclear if there's long-term log storage or archival).

Riku.ai allows workflows to be executed on a schedule (e.g., daily, weekly, or custom cron expressions) without requiring external scheduling infrastructure. This is implemented through a scheduler service that triggers workflows at specified intervals and passes any configured parameters as input. Scheduled workflows can be used for batch processing, periodic data synchronization, or recurring AI tasks. The platform likely stores schedule configurations and manages execution history for scheduled runs.

Riku.ai enables workflows to chain multiple LLM calls together, with outputs from one prompt fed as inputs to the next. The platform preserves context across steps, allowing later prompts to reference earlier outputs and build on previous reasoning. This is implemented through a context management layer that maintains state across workflow steps and passes relevant data forward. For example, a workflow might first classify a customer message, then generate a response based on the classification, then summarize the interaction. Each step has access to outputs from previous steps.

Riku.ai offers a freemium model where users can build and test workflows for free, with paid tiers based on API usage (LLM calls, API integrations, workflow executions). The platform likely tracks usage metrics (number of LLM calls, tokens consumed, API calls made) and displays them in a dashboard. However, the editorial summary notes that pricing opacity and unclear scaling costs are a weakness, suggesting that cost tracking may not be transparent enough for users to predict expenses as usage grows.