Your platform. Your choice of AI.
Discuss your model setup
Build your Agent services on a foundation you can extend.
OpenRouter. Laravel AI. Langfuse. Connected in Dollie.
OpenRouter. Choose what powers the work. Connect your account to access models from multiple providers. Choose what powers each Agent and the embeddings that make your Knowledge searchable. Read the OpenRouter documentation.
Laravel AI SDK. Extend your platform. Choose your infrastructure. Connect privately hosted models, add providers and build custom Agent capabilities on Dollie’s Laravel AI foundation. For Self Hosted and private enterprise deployments, we configure the setup around your infrastructure and data requirements. Explore Laravel AI.
Give each Agent the model its work needs.
Access models from multiple providers through one OpenRouter connection. Choose what powers each Agent, tailor access across Workspaces, and decide who can make those choices.
Browse models through OpenRouter and choose the ones you want to make available. You own the selection, from a focused set to a wider choice for your teams.
- Models from multiple providers
- Capability and pricing in view
- A default chosen by you
Give different customers or departments the model access they need. Keep selection with the platform team or allow Workspace Operators to choose for their Agents.
- Separate customer and department Workspaces
- Defaults for consistent setup
- Delegate model choice where useful
Give routine intake and summaries a fast, lower-cost model. Choose stronger reasoning for analysis and complex reviews, then evaluate the results on your own work.
- Different models for different jobs
- Per-Agent selection in Agent Studio
- Instructions and Knowledge stay connected
Choose the model for the work.
Connect the work in Dollie.
Routine intake
Handle frequent requests with a lower-cost model. Configure an intake Agent to read incoming briefs, extract the requirements and create a Task on your board. Your team can review the brief and assign the research to an Agent with a stronger reasoning model.
- Lower-cost intake
- A Task with the brief attached
- Choose who takes it further
Deeper research
Give complex decisions a stronger reasoning model. Assign the supplier comparison to a research Agent with the model and tools the job needs. It can compare the proposals against your criteria, investigate gaps and prepare a recommendation for your team to review.
- A model chosen for analysis
- Your assessment criteria
- A recommendation for review
Visual Knowledge
Turn scanned pages into evidence your Agents can use. Index technical PDFs and images with a multimodal embedding model such as Gemini Embedding 2. An Agent can retrieve the relevant diagrams and tables, inspect them with a model that accepts images, and prepare a visual presentation with source references.
- Multimodal embeddings
- Relevant PDF pages and images
- A presentation backed by sources
See what your Agents use.
Know what the work costs.
Inspect requests with Langfuse Review traced model inputs and outputs to investigate a slow or unexpected answer.
Compare models in use See token usage, latency and model costs for the traffic your deployment traces.
Understand customer economics Use Dollie’s separate usage accounting to understand what each Workspace consumes.
Choose where monitoring lives Connect Langfuse Cloud or a self-hosted instance. Configure OpenRouter Broadcast to send the traces.
Questions about models, usage and private deployments.
Planning the AI setup for your platform? Discuss your model setup
Your infrastructure. Your models. Your Agent OS.
Run your Agent OS with the models and infrastructure your organisation requires. Start with OpenRouter, or work with us to connect privately hosted models and self-hosted Langfuse monitoring.
Private model endpoints and on-premises monitoring are supported enterprise deployment options. We configure the complete setup around your organisation’s data and infrastructure requirements.
Discuss your private deployment