Sommelier
Sommelier is a free, open-source Excel add-in that bridges your workbook to an AI agent running on your own infrastructure. Instead of uploading sensitive spreadsheets to Copilot or cloud-based AI services, you pair the add-in with a local agent using a setup prompt and private connection key. The agent can read cell values and ranges on request, propose edits for your review, and generate charts inside the workbook. All traffic between Excel and the local bridge is encrypted, and the relay cannot access workbook contents. Installation requires Node.js 22.12+ and manual sideloading of the add-in manifest into Excel.
Sommelier is a free. InnovaAI scores it 4.2/10 for agency adoption, best for Operations Manager, Finance Manager, and Project Manager roles handling weekly client-facing work.
Agency Audit
Sommelier connects Excel workbooks to a local AI agent without routing sensitive data through third-party cloud services. The add-in lets teams ask their agent to read cells, propose changes, and generate charts directly inside Excel while keeping all workbook traffic encrypted between the spreadsheet and a self-hosted bridge. This is most valuable for agencies handling client financial data, campaign performance sheets, or proprietary analytics that cannot be shared with Copilot or other cloud-based AI assistants. Operations teams and Finance roles benefit most from the privacy-first architecture.
3recommended
24/mo
No paid plan published
Moderate
Illustrative scenario. Not a guarantee. Net capacity needs a verified paid base plan, and none is published for this service, so it is not modeled. Hours saved come from the service estimate; implementation, taxes, and unprovided usage charges are excluded.
- Operations Manager handling confidential budget and spend analysis
- Finance Manager handling campaign performance data queries
- Project Manager handling financial model review and updates
- Your team relies on Microsoft Copilot for Excel or other cloud-based AI spreadsheet tools and does not have privacy constraints that prevent their use.
- You do not have in-house DevOps or technical staff who can manage Node.js infrastructure and keep a local agent running during work hours.
- Your spreadsheet workflows are light and do not justify the overhead of running a local agent bridge just to ask occasional questions about cell values.
Internal Adoption Path
No paid plan published
24 hr/mo
3 seats × 8 hr each
$1,800/mo
modeled at $75/hr labor rate
No paid plan published
Illustrative scenario. Not a guarantee. No verified paid base plan is published for this service, so subscription cost and net capacity are not modeled. Implementation, taxes, and unprovided usage charges are excluded.
Platform Features
Core capabilities of Sommelier
Local agent pairing without cloud relay
Connects your Excel workbook directly to an AI agent running on your own infrastructure. The setup prompt includes a private connection key, and workbook traffic is encrypted between Excel and the local bridge so the relay cannot read sensitive data. Eliminates the need to share spreadsheets with Copilot or external AI services.
Cell reading and range queries
Allows the paired agent to request specific cell values or ranges from the open workbook on demand. Operations and Finance roles can ask the agent to summarize budget rows, extract campaign metrics, or pull historical data without manually copying and pasting into a chat interface.
Proposed changes with review gate
When the agent suggests edits to the workbook, Sommelier displays the changes for human approval before applying them. Project Managers and Analysts retain control over data integrity and can reject or modify suggestions before they are committed to the sheet.
Chart creation via agent commands
The agent can generate charts inside the workbook based on cell data or user requests. Saves time for Strategists and PMs who would otherwise manually select ranges and format visualizations for client presentations or internal dashboards.
Self-hosted relay and bridge components
Sommelier publishes instructions for self-hosting the relay and bridge on your own servers, giving teams full control over data residency and network isolation. Meets compliance requirements for agencies handling regulated client data or operating in restricted jurisdictions.
Manual Excel add-in sideload installation
Sommelier is installed by downloading an XML manifest and sideloading it into Excel, avoiding app store dependencies or automatic updates. Gives IT teams explicit control over rollout timing and version management across the agency.
What Makes Sommelier Different
Unique advantages vs similar tools in this niche
Keeps workbook data out of third-party AI services by routing through a local encrypted bridge
vs Microsoft Copilot in Excel, which sends data to a hosted model providerThe site states workbook traffic is encrypted between Excel and the local bridge and the relay cannot read it.
Works with the user's own agent harness rather than a fixed built-in assistant
vs Vendor-locked spreadsheet AI assistantsUsers copy a setup prompt into their chosen agent, which controls what it sends to its model provider.
Free and open source with a self-host option
vs Paid proprietary spreadsheet AI add-insThe site labels it 'Free and open source' and links to a GitHub repository and self-host page.
Latest Updates
Recent releases and improvements for Sommelier
Work in Excel with YOUR personal agent.
NewConnect Excel to your agent, running in your favourite harness. You don't need to give Copilot access to data you don't want to share!
Value Equation
Outcome-likelihood-time-effort assessment for Sommelier
Value math requires real pricing
The Value Equation (dream outcome × likelihood ÷ time × effort) feeds directly into ROI math. Sommelier has no published pricing, so we hold this section until real numbers are available.
Contact SommelierPricing
Pricing data not yet available for Sommelier.
Reality Check
Sommelier requires Node.js 22.12+ and a local agent running continuously during work sessions, which adds infrastructure overhead compared to cloud-based Excel AI tools. Setup involves manual sideloading of the add-in and pairing with your chosen agent, not a simple one-click installation. Teams without existing local AI infrastructure or those preferring managed solutions will face higher initial friction.
High effort: requires technical configuration and team training
How This Accelerates White-Label Services
Who It's For
- ✓agencies-working-heavily-in-excel
- ✓teams-with-privacy-sensitive-spreadsheet-data
- ✓users-running-their-own-local-ai-agents
Acceleration Steps
- 1Schedule onboarding with the vendor
- 2Configure connect excel workbooks to a personal ai agent running in a local harness
- 3Launch your first client project
Academy for Sommelier
Work through it in order: the course for this service first, then the modules behind it.
No Academy modules are published for this service yet. Browse the full Academy
Why this category matters
The commercial case before the tooling.
Core concepts
The mental model you need to price and scope the work.
- Wiring Over WidgetsConcept
The AI agent itself is a commodity, but the value for agencies lies in the integration layer: connecting a pre-built agent to a client's CRM, calendar, and review cycle. This framework shifts focus from selecting the 'best' agent to mastering the wiring process. For example, an agency using Vendasta's white-label AI receptionist for a local business must configure it to match the client's booking rules and follow-up cadence, turning a generic tool into a tailored service. As agentic AI adoption grows (77% of decision-makers now run agents in production), clients expect this customization. Agencies that treat agents as components and invest in repeatable wiring processes can charge retainers for ongoing optimization, rather than one-off setup fees.
- Wiring Over WidgetsConcept
The AI agent market sells finished workers, but the strategic value for agencies lies not in the agent itself, which is increasingly a commodity, but in the wiring that connects it to a specific client's CRM, calendar, and review cycle. This framework, 'Wiring Over Widgets,' argues that agencies that treat agents as components rather than products win. The agent is the widget; the wiring is the integration, customization, and ongoing optimization that turns a generic tool into a tailored solution. For example, a white-label platform like Vendasta provides AI employees, but the agency's role is to configure them for each local business's unique lead flow and follow-up process. This wiring is where retainer pricing originates, as it requires ongoing maintenance and adjustment. Recent research shows that 88% of B2B marketers face foundational gaps, meaning clients need help not just deploying agents, but ensuring their operations can support them. Agencies that master the wiring can charge a premium for the irreducible value they add.
- Integration MoatConcept
The Integration Moat framework holds that the durability of an AI agent engagement is determined by how deeply the agent is wired into a client's existing systems, not by the agent's underlying capability. Since the agent itself is increasingly a commodity, the switching cost for the client lives in the integrations: the CRM fields mapped, the calendar sync, the review-cycle triggers, and the exception-handling rules. Agencies that invest in this wiring create a moat that competitors offering generic agents cannot cross. For example, a white-label platform like Vendasta lets an agency deploy an AI receptionist for a local business, but the real value is in configuring it to the client's booking flow and follow-up cadence. With 77% of AI decision-makers now running agentic AI in production, clients expect this depth, and agencies that deliver it convert one-off projects into retainers.
Decision and risk
How to judge the fit, and the ways it goes wrong.
- AI Agents Rule: Wire the Agent, Not the ProductEvaluation Rule
Treat the AI agent as a commodity component and focus your value on the integration into the client's specific workflows, systems, and review processes.
- AI Agents Rule: Wire the Agent, Not the ProductEvaluation Rule
Treat the AI agent as a commodity component and charge for the integration into the client's specific systems and workflows.
- The Productized Agent Trap: Why AI Agent Services Stall Without Client-Specific WiringFailure Pattern
- The Agent-as-Product Trap: Why AI Agent Services Stall Without Client-Specific WiringFailure Pattern
8 modules selected for Sommelier
Frequently Asked Questions
Answers about pricing, setup, implementation
Sommelier is an Excel add-in that connects your workbook to a personal AI agent running in a local harness on your infrastructure. You can ask the agent to read cell values, propose changes to the spreadsheet, and create charts, all without leaving Excel. All workbook traffic is encrypted between Excel and a local bridge, so sensitive data never reaches a cloud relay or third-party AI service.
Sommelier is free and open source. There are no per-seat fees, subscription tiers, or licensing costs.
Operations and Finance teams benefit most when managing confidential client budgets, media spend, or performance data that cannot be shared with cloud AI tools. Project Managers gain efficiency when asking an agent to summarize campaign metrics or propose dashboard updates. Strategists save time on chart creation and data visualization. Any role working with sensitive spreadsheets in Excel and requiring privacy-first AI assistance is a good fit.
Savings depend on how frequently your team asks AI questions about spreadsheet data. A Finance or Operations role working with complex models or dashboards 5+ hours per week could reclaim 2 to 4 hours per week by eliminating manual copy-paste into chat interfaces and waiting for cloud-based AI responses. Teams with lighter spreadsheet workflows or those already using cloud AI tools will see lower time gains.
Sommelier requires Node.js 22.12 or later and an AI agent with shell access running on your local machine or internal server. The agent must remain listening while you work in Excel. You will also need to self-host the relay and bridge components if you want to avoid any external traffic, though Sommelier provides setup instructions for this.
Sommelier is optimized for single-user or small-team workflows where one person is actively working in the spreadsheet while the agent is paired. Real-time multi-user collaboration in Excel is not a primary use case, since each user would need their own agent instance and the local-bridge architecture is not designed for concurrent edits across many seats.