Coworker
Also known as: Coworker.ai, Village Platforms
Enterprise AI platform built on OM2, a permission aware organizational memory graph across 50+ connectors that read and write. It runs autonomous agents with approval gates, credit limits and audit trails, routes each task across twelve or more models with bring your own model, and offers on premises or air gapped deployment.
Coworker is an enterprise AI platform built on the idea that most company AI starts every session from zero. Its answer is OM2, an organizational memory layer that reads across more than fifty connected tools (Slack, Salesforce, Jira, Google Workspace, Microsoft 365, GitHub, Snowflake, Workday and the rest). OM2 holds what it finds as a permission aware graph of connected facts, where customers, projects, deals and people are nodes rather than raw text. Access policies live on every fact, so an answer only ever draws on what the person asking is allowed to see, and every answer traces back to its source.
On top of that sit autonomous agents that run around the clock. An Agent Builder that needs no code defines what an agent does, which tools it uses and when it runs, on a schedule or in response to events like a new Slack message, a Jira update or a CRM change. Coworker publishes a set of agents ready to adopt. An Expansion Pipeline agent finds accounts hitting usage ceilings, a Revenue Recovery agent works payment failures, and a Pipeline Cleanup agent enforces CRM discipline. An Incident Orchestrator routes and escalates incidents, and a Data Analyst agent queries data and reports on it. Every connector reads and writes, so agents update records and create tickets as well as report.
Approval gates can be added to any workflow, letting a person review, edit or reject an action before it executes. Agents can also run fully autonomously where that suits. Permissions are inherited from the customer's existing tools, credit limits cap spend, escalation logic routes what agents should not decide, and every action is logged.
A routing layer sends each task to the most suitable model across twelve or more providers, open and closed, and customers can bring their own model and run it on their own infrastructure. The same memory is reachable from Claude, Cursor, ChatGPT or Windsurf through Coworker MCP. Coworker is SOC 2 Type II, GDPR and CASA Tier 2 verified, runs on isolated single tenant infrastructure, and is available in cloud, private cloud, on premises or air gapped form. Pricing is $30 per user per month with all features included, with an Enterprise tier on application.
Vendor details
Canonical URL
https://coworker.ai
Category
Enterprise operations agent
Subcategory
Enterprise AI agent platform with organizational memory
Funding status
Seed; thirteen million dollars led by Jeff Huber (Triatomic Capital), May 2025 per company announcement
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
More than 50 OAuth connectors are offered, and every one reads and writes. About thirty five are named across the product, among them Slack, Microsoft Teams, Salesforce, HubSpot, Jira, Linear, Asana, Notion, Confluence, Google Drive, Google Calendar, Google Sheets, Google Meet, Gmail, Microsoft 365, Zoom, GitHub, VS Code, Figma, Stripe, Datadog, PagerDuty, ServiceNow, Zendesk, Intercom, Gong, Workday, ADP, SAP, NetSuite, Snowflake, BigQuery, Amplitude and Chrome. Agents pull context and push updates, updating CRM records, creating tickets, sending follow ups and drafting reports. They inherit the permissions already in place, so there is no parallel access model to maintain. Inbound, Coworker MCP exposes organizational memory, the connector set and dedicated agents to any MCP client, including Claude, Cursor, ChatGPT and Windsurf. That connection is read only by default and runs under the same SSO and permissions.
In practice
A revenue operations team deploys agents that join meetings, update Salesforce, create Jira tickets, and send follow ups automatically with approval gates on outbound actions
An IT service desk grounds its responses in organizational memory, and one customer's service desk saved thousands of hours in its first deployment phase
An engineer connects OM2 over MCP so agents in other clients get company context with fewer tool calls
Sources & related URLs
Agentic Index coverage score
11.5 / 14 capabilities · 82%
| Integrations & Tool Calling | Full |
|---|---|
|
About thirty five connectors are named on the platform and agents pages, out of a stated 50+ OAuth connectors listed in a directory at /connectors. On the platform page they cover CRM (Salesforce, HubSpot), communications and meetings (Slack, Gmail, Zoom, Google Meet, Google Calendar, Microsoft 365), docs and project work (Google Drive, Google Sheets, Notion, Confluence, Jira, Linear, Asana, Figma), engineering (GitHub, Datadog, PagerDuty, VS Code), data (Snowflake, BigQuery, Amplitude), payments (Stripe), the browser (Chrome) and the systems of record for IT service management, HR and finance (ServiceNow, Workday, ADP, SAP, NetSuite). The agents page adds Gong for sales, Zendesk and Intercom for support, and Microsoft Teams. Every connector reads and writes, so agents pull data and push updates across CRM, comms, support, docs, code and data, updating CRM records, creating tickets, sending follow-ups and drafting reports, and the published run drafts into Gmail, updates Salesforce and posts to Slack. Agents inherit the permissions already in place, with no new logins and no new SSO maps, so there is no parallel access model to drift. Chrome and VS Code appear in the OAuth connector list as ingestion paths feeding the graph, not as interface control. Sourcecoworker.ai/platform integrations section and /agents connector listread 2026-09-12 |
|
| Workflow Orchestration | Full |
|
The Agent Builder is the authoring surface, where customers create custom agents in minutes by defining what they do, which tools they use and when they run, with no code required, and set triggers, approval gates and notification preferences through a visual interface. Agent sequences span several steps and systems, and they branch. In the account agent's published run, it drafted outreach for six accounts through Salesforce and Gmail, escalated one strategic account to an AE through Slack, and posted an expansion summary to Slack, so one of the six accounts went to a person based on the state of the case. The Incident Orchestrator routes incidents, enforces escalation timers and tracks resolution, which means making a routing decision, holding a timer across a gap the agent does not control, and following an incident through to resolution. State persists across runs, agents run 24/7 in the background without anyone stepping in, and Coworker describes orchestrating several agents from a single control plane. A workflow involves the agent, the approver at a gate, the AE an account escalates to, and the connected systems each step reads and writes. Agents carry work through to the end, updating the CRM, creating tickets, sending follow-ups and drafting reports. Coworker does not describe retry, failure handling or what an agent does when a step fails. Sourcecoworker.ai/agents capabilities, agent examples and FAQ, with /platformread 2026-09-12 |
|
| Knowledge Grounding & RAG | Full |
|
OM2 reads every connected tool continuously, with no uploads or re-syncing, learns backwards over historical data at setup and keeps evolving as it sees more each day, whereas most assistants, Coworker says, fetch document chunks at query time and forget afterward. Knowledge is stored as connected facts about people, projects, customers and decisions, with customers, projects and deals, as well as people, as first class nodes rather than raw text. Recall is synthesized ahead of time rather than found at query time, relevancy-ranked by proximity, recency and centrality, with sub-second graph traversal. Retrieval is scoped by permission-aware traversal built into the graph, with access policies on every fact and connection. Every answer traces back to its source, and agents get permissioned context across Slack, CRM, docs, Jira and 50+ apps. The corpus covers messages, tickets, deals, docs, sheets, calendars, CRM, emails, meetings, transcripts, code, wikis, boards, PRs, recordings and contacts. Coworker's comparative figures (84% preference, 20% faster, 66% cheaper) are its own unaudited benchmarks. Sourcecoworker.ai/platform OM2 section with /blog/introducing-om2 and /agentsread 2026-09-12 |
|
| Human Oversight & Guardrails | Full |
|
Customers can add approval steps to any agent workflow, where a reviewer can review, edit or reject the agent's proposed action before it executes, so the hold sits on the agent's own action and the reviewer can amend it as well as approve or deny it. Both modes are supported, with agents running fully autonomously for routine tasks or with approval gates on any workflow so a person reviews and approves actions before they execute. Background runs work the same way, notifying the team when done so they can review the output and approve actions before they go live. Permissions, approvals, credit limits and escalation logic are named together as controls, and a credit limit is a hard spending stop on an autonomous agent that does not depend on anyone noticing. Escalation logic appears in the products too, with the Incident Orchestrator enforcing escalation timers and the account agent escalating one strategic account to an AE. Agents inherit the permissions already in place, with no new logins and no new SSO maps, so an agent cannot go beyond the authority of the person it acts for. Sourcecoworker.ai/agents capabilities and FAQ, with /platformread 2026-09-12 |
|
| Security, Identity & Governance | Full |
|
Coworker holds SOC 2 Type II, GDPR compliance and CASA Tier 2, shown as three badges on the platform page that each link to a Secureframe trust portal at village-labs.secureframetrust.com. Identity and access controls include SSO, RBAC, and encryption at rest and in transit, and SSO is part of the Enterprise entitlements. Permissions reach down to each fact, since Coworker is permission-aware by construction, with access policies on every fact and connection, so everyone sees only what they are allowed to see through traversal of the graph that respects permissions. Because the graph pulls Slack, CRM, email and HR systems together, that authorization on each fact governs what every user can reach. Agents inherit the permissions already in place, with no new logins and no new SSO maps, so there is no privilege elevation and no parallel access model to drift. Isolated single tenant infrastructure and complete audit trails across the platform add to this, along with a commitment never to train models on customer data and published legal agreements, namely a privacy policy, terms and a Master Services Agreement. The agents page says agents tap into 100k+ deployed agents' learnings, which reads as learning across customers and sits against the statement that customer data is never used to train models, and Coworker does not say whether the shared learnings are behavioral patterns rather than customer content. Sourcecoworker.ai/platform enterprise-grade section and FAQ, with /pricingread 2026-09-12 |
|
| Observability & Auditability | Full |
|
Every action is logged and every decision auditable, with guardrails the customer sets and audit trails the customer owns, and the agents FAQ says every action in autonomous runs is logged for full auditability. Complete audit trails across the platform are listed among the enterprise controls beside permissions and identity, and logging every action records what the agent did, not only what it produced. Answers are attributed separately in OM2, where every answer traces back to its source, so a conclusion can be walked back to the fact and the connected tool it came from. Coworker gives no detail on the audit trail itself, with no stated retention period and no word on whether it can be exported or filtered, whether it captures reasoning as well as actions, or whether it exists below the Enterprise tier. Sourcecoworker.ai/agents and /platform enterprise-grade section, with /blog/introducing-om2read 2026-09-12 |
|
| Memory & State Persistence | Partial |
|
OM2, which replaced OM1 as the headline layer, is built by reading the customer's connected tools continuously, with no uploads or re-syncing, and learns backwards over historical data at setup. Agents use the graph to track progress, learn from corrections and continuously improve, and memory compounds with every interaction, so learning from corrections is written by the agent as well as absorbed into the product. Scoping rests on isolated single tenant infrastructure, access policies on every fact and connection, and permission aware traversal, with permissions per user in the native apps. Coworker states no retention period, expiry, purge or deletion path for the memory. The only published retention figure is 90 days for recorded meetings on the Enterprise tier. Coworker MCP is one connection, read-only by default, so the graph can be read and inspected there and in the native apps, with permissions on each fact, but nothing lets a customer or an outside caller edit, correct or delete a fact in it. Sourcecoworker.ai/platform, /agents and /blog/introducing-om2read 2026-09-12 |
|
| Deployment & Data Residency | Full |
|
Isolated single tenant infrastructure is offered in four forms, cloud, private cloud, on premises or air gapped, and on premises and air gapped installs sit in the customer's own environment, so the customer decides where data rests. Coworker is SOC 2 Type II, GDPR and CASA Tier 2 verified, with SSO, RBAC, encryption, audit trails and air-gapped deployment support. Single tenancy is the baseline, and the OM2 memory runs on isolated single-tenant infrastructure in Coworker's cloud or via VPC. VPC peering and bring your own model on the customer's own infrastructure are further options, so a customer who cannot send data to a shared service has three published routes. The homepage says routing is all hosted in the US and the OM2 announcement leads with cloud and VPC, while the platform page states the full range. There is no named region list for the hosted option, no residency selection for cloud customers, and no page on what an air gapped deployment costs, excludes or requires. Routing across twelve providers is hard to square with an air gapped install, and bringing your own model on the customer's infrastructure may resolve that, though Coworker does not say so. Sourcecoworker.ai/platform OM2 security line and FAQread 2026-09-12 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
A catalog of agents is published, each described and tagged by role. Expansion Pipeline, for Account Management, finds accounts hitting usage ceilings and generates upgrade outreach, and Revenue Recovery, for Finance, processes payment failures with segment-specific recovery playbooks. Pipeline Cleanup, for Sales Ops, enforces CRM discipline on stale deals, past due dates and missing data. Incident Orchestrator, for Engineering, routes incidents, enforces escalation timers and tracks resolution, and Data Analyst, for BI and Analytics, queries data, builds reports and surfaces insights automatically. Three more are named in the deployment section, Post-Meeting Actions for Sales, Contract Review for Legal and Bug Triage for Engineering, and the agent picker offers Account, MCP, Engineering, BI, Legal, Meetings, Finance and Sales as classes. Each agent works on its own and serves a different function on different objects for different teams in the same company. Once a tool is connected, the product learns in minutes and suggests agents suited to the user's role, so the catalog proposes agents from what a customer connects. OM2 carries shared skills and artifact templates that travel across models and do work when selected, and use case pages by function, one each for Sales, Engineering, Customer Success, Support, Product, Marketing, People, Operations and Industries, make the catalog browsable. The named agents each appear as a card with no page of their own, and no count of the full library is given. Sourcecoworker.ai/agents agent set and role suggestions, with /platform OM2 skillsread 2026-09-12 |
|
| Triggers & Channel Coverage | Full |
|
Agents start on a schedule, on real time events or manually. Scheduled triggers run agents for daily briefings, weekly reports and hourly monitoring. Custom triggers start agents on new Slack messages and Jira updates, CRM changes and calendar events, four event sources in four systems. Agents work where the team already works, running in Slack, joining meetings and updating boards instead of living in another tab. The Coworker Native Apps (Work, Chat, Build, Meetings, Agents, Artifacts) are Coworker's own surfaces, and Coworker MCP puts the same agents inside Claude, Cursor, ChatGPT and Windsurf. Email appears in the agent examples, which draft outreach through Gmail. Agents run 24/7 in the background without anyone stepping in and send a notice when done, and none of this is held to one tier. Coworker does not say whether a customer can define a compound or conditional trigger beyond the four named event types. Sourcecoworker.ai/agents capabilities and FAQread 2026-09-12 |
|
| Model Flexibility & Routing | Full |
|
Coworker routes each task to the optimal model across closed, open-source and self-hosted providers, balancing cost, latency and accuracy, with every task routed to the cheapest model that meets the quality bar. It names 12+ model providers, among them OpenAI, Anthropic and Google, plus open source Llama, Mistral and MiniMax. With BYOM, a customer can bring its own models and run them on its own infrastructure. As better models ship, teams get them automatically with no migration and no vendor lock-in, and OM2's memory and skills travel with the customer whatever model it chooses. Coworker MCP, on the same page, lets the customer's own assistant reach Coworker's memory. Coworker does not say whether an administrator can pin a specific model per agent or can only rely on automatic routing. Sourcecoworker.ai/platform routing section and FAQread 2026-09-12 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Coworker MCP, a product with its own page, puts org memory, 50+ tools and dedicated agents inside any MCP client through one connection that is read-only by default and uses the same SSO and permissions, with Claude, Cursor, ChatGPT and Windsurf named as clients. OM2 also connects through MCP or an API, so Coworker's memory can be used outside Coworker in any MCP-compatible client. Through it the customer's assistant calls Coworker, and because dedicated agents sit inside any MCP client, an outside assistant can invoke a Coworker agent that updates CRM records, creates tickets and sends follow ups. The agent picker lists MCP as one of its surfaces alongside Account, Engineering, BI, Legal, Meetings, Finance and Sales. The connection reads by default, and the wording implies write access can be configured, but Coworker does not say how or what a write scope covers. Permissions and SSO come from the same identity, so the surface does not widen a customer's exposure. The memory is sold as one memory for every surface, with skills traveling too. Coworker publishes no tool list, endpoint reference, SDK or OpenAPI document, and the API named in the OM2 post has no published reference. Sourcecoworker.ai/platform portability section and FAQ, with /blog/introducing-om2read 2026-09-12 |
|
| Testing, Debugging & Optimization | Not documented |
|
There is no sandbox, dry run, simulation or staging workspace, no holdout, A/B comparison or versioning and rollback of an agent configuration, and no evaluator, scored result or regression surface. In the deployment lifecycle the agents FAQ walks through, a customer builds an agent in the Agent Builder and it runs, with no test step. The platform is organized around five layers, OM2, Routing, Portability, Integrations and Enterprise Grade, and none of them covers evaluation. The Optimize and scale step says memory compounds with every interaction, which describes the memory layer growing. Agents are said to get smarter with use, observe the team's patterns and suggest new automations, and get smarter every week as they learn how the team works. Approval gates let a person review, edit or reject each action before it executes. Sourcecoworker.ai/agents and /platformread 2026-09-12 |
|
| Browser & Computer Use | Not documented |
|
Data comes in through OAuth connectors feeding the graph, actions go out as connector writes that update CRM, create tickets and send follow-ups, and the outside surface is an MCP server. Coworker presents OM2 as replacing work at the interface, using sub-second graph traversal in place of brute force tool calling. Nothing operates a screen, and all fifty connectors are OAuth APIs. Chrome and VS Code appear among the OAuth connectors on the platform page, in the list of connectors feeding the graph alongside Slack, Snowflake and Workday, and what is read from them includes code, PRs and recordings, all ingested into the knowledge graph. Coworker has no hosted or local browser, desktop session or remote computer control, and no RPA, recorder or extension that acts on a page. Sourcecoworker.ai/platform integrations list and /agents context listread 2026-09-12 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Pricing
Priced on application. Coworker sells one Enterprise plan with every product included, scoped with the customer before purchase.
One Enterprise plan priced on application, tailored to the connectors needed, the number of people, and the deployment and support. The plan lists its entitlements instead of a price: custom credit allocation, all connectors plus custom ones for internal systems, Customer Intelligence, OM1/OM2 organizational memory, 90 day meeting retention, SSO, custom SLAs, implementation services and a dedicated Customer Success Manager.
What is public
Coworker publishes a pricing page with one Enterprise plan and no price. The plan includes all products and features and is priced on application, tailored to the connectors, the number of people, and the deployment and support. No per user price and no free trial appear on it. A Coworker blog post gives a per user figure of $29.99 per month.
Billing mechanics
Quoted per organization on the single Enterprise plan, with all features included. Deployments are scoped with the implementation team before the customer commits, without months long professional services. The plan carries custom credit allocation, SSO, custom SLAs, implementation services and a dedicated CSM.
Cost watchouts
Enterprise deployments in private cloud, on premises or air gapped are scoped separately, and their price is not published. On the Enterprise tier, consumption runs through a custom credit allocation, and what happens past it is not published.
Variable cost rationale
No usage meter is published. The Enterprise price is tailored to the connectors needed, the number of people, and the deployment and support, so the bill grows with headcount and scope. Model usage is not billed on top, and closed models carry no markup. Coworker routes work across model providers and pitches that routing as a saving, with an LLM cost calculator and a claim of frontier quality output for roughly 80% less. Credits are the one consumption mechanism, and they sit on the Enterprise plan as a "custom credit allocation". Credit limits also appear as a guardrail in the agent controls, so the allocation works as a budget. No page says whether going past it is billed, throttled or blocked.
Additional watchouts
Enterprise is the only plan and its price is not published, so every purchase runs through Book a demo and a scoping conversation. The plan carries a custom credit allocation, and nothing published says whether exceeding it is billed, throttled or blocked. Self hosted options are priced separately, and their price is not published.
Sales call required
Mixed (some tiers require a call)
Free / trial
None published
Lowest paid plan
Not published
Key ambiguities
The pricing page at coworker.ai/pricing is linked from the primary navigation of every page and offers one plan, Enterprise, with every product included and no price. Enterprise pricing is "tailored to your organization: the connectors you need, the number of people, and the deployment and support that fit." A Coworker blog post states $29.99 per user per month twice, and no per user price appears on the pricing page. There is no free tier and no free trial. The way in is "Book a demo," after which the Coworker team scopes what is needed and sets up the workspace. There is no self serve purchase. A sign in exists at app.coworker.ai, but every primary call to action across the homepage, platform, agents and pricing pages is "Book a demo." Credits are the one consumption mechanism. The Enterprise plan includes "custom credit allocation," and credit limits appear as a named guardrail in the agent control set, so a credit system exists and is administered. Nothing published says whether exceeding an allocation is billed, throttled or blocked.
Missing data
The Enterprise price, which is stated only as a set of entitlements and the factors it is tailored to. Whether exceeding the custom credit allocation is billed, throttled or blocked. Any minimum seat count.
Related vendors
- 11th Estate — Agentic platform whose AI engine scans markets, matches an…
- Abacum — FP&A platform for growing companies whose AI Modeler builds, edits…
- Adopt AI — AI native accounting and bookkeeping firm whose agents run…
- Aera Technology — Decision intelligence platform where an always on agent executes…
- Akro AI — On premise operational intelligence that automates document heavy…
- alfred_ — AI executive assistant that triages the inbox overnight and scores…
Alternatives to Coworker
The closest documented capability profiles to Coworker among enterprise operations agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Glean12.0 / 14Adds documented Testing, Debugging & OptimizationCoworker vs Glean →
- Workato12.0 / 14Adds documented Testing, Debugging & Optimization
- Boomi12.5 / 14Adds documented Testing, Debugging & Optimization
- Clio10.5 / 14A lighter documented profile than Coworker
- Dust12.5 / 14Adds documented Testing, Debugging & Optimization
- Harvey12.5 / 14Adds documented Testing, Debugging & Optimization
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded