Conveyor
Also known as: ConveyorAI, Conveyor Trust Center Agent
Customer security review platform whose AI completes incoming questionnaires with cited answers and whose Trust Center Agent lets buyers self serve the whole review, including uploading a questionnaire and getting it answered without the vendor's team involved.
Conveyor works on customer security reviews from both ends. On the seller side, ConveyorAI ingests security questionnaires and completes them with cited answers drawn from a knowledge base of approved policies, documents and past responses. On the buyer side, an agent-powered Trust Center lets the customer self-serve, and the Trust Center Agent answers their questions directly inside the portal instead of leaving them to dig through an information dump.
That second half is the strategic idea. Trust centers that grow too large to navigate push enterprise buyers back to demanding a manual response or a call, which puts the security team back in the loop it was trying to escape. Conveyor's answer is to embed the AI into the portal so a buyer can simply ask, including uploading a full standard questionnaire and having it completed without a human on the vendor side ever touching it. The company calls this a touchless security review, and the trigger sits with someone outside the customer's own organization.
The agent operates across the channels the work actually arrives on. It processes cases, tickets and Slack messages carrying uploaded questionnaire files, triages what comes in, updates stakeholders on status, and asks follow-up questions when it needs more information. For responses that must be filled in someone else's system, a Chrome extension autofills questionnaires directly inside third-party customer portals instead of forcing copy and paste between windows.
An AI Connector built on the Model Context Protocol puts the same knowledge inside Claude, ChatGPT, Notion AI and other assistants, carrying each person's existing permissions and able to approve Trust Center access or update knowledge as well as answer questions. A separate RFP path adds document automapping, go/no-go and red flag identification, rules-based routing to subject-matter experts, in-document Word editing and version controls.
Underneath, a Knowledge Librarian monitors and cleans the corpus so answers stay current, and analytics cover trust center engagement, AI accuracy, RFP insights and revenue impact. Conveyor holds SOC 2 Type II audited by Linford & Company, published through its own trust center, with SSO, SCIM provisioning and role-based permissions at the enterprise tier and portal access governed by NDA gating, access groups and document watermarking.
Deployment is multi-tenant cloud with no region selection or self-hosted option. Audit logging is documented over the AI assistant channel but not over the touchless path, which is the run with no human in it. Pricing is usage-based, not per-seat, with a free trust center tier, a Business plan from $9,600 a year, and Enterprise quoted on volume.
Vendor details
Canonical URL
https://www.conveyor.com
Category
GTM / revenue agent
Subcategory
Customer security review and trust center automation
Funding status
Independent. Legal entity Conveyor Inc. Customers named on its own property include Atlassian, Carta, dbt Labs, Zapier, Lucid, Cvent, Sinch, Instructure, TrueContext and Temporal. No funding figure is published on the property; press reports a Series B in 2025.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Named integrations across four classes, with the vendor stating explicitly that integrations carry no charge: Salesforce, delivered as a managed package, and HubSpot for CRM; Jira and Zendesk for ticketing; Slack for collaboration; DocuSign for NDA e-signature; and a published directory carrying more. The agent reads work out of those queues rather than only writing to them, picking up cases, tickets and Slack messages carrying questionnaire files, and reports security review effort back to Salesforce so the work ties to deals. Two further surfaces extend reach: a Chrome extension that autofills questionnaires inside third-party customer portals, and an MCP server at mcp.conveyor.com that connects Claude, ChatGPT, Notion AI, Atlassian Rovo, Glean and Cursor, carrying each user's existing Conveyor permissions and able to take actions as well as answer. A public API and developer documentation sit behind both.
In practice
A prospect's security team sends a 300 question standard questionnaire. They can upload it into your trust portal and the Trust Center Agent completes it, so nobody on your side opens the spreadsheet at all.
Your reps work inside Claude all day and keep interrupting security for one off answers. The Connector for Claude gives them cited answers and completed questionnaires without a handoff.
A questionnaire has to be filled inside the buyer's own portal. The browser extension autofills it in place, so no answers are copied between windows.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
9.0 / 14 capabilities · 64%
| Integrations & Tool Calling | Full |
|---|---|
|
Named integrations span several classes, and Conveyor does not charge for them. They cover CRM in Salesforce, delivered as a managed package, and HubSpot, ticketing and ITSM in Jira and Zendesk, collaboration in Slack and e-signature in DocuSign, with a published directory carrying more. The agent reads work out of those systems as well as writing to them, processing cases, tickets and Slack messages that arrive carrying questionnaire files, and reports security review effort back into Salesforce so the work ties to deals. A browser extension carries the platform into third-party portals and the MCP server carries it into AI assistants. There are no charges for integrations, so the connector set is not a tier lever. Sourceconveyor.com/integrations and conveyor.com/pricingread 2026-09-04 |
|
| Workflow Orchestration | Full |
|
Agents hand work along a chain that runs from intake to a returned document, on both sides of the review. Inbound, sales triage sorts what arrives and the agent processes cases, tickets and Slack messages carrying questionnaire files end to end, updating stakeholders on status and asking follow-up questions when it needs more. The Knowledge Librarian maintains the corpus underneath. On the RFP side the chain is longer, running through agentic document automapping, go/no-go and red flag identification, AI drafted answers grounded in briefs, deal docs and win themes, rules-based SME auto-assignment, in-document Word editing, and audit and version controls. On the buyer side the Trust Center Agent completes an uploaded questionnaire without anyone on the vendor side opening it. Each agent is priced as a separate capability. Sourceconveyor.com/ai-agents-for-security-reviews and conveyor.com/pricingread 2026-09-04 |
|
| Knowledge Grounding & RAG | Full |
|
Answers are grounded on the customer's own approved security corpus, which is actively maintained, not merely stored. A centralized knowledge base holds security documentation, compliance policies, past answers and organizational knowledge, and the AI connects to any source, including websites, shared drives, help centers and docs, so the material stays where teams keep it. A Knowledge Explorer and an AI Librarian curate it, with Q&A management and multi-product answer tagging so the right posture is used for the right product line. Retrieval runs on a RAG engine, not open generation, every answer cites its work, and a connected assistant answers only from approved content with the user's permissions attached, not by guessing from training data. The corpus also grows across reviews, and it remains the customer's content, not agent memory. Sourceconveyor.com/products/knowledge-management and conveyor.com/pricingread 2026-09-04 |
|
| Human Oversight & Guardrails | Partial |
|
Review exists on the seller's side and is deliberately absent on the buyer's, which is the product's central design choice, not an oversight. First-pass drafts are reviewable before they go back, the RFP path identifies red flags and runs go/no-go before work starts, rules-based auto-assignment routes questions to the named subject-matter expert and the AI notifies them, audit and version controls sit over RFP documents, and answers are bounded to approved content so the agent cannot draw on anything the team has not sanctioned. The flagship path removes the human by design. In Conveyor's touchless security review a buyer uploads a questionnaire into the trust portal and the Trust Center Agent completes and returns it without anyone on the vendor side opening it, and there is no approval gate, confidence threshold or hold on that path. Access controls on the portal, NDA gating, access groups and domain-based approval automation govern who may see documents, not what the agent may say. Sourceconveyor.com/products/security-questionnaire-automation and conveyor.com/products/trust-centerread 2026-09-04 |
|
| Security, Identity & Governance | Full |
|
The access surface is a named entitlement. Enterprise settings list enterprise roles and permissions as RBAC, and single sign-on with SCIM provisioning, and Conveyor supports user provisioning through Okta and other identity providers. Those permissions reach past the console. A person connecting an AI assistant through the MCP server sees only what their existing Conveyor role already allows, and revoking access in Conveyor revokes it for the assistant. Trust Center access is itself governed by access groups, domain-based approval automation, clickwrap NDA gating and auto-watermarking of downloaded documents. Behind that sit SOC 2 Type II covering Security, Availability and Confidentiality, audited by Linford & Company LLP with reports available for review through Conveyor's own trust center at trust.conveyor.com, a published security policy and a responsible disclosure program, API keys scoped to least privilege, and infrastructure on Aptible Deploy, itself SOC 2 Type 2 and HITRUST validated. SSO, SCIM and RBAC sit on the Enterprise tier. Sourcetrust.conveyor.com and conveyor.com/pricingread 2026-09-04 |
|
| Observability & Auditability | Partial |
|
Every question coming through a connected AI assistant is visible to the team in audit logs, giving a full picture of what is being asked and how it is being answered even when nobody on the team answered it, and answers carry citations back to approved sources. Around that sit analytics on Trust Center engagement and requests, ConveyorAI performance and accuracy, RFP response insights, business and revenue impact, CSAT on Trust Center responses, and audit and version controls on RFP documents. The audit log covers the MCP assistant channel, and nothing extends it to the touchless path, the product's headline capability, in which a buyer uploads a questionnaire into the trust portal and the Trust Center Agent completes it with no vendor-side human involved. That is the run most in need of a reconstructable record, and it has none. Sourceconveyor.com/products/analytics and conveyor.com/pricingread 2026-09-04 |
|
| Memory & State Persistence | Not documented |
|
Past answers and security documentation persist in a centralized knowledge base that grows with each completed review, and the Knowledge Librarian monitors and cleans it so what is read back stays current. That is the customer's content, and a content store is not memory. The agents keep no memory construct they write and read back as their own state, with no per buyer or per engagement recall and no retention or forgetting control at the agent level. Sourceconveyor.com/products/knowledge-managementread 2026-10-01 |
|
| Deployment & Data Residency | Not documented |
|
Multi-tenant cloud hosting comes with no location or topology control. The only hosting choice is between a portal hosted by Conveyor on its own domain and a custom domain such as trust.companyname.com, which is branding, not deployment control, and does not move where anything runs. There is no region selection, EU or other in-region option, private cloud, VPC, single-tenant tier or on-premises route. Infrastructure runs on Aptible Deploy over AWS, which Conveyor describes as continuously audited and carrying ISO 27001, FedRAMP, DoD CSM and PCI DSS, but those are the provider's certifications and say nothing about a region the customer selects. Residency is a routine line in the very questionnaires the platform exists to complete, since its function is publishing and answering security posture for enterprise customers. Sourcetrust.conveyor.com and conveyor.com/pricingread 2026-09-04 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Conveyor ships a named set of prebuilt agents, each a product doing its own job. Its plans list the Trust Center Agent, Knowledge Librarian, the questionnaire automation agent, the AI RFP responses agent, the portal browser extension and the sales triage agent as entitlements, and the Free plan carries the Trust Center while questionnaire automation and integrations sit on Business, so the customer selects among them by plan. Each stands without the others. The Trust Center Agent answers buyers in the portal, questionnaire automation completes incoming files, the RFP agent works bids, and the librarian maintains the corpus. Sourceconveyor.com/pricing and conveyor.com/ai-agents-for-security-reviewsread 2026-10-01 |
|
| Triggers & Channel Coverage | Full |
|
Work comes in from several directions, and one of them is the buyer, not the seller. Inbound sources are cases, tickets and Slack messages carrying questionnaire files, Jira and Zendesk queues, questionnaires imported in any format, the browser extension picking up a questionnaire inside a third-party portal, connected AI assistants through the MCP server, and the buyer-facing trust portal. There a prospect uploads a standard questionnaire and the Trust Center Agent completes it with no action on the vendor side, work that arrives from outside the customer's organization. Outbound, it returns completed documents in the original format, Slack and Salesforce updates, stakeholder and SME notifications, and answers inside the assistant a rep already uses. Sourceconveyor.com/products/trust-center and conveyor.com/pricingread 2026-10-01 |
|
| Model Flexibility & Routing | Not documented |
|
The customer does not choose the model and no provider is named. There is no model list, routing policy, per-agent selection or bring-your-own-key option. Conveyor says only that it continuously improves its models and calls the engine RAG-based, which is architecture, not choice. Claude, ChatGPT, Notion AI, Atlassian Rovo, Glean and Cursor appear as connector clients, but those are the assistants a customer already uses calling Conveyor through MCP. That is the customer picking the interface that reads Conveyor, the opposite of choosing what powers the product. Conveyor makes the point itself, contrasting an assistant guessing from general training data against one drawing on Conveyor's approved knowledge base. Sourceconveyor.com/products/ai-connector and conveyor.com/pricingread 2026-09-04 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Conveyor offers an MCP server that acts, a public API behind it, and developer documentation for both. The AI Connector is a server built on the Model Context Protocol at mcp.conveyor.com/mcp, added as a custom connector through OAuth with no engineering work, and Conveyor names Claude, ChatGPT, Notion AI, Atlassian Rovo, Glean and Cursor as clients plus anything else supporting the standard. It executes as well as reads. A connected assistant answers from the approved knowledge base, pulls analytics and reports, and takes actions including approving Trust Center access and updating knowledge, with each person's existing Conveyor permissions carried through so the assistant sees only what that user may already see. A public API is a listed Enterprise entitlement alongside SSO and SCIM, and documentation sits at docs.conveyor.com with an MCP server reference. No SDK or client library is published. Sourcedocs.conveyor.com/reference/mcp-server, conveyor.com/products/ai-connector and conveyor.com/pricingread 2026-09-04 |
|
| Testing, Debugging & Optimization | Partial |
|
ConveyorAI performance and accuracy is a shipped analytics surface, so a customer reads how the agent itself is doing, alongside RFP response insights, Trust Center engagement and CSAT on responses the agent gave to buyers, and continuous data monitoring and cleaning runs against the corpus. Nothing compares configurations under control. There is no scored evaluation set, benchmark suite, regression check when the knowledge base or instructions change, or sandbox before an answer reaches a buyer. Conveyor's published 95%+ accuracy figure is its own claim and the free-trial stress test is a pre-sales exercise, and neither is a mechanism the customer holds. Sourceconveyor.com/products/analytics and conveyor.com/pricingread 2026-10-01 |
|
| Browser & Computer Use | Partial |
|
Conveyor's Chrome extension fills questionnaires inside portals Conveyor does not control. It comes in two modes, a browser extension for one-off search and a browser extension for customer portals, and the second autofills questionnaires directly inside third-party platforms, so answers need not be copied between windows. The portal extension is listed among the named agents with its own accuracy band. Procurement and vendor-risk portals are the classic case of software with no programmatic interface. Coverage is limited to supported portals, not general browser or computer control, and there is no headless session, virtual desktop or arbitrary navigation. Sourceconveyor.com/pricing and the Conveyor Chrome Web Store listing; chromewebstore.google.com/detail/conveyor/djkpbjhiilodaficngfbddkhaendinhhread 2026-09-04 |
|
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
Product updates
Conveyor released its rebuilt Agentic Answer Engine, which uses sub-agents to plan, retrieve context, and iteratively generate complete answers for security questionnaires. The update also introduces an MCP-powered AI Connector for Trust Center visitors, exposes feedback data via API and MCP, automates question routing to experts, and adds a native SharePoint integration.
Bears on: Agent capability
View sourcePricing
Free tier at $0 a year. Enterprise is custom, and no paid price is published.
Credits. One credit equals one organization, covering unlimited users from its domain, and questionnaire and RFP volume draws credits too.
What is public
Two plans are published. Free carries its allowances and its feature limits, and Enterprise is custom. Trust Center and Questionnaire credits are named, with no published rate.
Billing mechanics
Priced on the number of organizations that download documents or information from the trust center and on the number of questionnaires and RFPs the AI processes. One credit equals one organization, covering unlimited users from that domain. The unit is unusual because it tracks demand from the customer's own buyers rather than the customer's headcount. An annual commitment is required, and monthly billing is not offered.
Cost watchouts
The free tier excludes questionnaire automation, the main reason to buy. An annual commitment is required with no monthly option, and credits are consumed per organization that interacts with gated content.
Variable cost rationale
Conveyor meters credits. Each organization that pulls documents or answers from the trust center uses one credit, and each questionnaire or RFP the AI processes draws credits too, so the bill grows with inbound security reviews rather than with headcount. There are no per user fees, and one credit covers every user from an organization's domain. The free plan stops at 10 Trust Center credits a month. Above it, Enterprise is custom and billed on credits under an annual commitment, with volume discounts but no published rate per credit, cap or scaling price.
Additional watchouts
The free tier deliberately excludes questionnaire automation and integrations, so it exercises the trust portal only and is not a trial of the core AI.
Overage / add-ons
Additional credits are needed as organization and questionnaire volume grows. Scaling rates are not published.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free plan at $0 a year with 10 Trust Center credits a month, up to 15 documents and 15 Q&As, without questionnaire automation or integrations
Lowest paid plan
Not published
Commercial notes
Cost is metered in Trust Center and Questionnaire credits rather than seats, so the bill follows review volume rather than headcount.
Key ambiguities
Only the free plan carries a price. Enterprise is custom, and no rate per credit or price for scaling above the free allocation is published. One credit covers one organization on the trust center, but how many credits a questionnaire or RFP consumes is not published.
Cancellation / refund
Annual commitment, with no monthly billing option. No cancellation or refund terms are published.
Related vendors
- 11x — AI digital workers (Alice for outbound SDR work, Julian for inbound…
- 1up — AI answer engine for sales teams that automates RFPs and security…
- Actively AI — GTM superintelligence platform that trains a custom reasoning model…
- Aircover.ai — AI sales assistant that delivers real time in call coaching, a…
- AiSDR — AI SDR platform with multichannel outreach automation, quota visible…
- Akkari — Autonomous customer ops agent that captures every commitment,…
Alternatives to Conveyor
The closest documented capability profiles to Conveyor among GTM and revenue agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Common Room8.5 / 14A lighter documented profile than Conveyor
- Demandbase8.5 / 14A lighter documented profile than Conveyor
- Gong8.5 / 14A lighter documented profile than Conveyor
- lemlist9.5 / 14Adds documented Model Flexibility & Routing
- 11x8.0 / 14A lighter documented profile than Conveyor
- Botify10.0 / 14Fuller documented coverage on Human Oversight & Guardrails and 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