One agent across all your systems.
SourceLace is the AI-native agentic platform for enterprise systems. One agent across all your systems, acting as each person, with every action approved and on the record. Your people work in the SourceLace app, with AI agents that do the routine work; their own AI apps can reach it too. It runs in our cloud.
How SourceLace fits together.
People ask in the SourceLace app, and AI apps can ask too. One SourceLace agent answers and acts, inside the SourceLace Trust Layer, and reaches every system as the person it works for. Changes come back to a person to approve, and agents on other platforms work with it over open standards.
Diagram: how SourceLace fits together People in the SourceLace app, and AI apps, at the top ask one SourceLace agent. The agent sits inside the SourceLace Trust Layer: each person's sign-in, data protection, approvals and audit. Threads lace out from the agent to many vendors' systems below. To the side, other platforms' agents work with it over open standards. The same content follows as a list.- Each person's sign-inTheir own account and permissions in each system
- Data protectionFields hidden or masked before the AI sees them
- Answers and acts in the SourceLace app, in your AI apps, and as AI agents
- Exact answers across your systems
- Runs on a schedule, before meetings, or when something happens
- Drafts, documents and proposed changes, never sent or applied on its own
- ApprovalsA preview and a person's yes before any change
- AuditA tamper-evident record of every call and change
- CRMSalesforceHubSpotDynamics 365
- ERPSAP S/4HANANetSuiteOracle Fusion
- HRWorkdaySuccessFactors
- Service desksServiceNowZendeskJira
- Data platformsSnowflakeBigQueryDatabricks
- FilesGoogle DriveSharePointAmazon S3
- Mail and calendarGmailMicrosoft 365
- Slack and TeamsSlackTeams
- Your own systemsREST and SOAP APIsVendors' MCP serversConnector SDK
Runs in our cloud, with AI agents in your own network on the SourceLace Runner for Enterprise organizationsRead live, where the data already is. Nothing copied.
Who asks
- People, in the SourceLace app, by chat or voice.
- AI apps, too: any AI app that supports MCP, with any AI model.
One SourceLace agent, across all your systems, acting as each person
- Answers and acts in the SourceLace app, in your AI apps, and as AI agents
- Exact answers across your systems
- Runs on a schedule, before meetings, or when something happens
- Drafts, documents and proposed changes, never sent or applied on its own
SourceLace Trust Layer, around every request
- Each person's sign-in: Their own account and permissions in each system.
- Data protection: Fields hidden or masked before the AI sees them.
- Approvals: A preview and a person's yes before any change.
- Audit: A tamper-evident record of every call and change, which you can export and verify.
Other platforms' agents
- They hand work to your agent and answer its questions, both ways over the open A2A standard. A person approves before your data leaves.
Many vendors' systems, read live as each person
- CRM: Salesforce, HubSpot, Dynamics 365.
- ERP: SAP S/4HANA, NetSuite, Oracle Fusion.
- HR: Workday, SuccessFactors.
- Service desks: ServiceNow, Zendesk, Jira.
- Data platforms: Snowflake, BigQuery, Databricks.
- Files: Google Drive, SharePoint, Amazon S3.
- Mail and calendar: Gmail, Microsoft 365.
- Slack and Teams: Slack, Teams.
- Your own systems: REST and SOAP APIs, vendors' own MCP servers, Connector SDK.
Where your people work, at sourcelace.ai.
People sign in, connect their systems, chat with an assistant that works with their own permissions, build and run AI agents (with the optional add-on Agent Architect to propose them from your own work), and approve what those agents propose in one inbox. It uses the AI included in your plan, or your organization's own AI key (Anthropic, OpenAI, Google Gemini, Mistral, Azure OpenAI and Amazon Bedrock keys today).
Chats and projects
Star the chats you come back to, and keep related chats in projects you can share. Chats are saved, encrypted, and deleted after your organization's retention period.
Charts
Turn a result into a chart. Pinned charts refresh themselves.
Files
Make Word, PowerPoint and PDF reports from results, and Excel or CSV spreadsheets of the data itself, with protected values still masked. Every file your chats and agents make is listed on one page, with when it will be removed.
Photos in the chat
Where your admin allows it, attach a photo or a screenshot to a question, such as an error message, and the assistant reads it with your question. Photos only: your admin accepts a short statement first and chooses everyone or chosen groups, and nobody can attach before that. A photo goes to the AI provider as it is, and is kept with the chat until the chat is deleted; an older stored copy can remain for up to 30 days. Photos work today with SourceLace's included AI and with your own Anthropic key.
Search everything
One search across your files, chat, mail, service desks and Salesforce at once, live and with each person's own access, best results first with links. Nothing is copied or indexed. A pilot feature, on request.
Help with SourceLace itself
Ask the assistant how to do something in SourceLace, such as setting up an agent or finishing your setup. It gives you a short plan and takes you through it one step at a time, with a button to open each screen. It only suggests screens you are allowed to use, and you make every change yourself.
Skills and voice
The assistant follows the skills your people write, shared with just the people and groups who need them, or with everyone as optional or required. Anyone can suggest a good skill for their group or the whole organization, and a group manager or admin approves it. Ask by speaking, and copy an answer or a table with one button. Answers appear as text; your admin decides whether they can also be read aloud and who sees the Copy buttons.
Your own AI app can reach it too.
An optional extra: any AI app that supports the Model Context Protocol (MCP) can add SourceLace with one address, then ask, propose changes, use skills and start your agents. Building agents and approving what they propose stay in the SourceLace app. It works with any AI model: SourceLace never assumes a particular vendor, and when people use their own AI app, SourceLace sends nothing to an AI model itself.
The same tools for every system
Find the right objects and fields, including your custom ones, query them live in each system's own language, read a record with its related lists, and propose changes.
Signed in as themselves
People sign in to SourceLace once in their AI app, then connect each system with their own account wherever the system offers one.
Your how-tos travel with you
Skills your organization writes, such as "build a QBR deck", are available in every AI app, in the SourceLace app and to agents.
Answers about SourceLace itself
The AI can look up setup, security and privacy questions in SourceLace's own manual and answer with a link to the page.
One exact answer, even when it spans systems.
Ask a question that needs several systems at once, such as Salesforce accounts with overdue SAP invoices, and get one exact answer. Each system is asked only for what it holds, every row is counted, and you can see where each number came from. Follow-up questions can work on the same result without fetching everything again. Where the same customer is written differently in two systems, your admins' matching rules decide which records are the same, the same way for every person and agent, and the answer says how many matched. Anyone can have the assistant draft a rule in a chat, try it on their own data and suggest it to the admins, and answers can show which system and field each column came from.
- "Which Corvanta renewals this quarter have overdue invoices?"CRM + ERP · one answer across both
- "Of those, which have an open severity 1 case?"adds the service desk · works on the result you already have
A question across six systems, answered in about half a second.1
Ask one question that needs your CRM, ERP, finance, support and product systems, and get one answer. SourceLace asks each system live, lets a system that can work out a total do it itself, and sends back only the result. You get the same answer, sooner, and your systems do less work. Nothing is copied into a lake first.
1 Measured on a standard cloud server with simulated systems, 500,000 invoices, 7 timed runs, every answer checked against an independent calculation. Your systems and network add their own time, so yours will vary.
Changes with a preview, and only after a yes.
Reading is read-only and checked before anything is sent. Where an admin allows changes for a system and object, the AI proposes each change, the person sees exactly what would change, and it is applied once, only after they confirm.
- Off until an admin turns it on. Changes are allowed per system and object, and only for the groups an admin chooses.
- Previewed field by field. Every field's current and new value, for records, spreadsheet rows, and Slack or Teams posts alike.
- Drafts, never sent mail. Mail connectors create drafts for the person to review and send.
- Recorded. Who changed which fields, on which system, and when.
Everything your admins need, in the app.
Sign-in and single sign-on
Google or Microsoft accounts out of the box, or your own identity provider with OpenID Connect or SAML 2.0. Require single sign-on for your domains and sync groups.
Automatic provisioning
With SCIM, Microsoft Entra ID, Okta or Ping Identity add people, keep their groups up to date, and deactivate them when they leave. Their sessions, AI app connections and sign-ins end at once.
People, groups and sources
Invite people or allow your email domains, decide which groups may use which systems and objects, name group managers to keep a group's people up to date, share skills with it and approve what its people suggest, choose how widely anything may be shared, and add or change sources.
Health
One page shows whether your connections, AI agents, audit trail, usage and sign-in are working, with the problems first and a link to the page that has the detail.
Limits and usage
See every limit on one page and make some stricter, such as shorter sign-in sessions or fewer agent runs at once. Usage and invoices are in the app too.
Retention and audit
Shorten how long results, chats and agent runs are kept. Search, filter and export the audit trail, or list only what SourceLace's own staff did on your account.
Data protection
Hide fields from the AI or mask sensitive values, per system and object. How it works for you.
A good setup, suggested for you and approved by you.
SourceLace helps admins get to a sound setup quickly. Every suggestion waits in a review queue with its reason, and nothing changes until an admin approves it.
Readiness score
A score from 0 to 100 with the checks behind it: sign-in, access, data protection, sources, AI model, agents, skills and terms, and audit and retention. Most checks offer a fix.
Setup assistant
After you connect a system, SourceLace suggests groups, data protection rules for fields that look sensitive, business terms such as ARR, and agents that fit.
Industry packs
Ready-made starting points by industry and team: Finance, Procurement, IT, HR, Customer Success, Marketing, RevOps, supply chain and leadership, plus healthcare on FHIR with test data: care gaps, readmissions, discharge follow-up and coverage checks before visits. See each pack's use cases. Each brings agents that replace a recurring manual task, with email drafts and Slack or Teams posts you approve.
Business terms
Tell SourceLace what your words mean, such as what counts as open pipeline, so every answer uses your definitions. A group such as Sales can give a term its own meaning for its people.
Setup as a file
Download your whole setup as one file to keep a record, review it, or copy it from a test organization to your real one. It never holds people, passwords, keys or data.
Learn from use
Off until an admin turns it on. SourceLace notices questions many people keep asking and suggests a skill or an agent for them, without showing who asked.
Our cloud, and your network for agents.
SourceLace cloud
Sign in at sourcelace.ai and start. Each customer is its own organization, with its own encryption key for what SourceLace keeps.
SourceLace Runner
Stay in our cloud, and run the AI agents you choose inside your own cloud account or data center. The runner connects out over HTTPS only, so you open no inbound port, and run results stay in your network. Choose where each agent runs: in our cloud or on your runner, all managed in the same SourceLace app (cloud and runners together). Enterprise plan only, on request, with an annual runner fee, a one-time onboarding fee (installation help and a security review), Premium support and a minimum one-year term. Contact us for prices.