Connect the tools you keep. The credentials stay with the platform.
The tools you keep, connected once for the whole workspace. Pipelines, ontology actions and the company agent all use the same connections, and none of them ever holds a token.
Connections declared in code and authorised here. The credentials stay with the platform, never in the repository.
Managed connections
21 ready-made connections: Google Ads, Meta Ads, Microsoft Ads, LinkedIn Ads, LinkedIn Pages, TikTok Ads, X Ads, Google Analytics 4, HubSpot, Apollo, Stripe, Xero, Resend, Telegram, Google Sheets, Supabase, Apify and AI evaluation. 3 generic ones reach any other API with a key, OAuth 2.0 or client credentials.
Declared in code, held by the platform
Connections are declared in connections/ and authorised in the console. Tokens refresh on their own, and calls go through the platform, so credentials never reach your code.
Inside actions
An ontology action can call a connection for one record: enrich a lead from Apollo, create a Stripe customer when a deal is won.
Pipelines and the agent
The same connections feed pipelines, and the company agent's Telegram channel runs on one.
Secrets
Named workspace secrets for pipeline code, created from a file and never returned by the API.
In code
# connections/connections.pyfrom segmentstream.connections import ( ApolloConnection, HubSpotConnection, StripeConnection, TelegramBotConnection,)connections = ( HubSpotConnection(key="hubspot"), StripeConnection(key="stripe"), ApolloConnection(key="apollo"), TelegramBotConnection(key="telegram"),)Use it, build on it, or have it built
Use it
Authorise Google Ads, HubSpot, Stripe and others in the console.
Build it with your agent
Your agent declares a connection for any API with a key and verifies it before anything uses it.
Have our engineers build it
Our engineers connect the tools you run today during a pilot.
Replaces Credential spreadsheets, API keys in environment variables and Connector setup in every tool.
Works with
Solutions built with it
Read more
- 8 October 2026Agent sprawl: how to run a company on one AI agent instead of 3,000Companies are building AI agents by the thousand, each with its own instructions, its own keys and its own copy of the rules. Vercel went the other way and moved hundreds of internal agents behind one. Here is how a company runs on a single agent, and what has to sit behind it.
- 8 October 2026MCP gateway vs raw MCP servers: how to run a company through any agentEvery tool your company uses now has an MCP server, and the usual way to give an agent access is to plug them all in. It demos well and breaks on permissions, rules, context and the next agent you try. An MCP gateway over your company's ontology gives every agent one door, with your own actions, roles and history behind it.
- 7 October 2026Read this before you cancel HubSpot or SalesforceCompanies are cancelling CRM contracts and having AI agents write their own. Writing the CRM is now the easy part. What decides whether it survives is the layer underneath it: objects, permissions, actions, history and safe access for agents. That layer is called an ontology.
- 3 October 2026AI agents can build your BI. Here's why they get the numbers wrong.Benchmarks keep finding that agents writing SQL against raw tables give confident wrong answers, while the same agents answering through a semantic layer get nearly everything right. What that means for how you build analytics now.
Start a pilot.
Want connections and secrets set up for you? Our forward-deployed engineers build it with you in your workspace, as code you own.
- One solution, on your data, in your own workspace
- First version live in two weeks
- Parity proven before anything is switched off
- Fixed scope and price, credited to your contract if you continue
Not ready for a pilot? Send the form anyway with your question. An engineer will reply, not a sales rep.
How the pilot worksYour company’s software, built by agents, owned by you.
$ segmentstream workspace create acme --region eu --subdomain acme
▸ Created workspace acme · database, warehouse and a private git repository
$ segmentstream workspace WORKSPACE-ID clone acme && cd acme
▸ your agent writes the five folders and runs the checks
$ git add -A && git commit -m "First version"
$ segmentstream deploy
▸ app, ontology API and MCP tools live for your invited members
Our engineers build the first version on your data in two weeks, at a fixed price.
Or join the waitlist for self-serve:
Self-serve opens to the waitlist first.