Governed agents

Governed AI agents with a budget and a run history

An agent with no governor is a rumor about what happened to your data. Here every Oxygent, OXYGEN's in-app AI agent, and every custom agent caps each paid step and records what it did.

try
Start freeRead the docs

On the ladder from most to least predictable, Tables with AI columns come first, then Workflows. Agents, Oxygents included, are the easiest to turn on and the least predictable, so the platform enforces their limits rather than a prompt.

In an Agent run, the saved version fixes what the run may do. Full access to every tool OXYGEN allows needs your explicit sign-off. Otherwise, limit it to chosen tools, or add rules that make it ask first or refuse one. Being allowed a tool never means being allowed to spend: each run, manual or triggered, carries a credit limit you approve.

Example searches

Ask for it the way you'd say it

Each example is a request in plain words, with what it returns underneath.

  • A worker for the inbox

    draft a reply for every new inbound conversation but never send one without me

    The drafting agent is held to draft-only by a database constraint. A draft goes out when you send it, or when an Oxygent or a Full-access Agent sends it.

  • Ask before anything external

    let it research freely but stop and ask me before any message or paid call

    Agent runs pause per ask rule at a checkpoint you resume; an Oxygent chat on Ask for approval holds sends and larger paid steps.

  • Read what it actually did

    show me what ran last night, what it cost, and where it stopped

    A run lists status, tool calls, approvals, model usage, credits, and a link to whatever it produced.

Plays

Three motions you can run this week

Each one is a chain of OXYGEN primitives: the same hosted objects your workspace already has, composed.

  • Turn on a job instead of building one

    A recurring chore runs continuously without anyone authoring the mechanism behind it.

    1. Agents
    2. Messages
    3. Observability
    1. 1Pick a shipped specialist whose job matches the chore, such as reply drafting or inbound tagging.
    2. 2Enable it, read the first run end to end, and only then leave it alone.
    oxygen agent enable

  • Give it a schedule and a ceiling

    Unattended work happens on a cadence with a per-delivery spend cap you approved in advance.

    1. Agents
    2. Observability
    1. 1Create a cron or event trigger on your first Oxygent and set the credit ceiling it carries per delivery.
    2. 2Review the run list weekly rather than the transcript daily.
    oxygen agent trigger-create

  • Keep it grounded in your own knowledge

    Output reads like your company, not like generic AI.

    1. Knowledge Graph
    2. Agents
    3. Records
    1. 1Pin voice, brand, and positioning pages. By default, Oxygent chats and your first Oxygent's runs read them; custom agents read knowledge on demand.
    2. 2Have runs file learnings on a working page; approve the best into the pinned pages.
    oxygen agent run

Capabilities

What you get

  • Limits that hold in every mode

    Platform deny rules on credentials, billing changes and admin, each step's credit cap and your balance live in the runtime, not in instructions. Auto-approve skips approval cards, never these.

  • Immutable versions

    An Agent run keeps the exact version it started on: its permissions, the knowledge it reads, and its skills. A later edit never changes a run in flight, so you can explain what it did. An Oxygent chat reads its Oxygent's current settings at every message.

  • Every action on the record

    An Agent run keeps its status, credits, tool calls and checkpoints. An Oxygent chat keeps each action and approval in its event log.

  • A roster with no placeholders

    Everything listed runs today: your Oxygents and specialists for reply drafting, meeting notes, knowledge synthesis, and inbound tagging.

Boundaries

What Agents does not own

Agents own goal-directed runs, not the objects they produce. A drafted reply is a Messages row, a filed note is Records activity, and a synthesized page belongs to the Knowledge Graph. Fixed steps an agent hands off run as Workflows. OXYGEN never runs an agent runtime you upload.

Data sources

Data sources and CRM connections

  • Exa

    Grounding search for a run that needs a fact the workspace does not already hold.

  • Pa
    Parallel

    On your own Parallel key, objective-steered search when the job is a question, not a lookup.

  • Serper

    Plain search results, often all a qualification step needs before it moves on.

  • Firecrawl

    Reads the page an agent chose to check, shown as a tool call on the run.

  • People Data Labs

    Person and company records for a job that has to resolve who somebody actually is first.

Use managed credits where available, or connect a supported provider key on an eligible paid plan. Your provider bills its calls; OXYGEN adds a per-call platform fee. Signed-in CRM connections such as HubSpot have no per-call fee. Connected sending accounts reserve monthly credits. See pricing and supported integrations.

Limits

Where this stops

  • An agent is the least predictable rung on the ladder. If you can write the steps, a workflow does the job more cheaply and predictably.
  • Platform deny rules and hard ceilings are not configurable. That is reassuring when something goes wrong and constraining when you want an agent to do something OXYGEN does not offer.
  • Cron, event, and webhook triggers belong to your first Oxygent; specialists keep their own cadence. An Oxygent with a published version can run recurring work as a routine set up from its chat, with per-run and daily credit caps.

FAQ

Questions people ask first

Which agents actually ship today?
Your workspace's first Oxygent opens on Home, and you can add more. Beside them run 4 specialists: inbox reply drafting, a meeting notetaker that files notes onto records, knowledge synthesis on a cadence, and an inbound conversation tagger.
Can an agent spend without asking?
Yes, within limits. An Agent run spends inside its approved ceiling, per manual run or per trigger delivery. A shared Oxygent's chat starts on Auto-approve, so paid steps run without a card, each within its own credit cap and your balance.
Can I build my own?
Yes. Add an Oxygent and give it its job in chat, or create a custom agent with its own instructions, tool access, and versions.
What stops it sending something embarrassing?
Two settings: what the agent's saved version allows, and your chat's approval mode. Reply drafting is draft-only, and an ask rule pauses an Agent run before the call. A shared Oxygent's chat starts on Auto-approve, which also answers ask rules. Switch it to Ask for approval to hold sends, sequence starts and larger paid steps.
How do I debug a bad run?
Open the run. It shows status, tool calls, approvals it waited on, model usage, credits drawn, and links to what it wrote. You diagnose the behavior instead of reconstructing it from the output.
Is this an agent builder?
Not for agent code. Oxygents and custom agents get their own instructions and tool access, but they run over OXYGEN's bounded set of tools. If you want a framework for agent code, this is the wrong product.

Try Agents in your own workspace

Sign up, get a working workspace with a one-time credit grant, and run the first play from the web app, the CLI, or your AI assistant over MCP.

Start freeSee pricing