Lets it through
When the action is clearly fine, it clears in well under a tenth of a second. Your agent never breaks stride.
Governance for AI agents
Control what your AI agents do.
If you run AI agents, GaaS makes their work safer and more consistently reliable — the same way, across every one of them. Free to start.
org_demo · your agents
Simulated
| Time | Agent | Action | Verdict | Latency |
|---|---|---|---|---|
| 09:41:02 | cx-agent | send_email → customer_4421 | APPROVE | 18ms |
| 09:41:00 | content-agent | post_to_social → promo_20_off | ESCALATE | 51.1s |
| 09:40:56 | buyer-agent | create_po → $2,480 pump | ESCALATE | 40ms |
| 09:40:54 | support-agent | issue_refund → $24.99 order | APPROVE | 37ms |
| 09:40:50 | content-agent | publish_post → disclosure_added | MODIFY | 32ms |
| 09:40:48 | patient-msgs | send_sms → diagnosis_detail | BLOCK | 29ms |
| 09:40:44 | cx-agent | quote_price → sku_3302 | APPROVE | 33ms |
| 09:40:42 | buyer-agent | reorder_part → duplicate_order | BLOCK | 33ms |
GOVERNING
29,904 decisions
Simulated feed. Actual decisions include full audit records with hash-chain verification.
The Problem
Your agents are already acting. Right now they send, post, order, and touch records on their own, and the only thing checking them is the prompt you wrote.
Hope is not a control.
What GaaS Does
Before your agent acts, GaaS decides.
Before an agent sends, posts, orders, or touches a record, GaaS checks it against your rules and does one of four things:
Fixes it, then sends it
When a small change — a required disclosure, a safer phrasing — is enough to make it fine, the action goes out corrected. No waiting, no human in the loop.
Holds it for you
When it wants a human to say yes first, the action waits — and lands where you already work.
Stops it cold
When it would cross a line you drew, it never executes. The mistake you prevented once is prevented forever.
Every decision is kept as a receipt you can show anyone — a tamper-evident record of what your agents did, and what they were never allowed to do.
The Proof
Set it up in an afternoon.
Install the SDK with one command and add one governance call before each agent action. Then author your policies in plain language — the conversational dashboard is powered by Claude, so you govern by describing what you want, not by writing rules by hand.
govern_payment.py
from gaas_sdk import GaaSClient, build_intent, ActionType, TargetType async with GaaSClient("https://api.gaas.is", headers={"X-API-Key": "gsk_..."}) as client: intent = build_intent( agent_id="my-agent-v1", action_type=ActionType.TRANSACT, verb="initiate_payment", target_type=TargetType.ACCOUNT, target_identifier="vendor_account_9912", summary="Pay invoice INV-2026-0044", content={"invoice": "INV-2026-0044"}, ) response = await client.submit_intent(intent) print(response.data.verdict) # approve | approve_modified | escalate | block
The real Python SDK; TypeScript, cURL, and the framework plugins are documented at gaas.to.
The Dividend
Governance that pays you back.
A self-governing agent spends about 14,700 tokens of context on every routine governed action. GaaS uses 0 through a framework plugin, or about 2,470 through MCP. On a 200K-token model, self-governance fills 60% of the agent's context window after about 28 governed actions.
For Every Operator
Whatever your agents do, GaaS governs it.
Content & social agencies
Posts checked against brand and claims rules before they publish; risky ones held for a yes.
Parts & purchasing
Orders verified for cost and correctness, and gated over the dollar amount you set.
Healthcare & clinics
PHI detected and blocked, minimum necessary enforced, audit trail ready if anyone asks.
Retail & customer service
Prices, promises, and refunds stay inside your policy — off-policy promises never go out.
Pricing
Start free, stay cheap.
Start free in Shadow Mode, no credit card. There is a free tier, plans from $99 a month, and less than a cent per governed action at scale. Nonprofits, NGOs, and veteran-owned businesses govern free for life.
FAQ
Every objection, answered.
What is GaaS, in one sentence?
An external layer that checks what your AI agents are about to do and allows, fixes, holds, or blocks it against your rules, keeping a tamper-evident record of every decision.
Do I have to be a regulated business?
No. GaaS is for any operator running agents. Regulated teams get framework mappings; everyone else gets control over what their agents do.
Is it hard to set up?
No. Start in Shadow Mode with just an email; it runs the full pipeline on real actions without enforcing anything, so there is zero operational risk. A developer wires the SDK in an afternoon, and you author policies in plain language.
What does it cost?
Start free in Shadow Mode, no card. There is a free tier, then plans from $99 a month, and under a cent per governed action at scale. Nonprofits, NGOs, and veteran-owned businesses govern free for life. See pricing.
Will it slow my agents down?
Routine actions clear in well under a tenth of a second. Only high-stakes decisions take longer, and only because you asked them to.
Do I have to change my agent or my model?
No. GaaS sits outside the agent and needs no model changes and no cooperation from the agent to work.
Doesn't governance cost me tokens?
The opposite. A self-governing agent spends about 14,700 tokens of context on every routine governed action; with GaaS it spends 0 through a framework plugin (74 when an action is blocked), or about 2,470 through MCP. On a 200K-token model, self-governance fills 30% of the window after about 14 governed actions and 60% after about 28. See The Context Dividend.
I already have prompt guardrails. Why GaaS?
Prompt guardrails live inside the model, get re-read on every call, and can be argued away. GaaS is external and enforced; the agent cannot talk it out of a block.
Start Free Shadow Mode
Real actions, real verdicts, zero enforcement, no credit card. See what your agents are doing, then decide when to go live. If you run AI agents, this is the safest move you can make today.