Cairn · Sections
Twenty-one sections, ready to copy
Every block below is a self-contained section with Desktop, Tablet and Phone layouts. Copy one into a page, keep its structure, and rewrite the copy for your product.
Section · Hero — Prompt
New · Approval rules by role
Agents that finish the job
Halden agents carry a ticket, invoice or CRM update from intake to done, and stop for review wherever you set a gate. Monolake’s finance team now closes the month in 3 days, down from 6.
Reconcile last week's invoices against the warehouse ledger and flag anything over $500 for review
Section · Hero — Split
New · Approval rules by role
Agents that finish the job
Halden agents carry a ticket, invoice or CRM update from intake to done, and stop for review wherever you set a gate. Monolake’s finance team now closes the month in 3 days, down from 6.
+140
140+ operations teams run their queues on Halden
Section · Hero — Centered
Run log
One place to watch every agent work
See what each agent read, which tools it called and why, then approve, retry or stop a run from the same screen.
Section · Hero — Launch
Private beta · 40 teams this winter
Your operations queue, run by agents
Halden opens to 40 operations teams this winter. Join the waitlist and we’ll set up your first supervised queue with you.
+1.2k
1,200 operations leads are on the waitlist
Section · Logo Strip
Section · Stats Band
Section · How It Works — Timeline
How it works
From first connection to a queue it runs alone
Most teams go from step one to step four in about three weeks, and widen access only after reviewing real runs.
01
Connect your tools
Point Halden at your ticket queue, CRM and accounting system. Read-only access is enough to start.
02
Describe the job
Write the playbook in plain language, the way you’d brief a new hire. Halden turns it into steps you can check.
03
Set review gates
Choose the steps that wait for a person: refunds over $500, outbound email, anything that touches the ledger.
04
Widen access
After a week of reviewed runs, loosen the gates where the agent was right and keep them where it wasn’t.
Section · How It Works — Tabs
How it works
Hand over a queue, keep the final say
Pick a workflow, connect the tools it needs and choose where it stops for review. The agent does the rest and logs every step.
Sort the queue before your team logs on
The agent reads each new ticket, checks order history, tags priority and drafts a reply. Anything involving a refund over $200 waits for a person.
Triage · #48213
Needs review
Read ticket and order history
0.8s
Tag priority: high, carrier delay
1.2s
Draft reply for review
2.4s
Section · Feature Grid
Platform
Everything an agent needs to run real work
Six parts of the platform that come with every plan, from the trigger that starts a run to the log that explains it.
Section · Bento
Capabilities
Built for work that spans five tools and a sign-off
Each capability below is a live part of the product, shown with the same components your team sees in the run log.
Briefs
Hand off work in plain language
Describe the job the way you’d brief a new hire. The agent asks when something is unclear.
Tool calls
Works inside your tools
Reads and writes in Tickets, CRM and Payments through scoped, logged calls.
search_tickets
1.2s
status: open · priority: high
update_account
running…
crm: Brightmoor · stage: renewal
Models
Swift, Steady or Deep
Fast for sorting, careful for anything that touches money. Set the tier per step.
Model
Swift
32k
Quick replies for routine triage
Steady
200k
Balanced for most workflows
Deep
1M
Careful multi-step reasoning
CLI and SDK
Ship agents like the rest of your code
Version playbooks, run evals before release and tail live runs from your terminal.
Terminal · refunds-agent
$ halden deploy refunds-agent
Bundled 14 tools · 3 review gates
Eval passed · 72% resolved on 1,200 tickets
Deployed refunds-agent v14 to production
$ halden runs tail refunds-agent
09:41:07 triage_ticket done 0.8s
09:41:09 issue_refund review $612.00
Section · Control & Safety
Control
You decide where the agent stops
Review gates, scoped access and a full run log come with every plan, so a person signs off on anything that matters.
Review gates on the steps you choose
Refunds over $500, outbound email and CRM merges wait for a person. Everything else runs.
Scoped access to each tool
Each agent gets only the permissions its job needs. Keys are encrypted and rotated every 30 days.
Every run is logged, step by step
Inputs, tool calls and decisions are kept for 400 days, searchable by ticket or invoice number.
Stops and asks when it isn’t sure
Below a confidence level you set, the agent hands the task to a person with its notes attached.
Read the order history
0.8s
3 orders · last 90 days · 1 prior refund
Email the customer a confirmation
queued
Runs after your approval
issue_refund
Review
waiting
ticket: T-8841 · amount: $612.00 · method: original
Section · Testimonials Wall
Customers
What operations leads say after the first month
Three teams, three queues: support, finance and account operations.
Section · Proof — Quote + Benchmark
Proof
Measured on real queues, not demos
We publish how agents score on real tickets. Customers tell you the rest.
“
We read every run log for the first two weeks. By the end we trusted it with four more queues, because we could see exactly what it had done.
Priya Natarajan
VP Operations, Pallas Health
Tickets resolved without a human
Internal eval · 1,200 real tickets · Oct 2026
Halden (Steady)
72%
Baseline agent
51%
Rules engine
44%
Human-only queue
38%
Section · Integrations Grid
Integrations
Connects to the tools your team already runs on
Agents act through scoped connections you approve one by one. Nothing is shared until you turn it on.
Plus a REST API and signed webhooks for anything else.
Section · Pricing
Pricing
Pay for seats. Agents run on usage you can see.
Every plan includes a monthly pool of agent runs. Past that, each run bills at its model tier’s rate, and every charge links to the run that caused it.
Save 20%
Section · API Pricing Table
Usage
Runs bill by model tier, per million tokens
Your plan’s included runs cover typical volume. Past that, each run bills the tokens it used at the rate of its model tier. Most runs use Steady.
Model
Input / 1M tokens
Output / 1M tokens
Context
Best for
Swift
Fast, low-cost calls
$0.40
$1.60
128k
Routing, classification
Steady
Default
Balanced default for agent runs
$3.00
$12.00
200k
Most agent runs
Deep
Careful multi-step reasoning
$12.00
$48.00
400k
Long, multi-step reasoning
Prices in USD per 1M tokens. Usage bills monthly, only after your plan’s included runs are used. Failed runs are never billed, and every line on the invoice links to its run log.
Section · Developer Quickstart
Developers
Start a run from your own code in three steps
The SDK and CLI cover everything the dashboard does: create runs, set review gates and stream the log as it happens.
runs.ts
// Hand refunds to an agent, keep a human on big ones
import { Halden } from "@halden/sdk"
const halden = new Halden(process.env.HALDEN_KEY)
const run = await halden.runs.create({
agent: "refunds", input,
review: { above: 500 },
})
Section · Trust — Summary
The short version
Six commitments that hold for every workspace
If you only read one part of this page, read this one. The sections below show how each one works.
Your data never trains models
Tickets, documents and run logs are used to run your agents and nothing else, by us or by our model providers.
Agents only see what you connect
Each agent gets scoped access to the tools and fields its job needs. The rest of your workspace stays out of reach.
Every action is logged
Each read, tool call and decision is recorded with its inputs and outputs. Export the log as CSV or JSON.
Humans approve risky steps
Payments, outbound email and deletes wait for a person by default. You set the thresholds per agent.
Delete anytime
Remove a run, a connection or your whole workspace. A hard delete clears every copy, backups included, within 30 days.
Region choice: US or EU
Choose where your workspace lives at sign-up. Data, run logs and backups stay in that region.
Section · Trust — Models Table
Models and providers
Where each model runs and what it keeps
Swift runs on Halden’s own servers. Steady and Deep run with a model provider under a contract that rules out training and limits retention.
Swift
Fast, low-cost calls
Steady
Default for agent runs
Deep
Careful multi-step reasoning
Hosted where
Halden servers, your region
Model provider, your region
Model provider, US (EU on request)
Retention of prompts
0 days
30 days, 0 with ZDR
30 days, 0 with ZDR
Used for training
No
No
No
Zero data retention option
Always on
Configurable
Configurable
ZDR is zero data retention: prompts and outputs are processed in memory and never stored by the provider. Turn it on per workspace in your data settings.
Section · FAQ
FAQ
Questions teams ask before the first run
Something else on your mind? Write to hello@halden.ai and a person replies within one business day.
It stops and asks. Any step below the confidence level you set goes to a person with the agent’s notes and the evidence it used, and the run waits until someone decides.
Most teams connect Tickets and CRM and run a first supervised queue within a week. We help you write the first playbook and set the review gates.
On our internal eval of 1,200 real support tickets, Halden on Steady resolved 72% without a person. You see accuracy per queue in the run log before you widen access.
No. Run data stays in your workspace and is not used to train models. You can export or delete any run at any time.
Plans start at $19 per seat a month with 1,000 agent runs included. Usage past that bills per model tier, and every charge links to the run that caused it.
Section · Closing CTA
Start with one queue this month
Connect Tickets and CRM, set a review gate, and watch the agent work a real queue with your team signing off.