Define what your agent should do. SPIRITT runs it on managed infrastructure and any model, with sandboxing, long-running sessions, scoped permissions and tracing built in

































Resolve order and refund tickets end to end, in the customer's language
ToolsRefunds over $200 wait for a human
Never share payment details
Escalate legal and safety questions
Ticket resolved, customer confirmed, within policy
Default harnessBaseline
Tools reshapedBetter
Prompts tunedBetter
Custom harnessSelected
+Added tool order_history
~Rewrote the refund policy prompt
~Context keeps the last three orders
−Removed generic web search
read_ticket
lookup_order
check_policy
draft_reply
issue_refund
Checkpoint saved, the run survives disconnects
support-agentOwn identity · managed credentials
zendesk.read_ticketAllowshopify.lookup_orderAllowgmail.send_replyAllowstripe.issue_refundAskcrm.delete_contactDenyEvery claim has a source
Covers the top five competitors
Fits on two pages, rewriting

Default harnessBaseline
Tools reshapedBetter
Prompts tunedBetter
Custom harnessSelected
Program search tunes the harness, tools and prompts to your workload

{
"agent" : "support-agent",
"input" : "Where is order 4821?"
}
{
"status" : "resolved",
"reply" : "It ships today, tracking…"
}Every agent ships behind an endpoint your product can call

read_ticketlookup_ordercheck_policydraft_replyissue_refundInspect every tool call, decision and failure, end to end

zendesk.read_ticketAllowshopify.lookup_orderAllowstripe.issue_refundAskcrm.delete_contactDenyAllow, ask or deny every tool, so real access never means lost control

support-agentIts own identity, not a shared key
Each agent gets its own identity and credentials, managed for you

ApprovedRefund of $80 for order 4790
support-agent needs youRefund $240 for order 4821. It's over the $200 limit, everything else checks out.
Sensitive steps wait for a person, one click to approve

Two claims had no source
RetryMissed one competitor
RetryEvery criterion met
PassSet success criteria. The agent checks its own work and iterates until it gets there

Shopify API timed out
Retried with backoff, order found
Context compacted, kept what matters
Ticket resolved
The harness manages context and works around failures for you

Every agent gets its own isolated cloud machine for its tools and code. You define the agent, we run it

OpportunityStageAmount
Northwind LabsProposal$84K
Contoso RetailNegotiation$61K
Fabrikam IncDemo$58K
Tailspin ToysQualified$42K
Your agents browse in the cloud, or in your own Chrome with your logins

Clicks and types through any app, just like a person would

1export async function POST (req) { 2const { accounts } =await req.json(); 3const scored =await score (accounts, { 4 model:"best-combo", 5 reasons:true , 6 }); 7return Response.json (scored); 8}
Writes, tests and ships production code, in any language

Claude, GPT, Gemini, Grok, Kimi, DeepSeek, Qwen and more. Switch models without rebuilding your agent

Blends the best of several models inside one agent, step by step

Claude MaxUsed for coding
ChatGPT ProUsed for research
SuperGrokConnect in one click
Connect the Claude, ChatGPT and Grok plans you already pay for


ApolloPeople search

HunterEmail finder

LushaPhone numbers

ZoomInfoCompany data
Apollo, Hunter, Lusha, ZoomInfo and more for your agents, paid per use with no extra subscriptions
Tag @SPIRITT in Slack, Teams, iMessage, WhatsApp and email. It reads the thread and gets to work

EmilyLet's push the launch ad budget
JakeCap it at $500 a day?
SPIRITTDone. Budget set for 3 channels, report every morning
Your whole team in one thread with SPIRITT, everyone sees the work as it happens

Draft a follow-up to Sarah and move the demo to Thursday
Talk instead of type, or have a live voice conversation with SPIRITT

1500+ ready to go, plus custom integrations for anything with an API

Sarah Lin, Northwind LabsOn call · 02:14
Hi Sarah, it's SPIRITT from Acme, calling about your renewal.
Sure, send me the new terms.
Buys a number, then makes and takes calls on your behalf

Voiceovers, narration, podcasts and original music, in any voice and language

this changed my morning routine9:16
4:5
16:9
UGC, ads and explainers, always on the frontier model




Ads, product shots and brand assets on demand

Point at any site or video you love and get your own version, in your brand

Parts, products and scenes modeled from a sentence, ready to print or render

From idea to production, full stack

PDFContract.pdf
XLSQ3 actuals
MP4Sales call
PNGReceipt scan
CustomerNorthwind
Total$46,200
RenewsMar 2027
Uplift7%
PDFs, sheets, scans, audio and video, turned into answers

Progress and outputs live in the cloud, so a dropped connection never costs a run

Long-running sessions for weeks and months, with progress reports along the way

Agents direct other agents to split big work in parallel, hundreds or thousands at once

NoticedChurn risk is up in EMEA this week
Noticed something worth doing23 trial accounts stall at onboarding step 3. I set up an agent that sends each one a short walkthrough.
Spots work worth doing and sets up agents for it

Say it once in your own words. SPIRITT runs it on schedule and keeps it healthy

Needs to read 1,200 scans
No tool exists, so it built one
invoice-ocr passed 20 tests
Processing 1,184 of 1,200
Builds the tool it needs and unblocks itself

EIN issued
Sales tax filed
1099s sent
Incorporation, tax filings, permits and the rest of the bureaucracy

Paid FigmaSPIRITT pays online with its own card, within limits you set

Domains, databases, storage and servers, handled for you

Emily wants the digest on Monday mornings3 weeks ago
Q4 ads budget capped at $500 a dayyesterday
Brand voice: warm, short, no jargon2 months ago
Remembers your people, preferences and decisions

Sales$4,200 of $5,000
Marketing$2,900 of $4,000
Engineering$6,100 of $8,000
Budgets by team, project and agent, with alerts before you hit them

The interface shapes itself around YOUR work
Describe your agent's tasks, tools and guardrails, and pick any model or a mixture. No infrastructure to wire, no agent loop to rebuild for every model upgrade
Explore the API ›

support-agentDefined

Tuned against your criteriaCustom harness
ToolsGeneric setFitted to your stack
PromptsDefaultTuned
ContextEverythingWhat matters
Model per stepOne modelMixture
Set your outcomes. Program search explores the harness, tools and prompts against them and hands you a custom harness fitted to your workload, not a one-size-fits-all loop
Talk to us ›Ship it behind a clean API on managed infrastructure. Sandboxing, long-running sessions, multi-agent coordination and scoped permissions come built in, so your team works on the product, not the plumbing
Get started ›

POST /agents/support-agent
Liveresolved

read_ticket0.8s
lookup_order1.1s
issue_refundApproved
reply_customerSent
Every run, tool call and decision is traced, so you always know what your agents did and why. Your agents keep getting better, and you stay in control
Explore Enterprise ›
AvaAI ops worker
MemoryVoiceJake@Ava send this month's invoices?
Remembers Jake wants PDFs
Pulls the invoices from Stripe
Emails them to finance
Ryan ColeVP Operations · Acme Logistics
Good fitRyan, an idea for your dispatch team
Saw Acme opened a new hub in Denver. Teams like yours use us to…
Incoming callEmily Carter · answered by AI
EmilyCan I move my appointment to Friday?
AgentFriday at 2 PM is open. You're booked.
Gmail
Zendesk
Stripe
Refunds need a human
Read ticket0.4s
Look up order1.1s
Draft refund0.8s
Ask EmilyApprove
EEmily ParkHead of Growth · LumenMeeting
JJake MillerCOO · FieldworkReplied
RRyan BrooksFounder · TidepoolFollow-up 2
MMegan LeeVP Sales · OrbitEmailed
Northwind contract ended, no renewal sent
Bluebird renewing below list price
Calling Harbor SupplyFrom your SPIRITT number
0:48TaskConfirm Tuesday delivery and dock time
Call summarySent to you
Delivery confirmed for Tuesday
Driver calls 30 min before arrival
Logged in your CRM
EEmily“Loved your post on pricing…”Replied
JJake“Congrats on the Austin office…”Opened
RRyan“Saw you're hiring SDRs…”Booked
Our own agents run on the same managed infrastructure you get, in production, at scale. We don't sell you anything we don't use ourselves.
Our mission