HITL vs Preloop
HITL puts the person at the center: your agent asks at the steps that need judgment, and a branching workflow carries each answer to the right reviewer and the right next step, with no proxy to run.
TL;DR: three reasons teams pick HITL
HITL keeps a person in the loop on AI agents, from a one-tap approval to a multi-stage review that branches on every answer. Here is where it pulls ahead of Preloop.
Multi-stage review: chain Human Review steps, branch on each answer and route by an AI classification.
Built for the person answering: 7 response types, a web inbox and apps for iPhone, Apple Watch and Android.
Works with no-code tools too: n8n, Zapier and Make, plus a REST API and a hosted MCP server.
Built for complex decisions, not just yes or no
In HITL a workflow is a graph, not a straight line. Classify the request, ask the right person, branch on what they say and merge back. Build it on a canvas, or describe it and let the workflow assistant build it for you.
Yes: Send the refund · No: Email the customer
As many reviews as the decision needs
Put several Human Review steps in one workflow: a first check, a second sign-off, an escalation, and a different reviewer on each branch.
Branch on the answer
A Condition step routes on what the person decided or on the data. An AI Classifier sends each request down the path for its category.
Paths that meet again
Branches can merge back into one path, so a refund, an escalation and a drafted reply can all finish with the same follow-up step.
Describe it, get the workflow
The built-in workflow assistant builds the graph from a plain-language prompt. Every revision is kept, so you can restore an earlier one.
Nine step types on the canvas
- TriggerStart on a schedule, an email or a spreadsheet row.
- Human ReviewAsk a person to decide, with any of the 7 response types.
- AIRun a prompt on the data so far.
- AI ClassifierSort input into categories, each with its own path, plus Other.
- ConditionBranch yes or no on the answer or on any data.
- TransformSet variables for the steps that follow.
- DataFetch from Google Sheets, an API or a table.
- ActionCall a webhook, send an email or post to Slack.
- EndClose the run once every path is done.
What about Preloop?
Preloop's docs describe conditional approval rules that decide whether a tool call needs approval, and an approval workflow with one approver pool and a quorum. Its teams page says teams have no workflow stages. HITL chains review steps and branches on each answer.
Feature comparison
Where HITL leads comes first. Then the features HITL and Preloop share, from connecting agents to pricing.
| Feature | HITL | Preloop |
|---|---|---|
| Nonlinear workflows (branching, multi-step review) | YesBranches, AI routing, several review steps | Not listedConditional approval rules |
| Visual workflow editor | YesCanvas with 9 step types | Not listed |
| No-code tools (n8n, Zapier, Make) | Yesn8n, Zapier, Make | Not listed |
| Reviewer edits the AI draft | YesEditable text | Not listed |
| Android app | Yes | Not listed |
| Telegram | Yes | Not listed |
| MCP server for agents | YesHosted, with sign-in | YesMCP proxy |
| REST API | Yes | Yes |
| One-step setup for coding agents | YesPaste-in setup prompt | YesCLI onboarding |
| Callback webhooks | YesPer request | Yes |
| Answers beyond approve or deny | Yes7 response types | YesMultiple options |
| Web inbox | Yesmy.hitl.sh | YesWeb console |
| iPhone app | Yes | Yes |
| Apple Watch | Yes | Yes |
| Free plan | Yes500 requests / mo | YesFree cloud and OSS |
| Slack | Coming soon | Yes |
"Not listed" means we could not find it on Preloop's public site or docs in October 2026. It may still exist. "Coming soon" channels are on HITL's roadmap and not live yet.
The products, side by side
HITL's web inbox next to a product image Preloop shows on its own site.
HITL web inboxfrom hitl.sh
Preloopfrom preloop.aiAbout Preloop
Preloop is an open source AI agent control plane from Spacecode AI. It sits between agents and their tools as an MCP proxy, applies allow, deny or approve rules, tracks model spend through a gateway and records an audit trail. Approvals go to mobile, Apple Watch, Slack, Mattermost, email or a webhook.
Why teams pick HITL
For the people who answer the requests and the teams who run the workflows.
Review in stages
A first reviewer checks, a Condition step reads the answer, and the big cases go to a second sign-off. Each branch can have its own reviewers.
Made for the reviewer
Each request shows up as a clear question with the right controls: approve or deny, choices, text, an editable draft, a number or a rating.
Not just coding agents
Connect n8n, Zapier, Make, Grok, Claude Code or your own code. Each request carries a source chip so reviewers know where it came from.
Oversight you can point to
Each answer is recorded with who gave it. That helps with the human oversight Article 14 of the EU AI Act asks for.
Why agents work well with HITL
For the agents asking the questions. HITL gives them a clear contract: ask, wait, get a typed answer.
A hosted MCP server
Add https://mcp.hitl.sh/mcp to Claude Code, Cursor or any client that supports remote MCP. Sign in once and the agent gets tools like list_loops, create_request and get_request.
A structured answer, every time
The agent picks one of 7 response types and gets back typed data: a decision, the chosen options, a number, a rating or the edited text. No parsing a chat reply.
Timeouts that keep work moving
Every request carries a default response. If nobody answers in time, the agent gets that answer and carries on instead of waiting forever.
A setup prompt the agent follows
Copy the setup prompt from hitl.sh and paste it into your agent. It asks for your API key, reads the docs at docs.hitl.sh/llms.txt and lists your loops to prove the connection works.
Add HITL to Claude Code
claude mcp add --transport http hitl https://mcp.hitl.sh/mcpQuestions
What teams ask when they weigh HITL against Preloop.
- Why choose HITL over Preloop?
- HITL is built around the person who answers. Your agent asks at the steps that need judgment, reviewers answer with 7 response types on phone, watch or web, and a branching workflow decides what happens next. There is no proxy to put in front of your tools.
- Can HITL run multi-stage approvals?
- Yes. Add several Human Review steps to one workflow, branch on each answer with a Condition step and send different categories to different reviewers. Preloop's docs describe one approver pool with a quorum per approval workflow.
- Do both have an Apple Watch app?
- Yes. Both send approvals to iPhone and Apple Watch. HITL also has an Android app, a web inbox at my.hitl.sh and Telegram.
- How does pricing compare?
- HITL is free for 500 requests a month, then $10 or $30 a month. Preloop has a free cloud tier and a free open source core, with paid cloud plans from $12 a month.
- Can I use both?
- Yes. A policy layer like Preloop can decide which actions need a person, and HITL can carry the question to that person with richer answers and a branching workflow.
Sources
Facts about Preloop come from these public pages, checked in October 2026. Products change, so check them for the latest. Spot something out of date? Email [email protected].
Ship AI workflows your team can trust
Free to start. Your first workflow takes minutes.