Heym Work gives business teams one place to describe a job, answer a few questions, and get a tested workflow. It runs on Heym, on your own infrastructure, with single sign-on, roles, and an audit trail.
Business teams get a place they can use on day one. The platform team keeps single sign-on, roles, approvals and the audit trail in one place, on infrastructure it already runs.
Heym Work: The Business Layer for Agentic AI
Describe a job, answer a few questions, and get a tested workflow, with Heym running it in the background.
Heym Work is the simple face of Heym for the people who run the business. No canvas and no learning curve: they describe the job, answer a few questions, and work from pages built for them.
People describe a job in their own words, by typing or by voice. Heym asks the few questions it needs, builds the workflow, runs it with sample data, fixes what failed, and marks it Verified.
Verified
Lead intake
Tested 1 time before it was saved.
Pin the dashboards a team uses every day into its own menu. Widgets are built by describing them, tables carry status chips, and a row can open its own detail page.
New leads this week
11
Acme Logistics
Opened from the table: its own page, its own widgets.
When an agent pauses for a person, the review lands where the team already works. Approve, request changes or reject, and the run continues from there.
The agent drafted a refund of 240 EUR and paused for a person to decide.
Owners, Editors and Viewers each see what their role allows. People sign in with the single sign-on your Heym already uses, and new members start as Viewers.
Heym Work hands every job to Heym on your own servers. Heym’s main instance takes it in, and the workers beside it share the runs. The result comes back to the chat or page that asked for it.
Heym Workwhat your team sees
Heymruns in the background, on your servers
Run Heym on-premises, in your VPC, or air-gapped. Self-hosted deployment means customer and revenue data never leaves your servers, and because Heym is source-available, security can audit every line before you ship. You bring your own models and credentials, so there is no lock-in to switch away from.
Run locally
Start Heym locally with the included run.sh script and own the full runtime from day one.
Single sign-on against your own identity provider, execution spread across as many instances as the work needs, and an audit line for every privileged action, streamed wherever your logs already go.
An administrator pastes an issuer URL under Settings → SSO, and Heym reads the authorization, token, and key endpoints from your provider's own discovery document. No provider is hardcoded, so Keycloak, Okta, Entra ID, Auth0, and Google connect through the same fields. A connection test tells you the setup is right before anyone depends on it.
Point a second instance at the same PostgreSQL database and it joins as a worker. Agent runs, cron, webhooks, and chat triggers are then shared between instances by a weight you set under Settings → Instances. The instances never talk to each other, so a worker needs no open port and no route back.
Every sensitive action leaves a record: who did it, what they touched, and whether it worked. There is nothing to switch on and nothing extra to run, so the record keeping starts on your first day. Your team can watch it happen live inside Heym, or send it to wherever your company already keeps its logs, so the history is still there months later.
Every workflow run produces a full trace: each node, each agent decision, each tool call, and each model call with token and cost visibility. When something fails, you see where and why instead of guessing. Read the AI agent observability guide for how teams debug agents in production.
Agents draft, people decide. Add human-in-the-loop checkpoints before emails go out, records change, or money moves. Reviewers see the full context, approve or reject, and the workflow continues or stops. Nothing critical happens unattended unless you decide it should.
Native nodes cover GitHub, Jira, Slack, Telegram, email, Google Sheets, BigQuery, and more. HTTP and webhook nodes reach any internal API, and MCP support connects Heym to the growing ecosystem of tool servers. When you need a connector that does not exist yet, we build, package, and deliver it as a plugin for your deployment.
Heym Work runs as one container next to your Heym, on the same infrastructure, with a license key from our team. Setup takes three steps.
One container starts next to your Heym, on the same database, with the industry edition your team works in.
A Heym admin opens Settings, Heym Work, enters Heym Work’s address and generates a key. Every action Heym Work takes goes through that channel.
Open Heym Work, enter the license key, connect Heym with its address and the key, and sign in as an Owner. Home opens, ready for the team.
Each edition opens with pages, tables, workflows and templates for that industry, so a team starts from work it recognizes.
Legal
Contract operations
Counsel
Chat
Tables
Knowledge
Drive
Activity
What do you want Heym to get done?
Contracts awaiting review
3
AI reviews by risk
Contracts triaged by risk, research and drafts grounded in your own playbooks, and lawyer decisions in one Approval Desk.
See Legal templatesThree patterns that turn agentic systems into dependable operations.
Agents answer from your documents with retrieval and citations, so policies, contracts, and internal knowledge stay current and queryable.
Legal, finance, sales, and support workflows where agents prepare the work and people approve it before anything is sent or saved.
A lead agent coordinates specialist agents across sources and data systems and returns structured, traceable results.
Bring one valuable workflow into production in four to six weeks. We help your team deploy Heym and Heym Work, connect one or two core systems, add approval checkpoints, and establish tracing and cost visibility, with the business team working from Heym Work. The engagement starts with agreed success metrics and ends with a production rollout plan and a commercial licensing proposal.
Enterprise customers pay for reduced production responsibility, not just software. Engagements can include commercial licensing, deployment and onboarding, migration support, custom integrations, managed upgrades, architecture reviews, and agreed response times for production issues.
The questions that come up in every procurement review, answered with the mechanism behind each one.
What Heym Work reports
Each day Heym Work sends heym.run your license ID, an installation ID, the number of active users in the last 30 days, the total number of members, the number of runs in the last 24 hours, and the Heym and Heym Work versions. Workflow content, inputs, outputs and credentials stay on your servers.
Networks without internet access use an offline license. Ask us for one
Tell us about your team and the work you want to automate. We will reach out with a Heym Work trial or a walkthrough tailored to your stack, or reach us at enterprise@heym.run.
AI workflows don't fail because of prompts. They fail because of orchestration.
One canvas for agents, RAG, human-in-the-loop, MCP, traces, evals, and alerts, self-hosted and observable.
The Heym Work introduction, plus practical guides for tracing, OpenTelemetry, RAG, and multi-agent orchestration.
What Heym Work is, how it builds and tests a workflow, and how to install it, with four videos.
Read guideA practical guide to tracing, monitoring, costs, and production debugging for AI agents.
Read guideTrace every workflow step with spans, context propagation, and native OTLP export.
Read guideArchitecture, chunking, vector search, and LLM wiring for reliable retrieval workflows.
Read guideOrchestrator patterns, specialist agents, and practical ways to coordinate agent teams.
Read guide