Hedy joins your Feishu, Lark or Slack, answers from your knowledge base with citations, ships daily reports, reviews code and preps your meetings — governed by code, not by prompts, with every action audited.
$ docker compose up -d · runs air-gapped · your model keys, your data
Every Hedy ships the same governed core. The role profile decides what she owns, which tools she carries, and how far her permissions reach.
One employee can hold several of these. Roles are profiles over the same core — swap duties without re-hiring, or run multiple employees with separate permissions.
Not a bag of prompts — each skill ships with hard rules, tool boundaries and its own acceptance tests.
Company questions answered from your knowledge base — hybrid retrieval, ACL-filtered per asker. Every claim carries its source link. No citation, no answer.
A 60-second pre-read brief before you walk in; minutes with owners and action items after. Decisions land in memory, not in a void.
Daily digests and weekly reports assembled from scripts and APIs — numbers come from command output, never from imagination.
Reviews merge requests with project context, triages bugs to suspect files with confidence levels. Writes are allowlisted; merging stays human.
Scheduled jobs with explicit delivery targets, watchdog-supervised. Missed runs alert — silence is never mistaken for success.
Repeated workflows get distilled into new, versioned skills — verification-first, enabled only after your sign-off. Your Hedy compounds.
up -d to first deliverable.docker compose up -d on a VM, or Helm on Kubernetes. Air-gapped works with local models.
Feishu, Lark or Slack for conversation; Git, Notion, Confluence and your wiki as knowledge sources.
Seats, approval tiers, write allowlists, knowledge ACLs. Defaults are deny — you open doors deliberately.
Cited answers in the group by minute one. Reports, reviews and briefs follow on schedule.
Anyone can demo an agent that acts. The hard part is an employee that provably doesn't — doesn't leak, doesn't overstep, doesn't freelance. Every limit below lives in code and config. Prompts are not a security boundary.
Compose or Helm, in your VPC or fully air-gapped. Source available for audit. Data never leaves.
Every action logged with actor, object and reasoning. No update or delete path exists — not even for admins.
Tiered authorization (L0–L2) stored in the database. External posts, spends and commitments wait for a human tap.
Repo writes require an explicit allowlist. Code changes ship as draft PRs; merging is a human verb.
We test what Hedy must never say: salary probes, credential requests, injection attempts. Leak checks run in the same eval gate as quality — before every release.
Retrieval is ACL-filtered server-side by who's asking. External-facing employees are hard-capped to the public layer.
Every model call flows through a single quota gateway — budgets, degradation policy and per-employee metering with one source of truth.
Product scenarios, not testimonials — this is the shipped behavior, demoable on day one.
Yesterday's commits, open approvals and today's schedule — assembled from APIs, delivered to the group, every number traceable.
Owners, decisions and deadlines extracted and filed to the doc space. Action items become tracked tasks with reminders.
Hedy comments on the merge request with project context — as a draft-first reviewer who cannot merge. Allowlisted repos only.
Retrieval scoped to what the asker may see. The answer links its source doc; what's ACL-filtered is declared, never leaked.
The week's activity ledger — reviews shipped, questions answered, hours saved — compiled into a report your boss actually reads.
Conduct tests ship in the eval gate: salary probes, credential requests and injection attempts are refused and audited.
SaaS agents ask you to ship your knowledge base, credentials and chat history to their cloud. Hedy takes the opposite bet.
| Hedy | Cloud AI employees | |
|---|---|---|
| Where your data lives | Your VPC — or air-gapped | Vendor cloud |
| Source auditable | Yes, by your security team | Rarely |
| Feishu & Lark native | First-class, plus Slack | Slack / Teams only |
| Conduct red-line testing | Shipped, runs in eval gate | Undisclosed |
| Model keys & token spend | Yours, metered locally | Vendor's, marked up |
| Pricing model | Flat per-seat licence | Usage credits |
You bring the model keys; tokens flow through your own gateway at cost. We charge for the software — flat, per seat, predictable.
Why flat? AI employees billed by usage penalize you for using them. A seat licence means Hedy working harder costs you nothing extra — the meter belongs to you.
A 30-minute demo on our infrastructure — then the same stack, deployed on yours.