$ cat ./what-your-end-users-see.md

ship the workflow experience your end-users actually want.
without writing it for them.

this is the view your B2B customer's end-users get when you embed Flowget — they describe what they need in chat, the agent composes from your typed catalog, and you keep the data, the bill, and the audit trail. their tenant never leaves your VPC.

the boundary your customers ask about

what your customer's data sees vs. what our control plane sees

your tenant sees everything

  • raw customer data, every field
  • secrets, tokens, credentials
  • full business logic
  • per-node inputs and outputs
  • the entire workflow history

our control plane never sees

  • customer plaintext (we hold ciphertext)
  • secrets — never leave your worker
  • your business logic — it runs in your VPC
  • raw inputs / outputs of any node
  • chat content — the agent runs in your worker too

we orchestrate. we never see the bytes. when your customer's legal team asks what crosses the line, you can answer with the full list — and it's metadata, not content.

$ recordings/end-user-builder.gifreal product
real builder · screenshot pending
16:9 · gif / mp4 / webm · swap in RealBuilderSlot.tsx

this is what your end-user actually sees — describe an automation in chat, the agent composes from your catalog, the graph appears, they approve. swap in the real recording when ready.

describe → composed

the agent builds from your catalog.

your customer says "when an order comes in, check risk score; if low, charge — if high, escalate." the agent composes the graph from operations you declared. no hallucinated steps. no made-up fields. catalog-grounded by construction.

always a draft

nothing fires until they approve.

generated workflows land disabled. your customer reviews the graph, tests in sandbox, then enables. no silent prod changes — the agent never ships an automation behind their back.

conversation, not commands

refine in chat. review the diff.

"change the threshold to 750." the agent updates the graph; your customer sees a one-line diff. no drag-drop required — though the visual builder is there if they want it.

their data stays put

our cluster never sees plaintext.

workflows run inside your environment. payloads cross our cluster as ciphertext. the AI authoring agent itself runs in your worker — the same BYO-worker boundary that protects domain data extends to the model. (the agent calls the LLM you wired in, on your key — what crosses your VPC to that provider is yours to log, redact, or route.)

see what they pay for

every run, itemized.

per-node cost on every execution — LLM tokens, API calls, compute, storage. if a number changes, the breakdown changes with it. trust by default. (or hide it entirely — that's your call as the host product.)

audit-ready

every decision, replayable.

every run produces a deterministic history. every approval is logged with who, what, when. when the regulator asks what happened on March 14th, your customer shows them the same view your compliance team sees.

the experience you ship. the data you keep.

this is what we ship for your customers — in alpha, choosing partners carefully. talk to us first; ship together.