---
title: "Slipform: More agents shouldn’t mean more to manage"
description: We built Slipform to move repeatable agent work out of chat and bring back the evidence, exceptions, and decisions that need you.
canonical: https://slipforms.ai/
---

# We wanted AI to do more work. Instead, we got more work to manage.

Agents made it easier to start. Keeping the work moving, reviewing it, and
remembering what happened still fell on us.

We were already using agents every day. They could research, write, analyze,
and build faster than we could alone. So we opened more threads and gave them
more work.

It looked like leverage. It did not feel like it.

Each new thread became another place to explain the job, check the progress,
correct the course, find the output, and reconstruct the context later. The
agents multiplied. So did the work of managing them.

> The agent was faster. We were busier.

## We stopped trying to manage more chats.

We asked a different question: what would it take to give an agent real work,
step away, and return to something we could inspect?

A better prompt was not enough. Repeatable work needed a shape. It needed clear
stages, the right context, a definition of done, routes for work that fell
short, and a clear place for human judgment.

Once the method was explicit, the unit of work was no longer a chat we had to
babysit. It was a run with a record. We could see what was moving, what had
stopped, what needed another pass, and what needed us.

## That experiment became Slipform.

Slipform is a Mac app for building repeatable agent workflows around how you
work. Start with your own method or a useful structure. Codex executes the work
today. Slipform keeps the stages, artifacts, evaluations, routes, and decisions
with each run.

When a run reaches a human gate, a person can Approve, Rework, or Fail. Slipform
records the decision. A person decides what changes before the next workflow
version.

Slipform does not learn how a person thinks, approve its own work, or revise a
workflow autonomously.

## We are still early.

The current beta works with Codex on Mac. People create the workflows, approve
the work, and own every revision. Broader runtime support is part of the
direction, not something shipped today.

We are building toward a workday where more agent work can move at once without
creating more work to supervise. A workday organized around evidence,
exceptions, and decisions instead of a wall of active chats.

That future is not finished. We are trying to reach it by doing real work,
studying real runs, and improving the system with people who feel this problem
too.

## Join the journey.

Already pushing agents beyond one-off chats? Bring real work. Tell us where
your current approach breaks. Help us learn what this way of working should
become.

The private-beta form records interest only. Requests are reviewed in small
cohorts and do not guarantee access or timing. If selected, a participant may
work directly with the Slipform team, but requesting access does not promise a
specific deliverable or outcome.

Current beta requires macOS 26 and Codex. The interest form collects an email
address, affirmative consent, consent version `beta-access-2026-07-16`, and a
server-authored consent timestamp. It does not collect a workflow description.

## Current product boundary

- Codex execution is supported today and is the only supported runtime in the
  current beta.
- Workflows can include stages, handoffs, authored decision paths, evidence
  requirements, evaluations, and human gates.
- Run records can retain activity, artifacts, evaluations, duration, token use,
  overrides, route, and review state.
- A person owns every approval and workflow revision.
- Workflows remain operator-controlled between human-approved revisions.
- Operator is Alpha. It coordinates bounded run actions while the Mac app is
  running. It does not approve work, revise workflows, or operate as an
  unattended approval system.
- Broader provider and model support is Product direction and is not shipped.
  Claude Code support is planned and is not yet shipped.
- Native Slipform emission of signed Agent Run Attestation records is not
  shipped.
- Autonomous workflow improvement, unattended approval, automatic model
  selection, performance-based routing, and token-savings claims are not
  shipped capabilities.

Decision paths are authored by people. Dynamic routing inside those paths does
not mean Slipform selects models or rewrites its own workflow.

## Evidence and public resources

- [One current-beta workflow and run record](https://slipforms.ai/evidence/deep-analysis-001/)
- [Why we started building Slipform](https://slipforms.ai/introducing-slipform/)
- [The earlier launch essay in Markdown](https://slipforms.ai/introducing-slipform.md)
- [Detailed product context](https://slipforms.ai/llms.txt)
- [Agent Skills index](https://slipforms.ai/.well-known/agent-skills/index.json)
- [Terms](https://slipforms.ai/terms/)
- [Privacy](https://slipforms.ai/privacy/)

The evidence record is one supporting example, not the product category, a
benchmark, customer proof, or a claim that a later run improved.

Slipform is operated by Kaska LLC. The public site does not currently expose a
developer API, remote MCP server, A2A agent, agent-commerce endpoint, or WebMCP
tool. The private `POST /api/waitlist` route is the transport behind a
human-consent form, not a public agent API.