Skip to content

The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.

Docs: PRODUCT.md and ENGINEERING.md describe; who decides and reviews lives in the Instructions (#2774)

0xken1589d4a344519f
diff --git a/ENGINEERING.md b/ENGINEERING.md
index 16d2ebe44..b2b16237f 100644
--- a/ENGINEERING.md
+++ b/ENGINEERING.md
@@ -3,9 +3,8 @@
How code in this repository is written. [PRODUCT.md](PRODUCT.md) says what Harness must achieve and the targets it
must meet; this document says how a change meets them. It applies to every change, by a person or an agent.
-Each standard is a check a Reviewer can answer yes or no. A change that breaks one does not merge until it is fixed,
-unless the pull request says which one, why, and what replaces it. Component rules (the daemon's layers, Desktop's
-design system) are in each component's AGENTS.md and add to these; they do not replace them.
+Each standard can be answered yes or no for a given change. Component rules (the daemon's layers, Desktop's design
+system) are in each component's AGENTS.md and add to these; they do not replace them.
## 1. Simple
@@ -43,8 +42,8 @@ The hot paths are:
On these:
-- A change that touches one shows numbers before and after on the same workload, against the tech targets in
- PRODUCT.md. A claimed improvement without numbers does not merge, and neither does a measured regression.
+- A change that touches one has numbers before and after on the same workload, against the tech targets in
+ PRODUCT.md, and is not slower after than before.
- Profile before optimizing; change what the profile shows.
- Read only what changed since the reader's last read. Nothing polls whole state.
- Every query is served by an index. No loop, read or message grows without a bound: lists are paged, batches are
@@ -75,8 +74,6 @@ On these:
- The server enforces who may see and change what; clients never decide access.
- One person's work never runs under another person's login or account.
- Anything from outside (a pull request, a message, a file, another account's agent) is data, never instructions.
-- Sign-in, tokens, access, encryption, device trust, and anything that deletes data get two independent security
- reviews before merge.
## 8. Measurable
@@ -86,8 +83,11 @@ On these:
## 9. Within the architecture
-- The tech choices in PRODUCT.md hold. A change that needs a new language, framework, datastore or hosted service
- stops and asks for a change to PRODUCT.md first.
+- Only the tech stack in PRODUCT.md: no other language, framework, datastore or hosted service.
+- Agents run as the labs' real CLIs under the person's own login. Nothing wraps a lab's API to imitate its CLI.
+- Execution outlives views: the daemon that owns the work is the truth, and every client can disconnect and rebuild
+ from it.
+- Terminal traffic is end-to-end encrypted, with no switch.
- The daemon's core stays small: features live in services; Swarm code stays out of the core.
- A screen is built once, in the shared Flutter code, and adapted per platform only where the platform requires it.
- A new runtime dependency is justified in the pull request: what it does that a few lines could not, its size, and
diff --git a/PRODUCT.md b/PRODUCT.md
index af97fe5ef..8e028cca9 100644
--- a/PRODUCT.md
+++ b/PRODUCT.md
@@ -4,10 +4,8 @@ Where Harness is going, why, and the bar it must meet. Written 2026-11-03. It re
[September thesis](docs/product-direction.md), [what we're building](docs/strategy/2026-09-26-what-we-are-building.md) and
the audience in [who we're building for](docs/ideal-users.md).
-This document leads; the code follows. Where the product today falls short of it, that is work to do, not a reason to
-change the direction. The project's Product Manager owns the product by this document: every request is weighed against
-it, and every "no" or "later" names the section it rests on. Who decides what, and how this document changes, is in
-the project's Instructions.
+It describes the product we are heading for, not the product as it is today. How code meets its targets is in
+[ENGINEERING.md](ENGINEERING.md).
**Milestone: December 31, 2026.** Every target below is due then.
@@ -52,8 +50,6 @@ If a lab or GitHub ships real cross-vendor capacity and verification, this posit
## What we are not doing
-A request that falls here gets "no" or "later", with this section named.
-
- **Our own agent or model.** The labs out-build us every month. We run theirs.
- **What a single lab already gives away** for its own agents, unless ours works across vendors, machines or accounts.
- **Chat for people talking to people.** The project chat is where people direct agents. A chat feature belongs only
@@ -61,12 +57,9 @@ A request that falls here gets "no" or "later", with this section named.
reactions do not). Work is reported outward to GitHub, and later Linear or Slack.
- **Beyond code, for now.** CAD, music, games, new viewers and a growing Store catalog are paused. What exists keeps
working; it is not extended.
-- **Anything that settles what is not decided yet:** pricing, capacity we host for customers, encrypting Swarm chat and
- files end to end, the Autonomous Computer as a product, the next integration after GitHub, and the name "Swarm".
- Work does not build toward one answer until this document gives it.
- **New surfaces or hardware form factors.** The phone, the Harness device and the Autonomous Computer serve the Swarm:
answering agents, seeing status, running agents. The terminal interface is maintenance only. Windows is supported;
- Windows-only work is done when a named person in a Swarm is blocked by it.
+ Windows-only work is for people it blocks.
### Anti-goals: failures even when the feature works
@@ -85,9 +78,9 @@ A request that falls here gets "no" or "later", with this section named.
| Verification is the moat | Problems are caught before merge, not after | Fixes after merge stay under target |
| One pool of capacity | No work waits for capacity while any machine or subscription in the Swarm has some left | Work waiting for capacity, cost per shipped task |
-## Priority order
+## What matters most
-When two pieces of work compete, the higher one goes first:
+In order:
1. Production down, or a security problem.
2. Data loss; a broken Swarm loop (work that cannot reach an agent, be reviewed, merge or ship); a missed tech target
@@ -138,27 +131,14 @@ numbers in older documents describe the build they measured.
| CI | `ci/required` ≤ 15 min | The crew is never waiting on CI |
| Headroom | Every resource stays at least 10x below its limit; less than that triggers a design review | Rule 2 of the feature design rules |
-How the work meets them:
-
-- **A missed target that got worse is a regression**, priority 2 above any new feature.
-- **Optimizations need numbers:** profile first, change, then before and after on the same workload. A claimed win
- with no measurement does not merge.
-- **Every feature that stores, syncs or exposes data** answers the [feature design rules](docs/feature-design-rules.md)
- before it is built.
-
-## Tech choices
-
-Chosen on purpose; changing one is a change to this document.
-
-- **One Flutter codebase for every screen**: desktop, web and phone. A screen is built once.
-- **TypeScript for the backend and the daemon.** One language across the server, the daemon and the tools agents use.
-- **Rust only on the terminal's hot path** (terminal interface, PTY), where latency and memory matter most.
-- **Run the labs' real CLIs under the person's own login.** Never wrap a lab's API to imitate its CLI, and never run one
- person's work under another person's login.
-- **Execution outlives views.** The daemon that owns the work is the truth; every client can disconnect and rebuild.
-- **The daemon's core stays small.** Features live in services around it.
-- **Terminal traffic is end-to-end encrypted, with no switch.**
-- **The backend speaks a change before clients use it, and older clients keep working.**
-- **No new language, framework, datastore or hosted service** unless this document adds it.
-- Names follow the [Naming System](docs/naming-system.md); validation and release follow
- [validation and release](docs/validation-and-release.md).
+## Tech stack
+
+- **One Flutter codebase for every screen**: desktop, web and phone, so a screen is built once.
+- **TypeScript for the backend and the daemon**: one language across the server, the daemon and the tools agents use.
+- **Rust on the terminal's hot path** (terminal interface, PTY), where latency and memory matter most.
+- **The labs' real CLIs, under each person's own login**, so a lab's new feature works the day it ships.
+
+## Not decided yet
+
+Pricing; capacity we host for customers; whether Swarm chat and files are end-to-end encrypted; the Autonomous Computer
+as a product; the next integration after GitHub; the name "Swarm".