Decision Intelligence

Code is cheap. Show me the decisions.

Your agents make dozens of choices in every change. Braid records each one as a decision you can read, question and trace, from review to production.

Install Braid

braidAdd cart totals

Decision D1Written by Claude Opus 5.5

Store prices as whole cents

How should the cart store prices?

Chosen approach

Whole cents as integers

$4.99 is stored as 499, so every total is exact.

Other approach considered

Dollars as decimal numbers

Why not 0.1 + 0.2 gives 0.30000000000000004, so totals drift by a cent.

Other approach considered

Text, like "4.99"

Why not Every sum must convert the text first.

cart/cart.go:10-17

8type Item struct {
9    Name       string
10    PriceCents int64 // $4.99 is 499
11    Qty        int64
12}
13
14func Total(items []Item) int64 {
15    var total int64
16    for _, it := range items {
17        total += it.PriceCents * it.Qty
18    }
19    return total
20}

TraceReasoning

Chosen approach

Whole cents as integers

How the agent got here

10:42:08
AskedPrompt
Add a cart that shows the order total.
10:42:15
Looked atTool call ×2
Read cart/cart.goRead db/schema.sql
10:42:31
WeighedDecision marker
Whole cents as integerschosen
$4.99 is stored as 499, so every total is exact.
In the agent's words
a float cannot hold 0.10 exactly, so store whole cents and every sum stays exact
Entry #4 at 10:42:31
What followed
Write cart/cart.goRun the cart tests
Dollars as decimal numbersset aside
0.1 + 0.2 gives 0.30000000000000004, so totals drift by a cent.
Text, like "4.99"set aside
Every sum must convert the text first.

Nobody reads code anymore.

Not because we stopped caring. Agents write code faster than anyone can read it. Braid keeps the goal and the decisions with the change, so the next reader starts from the reasons, not a bare diff.

without Braid
with Braid
trace
decision
intent

The developer
Own what you ship
Know what you're merging, and see the evidence for it.
The reviewer
Pass on the context
Your reviewer reads the reasons first, then the diff.
The organisation
Pick up where you left off
Months later, the why is still there, for you or a teammate.

What decisions do for you

A decision keeps working after the review.

Each decision stays linked to the code it shaped. It is there for the next reader, the next merge and the next agent.

Understand any change
See what your agent chose, what it set aside, and why. A long diff becomes a short list of decisions.
Review only what matters
Each decision shows the tests that cover it. You and your team spend review time on the few that nothing checks.
Merge safely
Before a change lands, Braid checks it against the decisions already on main, and stops one that quietly undoes another.
Trace any line to its reason
Ask why a line exists, in review or in production. Braid answers with the decision behind it and the request that started it.
Give your agents better context
Your agents read the decisions behind the code before they change it. They skip the approaches your team already set aside.

How it works

Know what your agent did. Decide what's next.

Once the work is committed, ask your agent to reconstruct the intent. Build a working model of its direction and decisions. Then fix a bad call, hand it to a reviewer, or pick it up next week. This is a real braid from the BrewGo sample app.

Decisions

See every choice, and the roads not taken.

Each decision shows the question the agent faced, the approach it picked, what it rejected and why, and the checks behind it. Inspect code jumps to the lines that decision shaped.

Review byStepsDecisionsWorkstreamsDiagrams

D4Return and validate analytics through the API
D5Open and close SQLite connections per list call
How should the SQLite repository manage database connections during list calls?
✓ Covered by 09 · Test SQLite order repository · Tests passed
Chosen approach
Open and close per list call
Each read sees current orders, and no database file stays open after the list returns.
Other approach considered
Keep one connection open
Not chosen: it would leave the database file open.
src/backend/app.js · lines 35–39
35 const db = new DatabaseSync(dbPath, { readOnly: true });
36 try {
37 return db.prepare('SELECT payload FROM orders ORDER BY id').all().map((row) => JSON.parse(row.payload));
38 } finally {
39 db.close();
D6Use normal read-only mode for WAL database access

Steps

Read the work in the order it happened.

Each step says what the agent did, the decision that drove it, and the files it touched. Open a file to land on the exact lines.

Review byStepsDecisionsWorkstreamsDiagrams9 steps · 6 decisions

06Test frontend analyticsD4
07Run full analytics testsD4
08Add SQLite order repositoryD5 D6
What
The SQLite order repository opens the database per list call, reads order payloads, and closes the file after returning rows.
Decisions
D5 Open and close SQLite connections per list call
D6 Use normal read-only mode for WAL database access
Files
src/backend/app.js
32 const { DatabaseSync } = require('node:sqlite');
33 return Object.freeze({
34 list() {
35 const db = new DatabaseSync(dbPath, { readOnly: true });
09Test SQLite order repositoryD5 D6

Workstreams

Know which agent did what.

When your agent splits the work, each subagent gets a workstream: the job it was given, the model that ran it, and the files it changed. Open the trace when you want the receipts.

Diagrams

See the shape of the change.

Diagrams map the components the change touched, how they call each other, and which calls a decision shaped. Select a component to get to its files.

Multiplayer

Settle the decision together.

Your team comments on the decision itself, next to the approaches and the reasons. When you agree on a fix, hand it to your agent. Today, share the intent on your pull request for teammates to read.

Review byStepsDecisionsWorkstreamsDiagrams

D4Return and validate analytics through the API
D5Open and close SQLite connections per list call
How should the SQLite repository manage database connections during list calls?
Chosen approach
Open and close per list call
Each read sees current orders, and no database file stays open after the list returns.
Other approach considered
Keep one connection open
Not chosen: it would leave the database file open.
Comments
1. P
  Priya 10:42
  I think one shared connection would be faster for the admin page. Is opening the file on every list worth it?
2. A
  Alex 10:51
  It keeps the file free for the Python API's writes. I'll ask my agent to measure both.
Add a comment

Multiplayer

Watch a teammate review the decisions.

Stop cognitive surrender
to your agents.

Install Braid

For macOS. Works with Claude Code and Codex.

Code is cheap. Show me the decisions.

Nobody reads code anymore.

Own what you ship

Pass on the context

Pick up where you left off

A decision keeps working after the review.

Understand any change

Review only what matters

Merge safely

Trace any line to its reason

Give your agents better context