Engineering excellence

Compare agent-authored work with human work on the same measures.

“Agents are writing code now. Is that work reaching anything that matters?”

Agent pull requests are read beside human ones on share of merged work, cycle time and cost. Each is linked to the goal it served.

In the product
Kestrel Bankdemo data
Initiative · expected to deliver 3 days of the improvementdemo

Income verified through open banking, not payslips

AI spend $56.25 on 3 pull requests · $2.30 matched by push

Work in progress

MORT-530Open-banking income, phase two

Self-employed applicants are the third of the manual income queue that phase one left behind.

Rahul Shahconfirmed
In Progress
  1. Story
    MORT-531Detect self-employed income from twelve months of transactions
    Rahul Shah
    In Progress
    1. Pull request
      mortgage-origination #648Self-employed income from transactions
      agent: ClaudeAI $38.40
      In review
    2. Pull request
      mortgage-origination #651Count regular transfers from a business account as income
      agent: Cursorsuggested, not confirmedAI $11.75
      Open
  2. Story
    MORT-532Show the applicant which transactions we counted as income
    To Do
  3. Bug
    MORT-533Consent screen times out on slow bank redirects
    Joe Barnes
    Done
    1. Pull request
      mortgage-origination #646Longer timeout on the bank consent redirect
      Joe BarnesAI $6.10, $2.30 matched by push
      Merged

The work under one goal, who shipped it — person or agent — and what each run cost.

What you get
  • People and agents on one boardLive

    Work under way by people and by agents appears on one board, grouped by the goal it serves.

  • Agent and human pull requests comparedLive

    See the share of merged pull requests written by agents, and their cycle time beside the human figure.

  • Cost of a pull requestLive

    Each pull request shows what its AI spend and people time came to, without timesheets.

  • Session spend tied to a branchLive

    Each Claude Code session's spend arrives tied to its repository and branch, so cost joins the pull request.

  • AI spend by goalLive

    See how much AI spend reached each goal, and how much reached none.

  • Agent work linked to its goalLive

    An agent's pull requests come back linked to the goal and the person who sent the work.

Live In the product today. Preview Working, refined with customers.

An example

Kestrel's CTO is asked whether coding agents are worth their cost.

  1. 01Agents wrote twenty-two percent of the quarter's merged pull requests on the lending platform, with a one-day median cycle time.
  2. 02The average agent pull request cost about a tenth of a comparable human one, counting AI spend and review time.
  3. 03Two thirds of agent work served the time to offer goal. A fifth of AI spend was linked to none.

Kestrel Bank is a fictional example. The figures are calculated by the product.

What you connect
  • GitHub
  • Claude Code
  • Anthropic
  • Cursor
  • Cursor agents
  • Devin
  • Claude

If a system you rely on is not listed, ask for it. Outcome’s integration builder drafts the connection, and it is offered to you to try before it is switched on. How the agents work

Beside the tools you have

The comparison uses your own teams' figures over time.

See how Outcome compares

Leaders can decide where agents are worth extending, using the cost and the result of work already shipped.

More in engineering excellence